2D view (faster)

app.py

@@ -3,37 +3,51 @@ from src.utils import *
 
 if __name__ == '__main__':
     theme = gr.themes.Soft(primary_hue="emerald", secondary_hue="stone", font=[gr.themes.GoogleFont("Source Sans 3", weights=(400, 600)),'arial'])
-    
-    with gr.Blocks(theme=theme) as demo:
-        with gr.Column(elem_classes="header"):
-            gr.Markdown("# 🏔 MESA: Text-Driven Terrain Generation Using Latent Diffusion and Global Copernicus Data")
-            gr.Markdown("### Paul Borne–Pons, Mikolaj Czerkawski, Rosalie Martin, Romain Rouffet")
-            gr.Markdown('[[Website](https://paulbornep.github.io/mesa-terrain/)] [[GitHub](https://github.com/PaulBorneP/MESA)] [[Model](https://huggingface.co/NewtNewt/MESA)] [[Dataset](https://huggingface.co/datasets/Major-TOM/Core-DEM)]')
-            
-        with gr.Column(elem_classes="abstract"):
-            gr.Markdown("MESA is a novel generative model based on latent denoising diffusion capable of generating 2.5D representations of terrain based on the text prompt conditioning supplied via natural language. The model produces two co-registered modalities of optical and depth maps.") # Replace with your abstract text
-            gr.Markdown("This is a test version of the demo app. Please be aware that MESA supports primarily complex, mountainous terrains as opposed to flat land")
-            gr.Markdown("> ⚠️ **The generated image is quite large, so for the larger resolution (768) it might take a while to load the surface**")
-    
+
+with gr.Blocks(theme=theme) as demo:
+    with gr.Column(elem_classes="header"):
+        gr.Markdown("# 🏔 MESA: Text-Driven Terrain Generation Using Latent Diffusion and Global Copernicus Data")
+        gr.Markdown("### Paul Borne–Pons, Mikolaj Czerkawski, Rosalie Martin, Romain Rouffet")
+        gr.Markdown('[[Website](https://paulbornep.github.io/mesa-terrain/)] [[GitHub](https://github.com/PaulBorneP/MESA)] [[Model](https://huggingface.co/NewtNewt/MESA)] [[Dataset](https://huggingface.co/datasets/Major-TOM/Core-DEM)]')
+
+    with gr.Column(elem_classes="abstract"):
+        gr.Markdown("MESA is a novel generative model based on latent denoising diffusion capable of generating 2.5D representations of terrain based on the text prompt conditioning supplied via natural language. The model produces two co-registered modalities of optical and depth maps.") # Replace with your abstract text
+        gr.Markdown("This is a test version of the demo app. Please be aware that MESA supports primarily complex, mountainous terrains as opposed to flat land")
+        gr.Markdown("> ⚠️ **The generated image is quite large, so for the larger resolution (768) it might take a while to load the surface**")
         with gr.Row():
-            prompt_input = gr.Textbox(lines=2, placeholder="Enter a terrain description...")
-            generate_button = gr.Button("Generate Terrain", variant="primary")
-    
-        model_output = gr.Model3D(
-            camera_position=[90, 180, 512]
-        )
-    
+            prompt_input = gr.Textbox(lines=2, placeholder="Enter a terrain description...")            
+
+        with gr.Tabs() as output_tabs:
+            with gr.Tab("2D View (Fast)"):
+                generate_2d_button = gr.Button("Generate Terrain", variant="primary")
+                with gr.Row():
+                    rgb_output = gr.Image(label="RGB Image")
+                    elevation_output = gr.Image(label="Elevation Map")
+                    
+            with gr.Tab("3D View (Slow)"):
+                generate_3d_button = gr.Button("Generate Terrain", variant="primary")
+                model_3d_output = gr.Model3D(
+                    camera_position=[90, 135, 512]
+                )
+
         with gr.Accordion("Advanced Options", open=False) as advanced_options:
             num_inference_steps_slider = gr.Slider(minimum=10, maximum=1000, step=10, value=50, label="Inference Steps")
             guidance_scale_slider = gr.Slider(minimum=1.0, maximum=15.0, step=0.5, value=7.5, label="Guidance Scale")
             seed_number = gr.Number(value=6378, label="Seed")
-            crop_size_slider = gr.Slider(minimum=128, maximum=768, step=64, value=512, label="Crop Size")
+            crop_size_slider = gr.Slider(minimum=128, maximum=768, step=64, value=512, label="(3D Only) Crop Size")
+            vertex_count_slider = gr.Slider(minimum=0, maximum=10000, step=0, value=0, label="(3D Only) Vertex Count (Default: 0 - no reduction)")
             prefix_textbox = gr.Textbox(label="Prompt Prefix", value="A Sentinel-2 image of ")
-    
-        generate_button.click(
-            fn=generate_and_display,
-            inputs=[prompt_input, num_inference_steps_slider, guidance_scale_slider, seed_number, crop_size_slider, prefix_textbox],
-            outputs=model_output,
+            
+        generate_2d_button.click(
+            fn=generate_2d_view_output,
+            inputs=[prompt_input, num_inference_steps_slider, guidance_scale_slider, seed_number, prefix_textbox],
+            outputs=[rgb_output, elevation_output],
+        )
+
+        generate_3d_button.click(
+            fn=generate_3d_view_output,
+            inputs=[prompt_input, num_inference_steps_slider, guidance_scale_slider, seed_number, crop_size_slider, vertex_count_slider, prefix_textbox],
+            outputs=[model_3d_output],
         )
         
-        demo.queue().launch()
+        demo.queue().launch(share=True)

src/.ipynb_checkpoints/build_pipe-checkpoint.py

@@ -1,22 +0,0 @@
-from .pipeline_terrain import TerrainDiffusionPipeline
-#import models
-from huggingface_hub import hf_hub_download, snapshot_download
-import os
-import torch
-
-def build_pipe():
-    print('Downloading weights...')
-    try:
-        os.mkdir('./weights/')
-    except:
-        True
-    snapshot_download(repo_id="NewtNewt/MESA", local_dir="./weights")
-    weight_path = './weights'
-    print('[DONE]')
-    
-    print('Instantiating Model...')
-    pipe = TerrainDiffusionPipeline.from_pretrained(weight_path, torch_dtype=torch.float16)
-    pipe.to("cuda")
-    print('[DONE]')
-    
-    return pipe

src/.ipynb_checkpoints/models-checkpoint.py

@@ -1,1528 +0,0 @@
-from torch import nn
-from torch.nn import functional as F
-from diffusers import UNet2DConditionModel
-import torch
-
-def init_dem_channels(model,conv_in=None,conv_out=None):
-        """
-        Add a channel to the input and output of the model, with 0 initialization
-        """
-        # add one channel to the input and output, with 0 initialization
-        if conv_in is not None:
-            # add a channel to the input of the encoder  
-            pretrained_in_weights = conv_in.weight.clone()
-            pretrained_in_bias = conv_in.bias.clone()
-
-            with torch.no_grad():
-                # weight matrix is of shape (out_channels, in_channels, kernel_size, kernel_size)
-                model.conv_in.weight[:, :4, :, :] = pretrained_in_weights
-                model.conv_in.weight[:, 4:, :, :] = 0
-                # bias vector is of shape (out_channels) no need to change it
-                model.conv_in.bias[...] = pretrained_in_bias
-
-
-
-        if conv_out is not None:
-            # add a channel to the output of the decoder
-            pretrained_out_weights = conv_out.weight.clone()
-            pretrained_out_bias = conv_out.bias.clone()
-
-            with torch.no_grad():
-                # weight matrix is of shape (out_channels, in_channels, kernel_size, kernel_size)
-                model.conv_out.weight[:4, :,  :, :] = pretrained_out_weights
-                model.conv_out.weight[4:, :, :, :] = 0
-                # bias vector is of shape (out_channels) 
-                model.conv_out.bias[:4] = pretrained_out_bias
-                model.conv_out.bias[4:] = 0
-                    # Ensure the new layers are registered
-                model.register_to_config()
-        
-        return model
-
-
-
-
-# Copyright 2024 The HuggingFace Team. All rights reserved.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-from dataclasses import dataclass
-from typing import Any, Dict, List, Optional, Tuple, Union
-
-import torch
-import torch.nn as nn
-import torch.utils.checkpoint
-import diffusers
-
-from diffusers.configuration_utils import ConfigMixin, register_to_config
-from diffusers.loaders import PeftAdapterMixin, UNet2DConditionLoadersMixin
-from diffusers.loaders.single_file_model import FromOriginalModelMixin
-from diffusers.utils import USE_PEFT_BACKEND, BaseOutput, deprecate, logging, scale_lora_layers, unscale_lora_layers
-from diffusers.models.activations import get_activation
-from diffusers.models.attention_processor import (
-    ADDED_KV_ATTENTION_PROCESSORS,
-    CROSS_ATTENTION_PROCESSORS,
-    Attention,
-    AttentionProcessor,
-    AttnAddedKVProcessor,
-    AttnProcessor,
-    FusedAttnProcessor2_0,
-)
-from diffusers.models.embeddings import (
-    GaussianFourierProjection,
-    GLIGENTextBoundingboxProjection,
-    ImageHintTimeEmbedding,
-    ImageProjection,
-    ImageTimeEmbedding,
-    TextImageProjection,
-    TextImageTimeEmbedding,
-    TextTimeEmbedding,
-    TimestepEmbedding,
-    Timesteps,
-)
-from diffusers.models.modeling_utils import ModelMixin
-from diffusers.models.unets.unet_2d_blocks import (
-    get_down_block,
-    get_mid_block,
-    get_up_block,
-)
-
-
-logger = logging.get_logger(__name__)  # pylint: disable=invalid-name
-
-
-@dataclass
-class UNet2DConditionOutput(BaseOutput):
-    """
-    The output of [`UNet2DConditionModel`].
-
-    Args:
-        sample (`torch.Tensor` of shape `(batch_size, num_channels, height, width)`):
-            The hidden states output conditioned on `encoder_hidden_states` input. Output of last layer of model.
-    """
-
-    sample: torch.Tensor = None
-
-
-class UNetDEMConditionModel(
-    ModelMixin, ConfigMixin, FromOriginalModelMixin, UNet2DConditionLoadersMixin, PeftAdapterMixin
-):
-    r"""
-    A conditional 2D UNet model that takes a noisy sample, conditional state, and a timestep and returns a sample
-    shaped output.
-
-    This model inherits from [`ModelMixin`]. Check the superclass documentation for it's generic methods implemented
-    for all models (such as downloading or saving).
-
-    Parameters:
-        sample_size (`int` or `Tuple[int, int]`, *optional*, defaults to `None`):
-            Height and width of input/output sample.
-        in_channels (`int`, *optional*, defaults to 4): Number of channels in the input sample.
-        out_channels (`int`, *optional*, defaults to 4): Number of channels in the output.
-        center_input_sample (`bool`, *optional*, defaults to `False`): Whether to center the input sample.
-        flip_sin_to_cos (`bool`, *optional*, defaults to `True`):
-            Whether to flip the sin to cos in the time embedding.
-        freq_shift (`int`, *optional*, defaults to 0): The frequency shift to apply to the time embedding.
-        down_block_types (`Tuple[str]`, *optional*, defaults to `("CrossAttnDownBlock2D", "CrossAttnDownBlock2D", "CrossAttnDownBlock2D", "DownBlock2D")`):
-            The tuple of downsample blocks to use.
-        mid_block_type (`str`, *optional*, defaults to `"UNetMidBlock2DCrossAttn"`):
-            Block type for middle of UNet, it can be one of `UNetMidBlock2DCrossAttn`, `UNetMidBlock2D`, or
-            `UNetMidBlock2DSimpleCrossAttn`. If `None`, the mid block layer is skipped.
-        up_block_types (`Tuple[str]`, *optional*, defaults to `("UpBlock2D", "CrossAttnUpBlock2D", "CrossAttnUpBlock2D", "CrossAttnUpBlock2D")`):
-            The tuple of upsample blocks to use.
-        only_cross_attention(`bool` or `Tuple[bool]`, *optional*, default to `False`):
-            Whether to include self-attention in the basic transformer blocks, see
-            [`~models.attention.BasicTransformerBlock`].
-        block_out_channels (`Tuple[int]`, *optional*, defaults to `(320, 640, 1280, 1280)`):
-            The tuple of output channels for each block.
-        layers_per_block (`int`, *optional*, defaults to 2): The number of layers per block.
-        downsample_padding (`int`, *optional*, defaults to 1): The padding to use for the downsampling convolution.
-        mid_block_scale_factor (`float`, *optional*, defaults to 1.0): The scale factor to use for the mid block.
-        dropout (`float`, *optional*, defaults to 0.0): The dropout probability to use.
-        act_fn (`str`, *optional*, defaults to `"silu"`): The activation function to use.
-        norm_num_groups (`int`, *optional*, defaults to 32): The number of groups to use for the normalization.
-            If `None`, normalization and activation layers is skipped in post-processing.
-        norm_eps (`float`, *optional*, defaults to 1e-5): The epsilon to use for the normalization.
-        cross_attention_dim (`int` or `Tuple[int]`, *optional*, defaults to 1280):
-            The dimension of the cross attention features.
-        transformer_layers_per_block (`int`, `Tuple[int]`, or `Tuple[Tuple]` , *optional*, defaults to 1):
-            The number of transformer blocks of type [`~models.attention.BasicTransformerBlock`]. Only relevant for
-            [`~models.unets.unet_2d_blocks.CrossAttnDownBlock2D`], [`~models.unets.unet_2d_blocks.CrossAttnUpBlock2D`],
-            [`~models.unets.unet_2d_blocks.UNetMidBlock2DCrossAttn`].
-        reverse_transformer_layers_per_block : (`Tuple[Tuple]`, *optional*, defaults to None):
-            The number of transformer blocks of type [`~models.attention.BasicTransformerBlock`], in the upsampling
-            blocks of the U-Net. Only relevant if `transformer_layers_per_block` is of type `Tuple[Tuple]` and for
-            [`~models.unets.unet_2d_blocks.CrossAttnDownBlock2D`], [`~models.unets.unet_2d_blocks.CrossAttnUpBlock2D`],
-            [`~models.unets.unet_2d_blocks.UNetMidBlock2DCrossAttn`].
-        encoder_hid_dim (`int`, *optional*, defaults to None):
-            If `encoder_hid_dim_type` is defined, `encoder_hidden_states` will be projected from `encoder_hid_dim`
-            dimension to `cross_attention_dim`.
-        encoder_hid_dim_type (`str`, *optional*, defaults to `None`):
-            If given, the `encoder_hidden_states` and potentially other embeddings are down-projected to text
-            embeddings of dimension `cross_attention` according to `encoder_hid_dim_type`.
-        attention_head_dim (`int`, *optional*, defaults to 8): The dimension of the attention heads.
-        num_attention_heads (`int`, *optional*):
-            The number of attention heads. If not defined, defaults to `attention_head_dim`
-        resnet_time_scale_shift (`str`, *optional*, defaults to `"default"`): Time scale shift config
-            for ResNet blocks (see [`~models.resnet.ResnetBlock2D`]). Choose from `default` or `scale_shift`.
-        class_embed_type (`str`, *optional*, defaults to `None`):
-            The type of class embedding to use which is ultimately summed with the time embeddings. Choose from `None`,
-            `"timestep"`, `"identity"`, `"projection"`, or `"simple_projection"`.
-        addition_embed_type (`str`, *optional*, defaults to `None`):
-            Configures an optional embedding which will be summed with the time embeddings. Choose from `None` or
-            "text". "text" will use the `TextTimeEmbedding` layer.
-        addition_time_embed_dim: (`int`, *optional*, defaults to `None`):
-            Dimension for the timestep embeddings.
-        num_class_embeds (`int`, *optional*, defaults to `None`):
-            Input dimension of the learnable embedding matrix to be projected to `time_embed_dim`, when performing
-            class conditioning with `class_embed_type` equal to `None`.
-        time_embedding_type (`str`, *optional*, defaults to `positional`):
-            The type of position embedding to use for timesteps. Choose from `positional` or `fourier`.
-        time_embedding_dim (`int`, *optional*, defaults to `None`):
-            An optional override for the dimension of the projected time embedding.
-        time_embedding_act_fn (`str`, *optional*, defaults to `None`):
-            Optional activation function to use only once on the time embeddings before they are passed to the rest of
-            the UNet. Choose from `silu`, `mish`, `gelu`, and `swish`.
-        timestep_post_act (`str`, *optional*, defaults to `None`):
-            The second activation function to use in timestep embedding. Choose from `silu`, `mish` and `gelu`.
-        time_cond_proj_dim (`int`, *optional*, defaults to `None`):
-            The dimension of `cond_proj` layer in the timestep embedding.
-        conv_in_kernel (`int`, *optional*, default to `3`): The kernel size of `conv_in` layer.
-        conv_out_kernel (`int`, *optional*, default to `3`): The kernel size of `conv_out` layer.
-        projection_class_embeddings_input_dim (`int`, *optional*): The dimension of the `class_labels` input when
-            `class_embed_type="projection"`. Required when `class_embed_type="projection"`.
-        class_embeddings_concat (`bool`, *optional*, defaults to `False`): Whether to concatenate the time
-            embeddings with the class embeddings.
-        mid_block_only_cross_attention (`bool`, *optional*, defaults to `None`):
-            Whether to use cross attention with the mid block when using the `UNetMidBlock2DSimpleCrossAttn`. If
-            `only_cross_attention` is given as a single boolean and `mid_block_only_cross_attention` is `None`, the
-            `only_cross_attention` value is used as the value for `mid_block_only_cross_attention`. Default to `False`
-            otherwise.
-    """
-
-    _supports_gradient_checkpointing = True
-    _no_split_modules = ["BasicTransformerBlock", "ResnetBlock2D", "CrossAttnUpBlock2D"]
-
-    @register_to_config
-    def __init__(
-        self,
-        sample_size: Optional[int] = None,
-        in_channels: int = 8,
-        out_channels: int = 8,
-        center_input_sample: bool = False,
-        flip_sin_to_cos: bool = True,
-        freq_shift: int = 0,
-        down_block_types: Tuple[str] = (
-            "CrossAttnDownBlock2D",
-            "CrossAttnDownBlock2D",
-            "CrossAttnDownBlock2D",
-            "DownBlock2D",
-        ),
-        mid_block_type: Optional[str] = "UNetMidBlock2DCrossAttn",
-        up_block_types: Tuple[str] = ("UpBlock2D", "CrossAttnUpBlock2D", "CrossAttnUpBlock2D", "CrossAttnUpBlock2D"),
-        only_cross_attention: Union[bool, Tuple[bool]] = False,
-        block_out_channels: Tuple[int] = (320, 640, 1280, 1280),
-        layers_per_block: Union[int, Tuple[int]] = 2,
-        downsample_padding: int = 1,
-        mid_block_scale_factor: float = 1,
-        dropout: float = 0.0,
-        act_fn: str = "silu",
-        norm_num_groups: Optional[int] = 32,
-        norm_eps: float = 1e-5,
-        cross_attention_dim: Union[int, Tuple[int]] = 1280,
-        transformer_layers_per_block: Union[int, Tuple[int], Tuple[Tuple]] = 1,
-        reverse_transformer_layers_per_block: Optional[Tuple[Tuple[int]]] = None,
-        encoder_hid_dim: Optional[int] = None,
-        encoder_hid_dim_type: Optional[str] = None,
-        attention_head_dim: Union[int, Tuple[int]] = 8,
-        num_attention_heads: Optional[Union[int, Tuple[int]]] = None,
-        dual_cross_attention: bool = False,
-        use_linear_projection: bool = False,
-        class_embed_type: Optional[str] = None,
-        addition_embed_type: Optional[str] = None,
-        addition_time_embed_dim: Optional[int] = None,
-        num_class_embeds: Optional[int] = None,
-        upcast_attention: bool = False,
-        resnet_time_scale_shift: str = "default",
-        resnet_skip_time_act: bool = False,
-        resnet_out_scale_factor: float = 1.0,
-        time_embedding_type: str = "positional",
-        time_embedding_dim: Optional[int] = None,
-        time_embedding_act_fn: Optional[str] = None,
-        timestep_post_act: Optional[str] = None,
-        time_cond_proj_dim: Optional[int] = None,
-        conv_in_kernel: int = 3,
-        conv_out_kernel: int = 3,
-        projection_class_embeddings_input_dim: Optional[int] = None,
-        attention_type: str = "default",
-        class_embeddings_concat: bool = False,
-        mid_block_only_cross_attention: Optional[bool] = None,
-        cross_attention_norm: Optional[str] = None,
-        addition_embed_type_num_heads: int = 64,
-    ):
-        super().__init__()
-
-        self.sample_size = sample_size
-
-        if num_attention_heads is not None:
-            raise ValueError(
-                "At the moment it is not possible to define the number of attention heads via `num_attention_heads` because of a naming issue as described in https://github.com/huggingface/diffusers/issues/2011#issuecomment-1547958131. Passing `num_attention_heads` will only be supported in diffusers v0.19."
-            )
-
-        # If `num_attention_heads` is not defined (which is the case for most models)
-        # it will default to `attention_head_dim`. This looks weird upon first reading it and it is.
-        # The reason for this behavior is to correct for incorrectly named variables that were introduced
-        # when this library was created. The incorrect naming was only discovered much later in https://github.com/huggingface/diffusers/issues/2011#issuecomment-1547958131
-        # Changing `attention_head_dim` to `num_attention_heads` for 40,000+ configurations is too backwards breaking
-        # which is why we correct for the naming here.
-        num_attention_heads = num_attention_heads or attention_head_dim
-
-        # Check inputs
-        self._check_config(
-            down_block_types=down_block_types,
-            up_block_types=up_block_types,
-            only_cross_attention=only_cross_attention,
-            block_out_channels=block_out_channels,
-            layers_per_block=layers_per_block,
-            cross_attention_dim=cross_attention_dim,
-            transformer_layers_per_block=transformer_layers_per_block,
-            reverse_transformer_layers_per_block=reverse_transformer_layers_per_block,
-            attention_head_dim=attention_head_dim,
-            num_attention_heads=num_attention_heads,
-        )
-
-        # input
-        conv_in_padding = (conv_in_kernel - 1) // 2
-        self.conv_in_img = nn.Conv2d(
-            in_channels, block_out_channels[0], kernel_size=conv_in_kernel, padding=conv_in_padding
-        )
-        self.conv_in_dem = nn.Conv2d(
-            in_channels, block_out_channels[0], kernel_size=conv_in_kernel, padding=conv_in_padding
-        )
-
-        # time
-        time_embed_dim, timestep_input_dim = self._set_time_proj(
-            time_embedding_type,
-            block_out_channels=block_out_channels,
-            flip_sin_to_cos=flip_sin_to_cos,
-            freq_shift=freq_shift,
-            time_embedding_dim=time_embedding_dim,
-        )
-
-        self.time_embedding = TimestepEmbedding(
-            timestep_input_dim,
-            time_embed_dim,
-            act_fn=act_fn,
-            post_act_fn=timestep_post_act,
-            cond_proj_dim=time_cond_proj_dim,
-        )
-
-        self._set_encoder_hid_proj(
-            encoder_hid_dim_type,
-            cross_attention_dim=cross_attention_dim,
-            encoder_hid_dim=encoder_hid_dim,
-        )
-
-        # class embedding
-        self._set_class_embedding(
-            class_embed_type,
-            act_fn=act_fn,
-            num_class_embeds=num_class_embeds,
-            projection_class_embeddings_input_dim=projection_class_embeddings_input_dim,
-            time_embed_dim=time_embed_dim,
-            timestep_input_dim=timestep_input_dim,
-        )
-
-        self._set_add_embedding(
-            addition_embed_type,
-            addition_embed_type_num_heads=addition_embed_type_num_heads,
-            addition_time_embed_dim=addition_time_embed_dim,
-            cross_attention_dim=cross_attention_dim,
-            encoder_hid_dim=encoder_hid_dim,
-            flip_sin_to_cos=flip_sin_to_cos,
-            freq_shift=freq_shift,
-            projection_class_embeddings_input_dim=projection_class_embeddings_input_dim,
-            time_embed_dim=time_embed_dim,
-        )
-
-        if time_embedding_act_fn is None:
-            self.time_embed_act = None
-        else:
-            self.time_embed_act = get_activation(time_embedding_act_fn)
-
-        self.down_blocks = nn.ModuleList([])
-        self.up_blocks = nn.ModuleList([])
-
-        if isinstance(only_cross_attention, bool):
-            if mid_block_only_cross_attention is None:
-                mid_block_only_cross_attention = only_cross_attention
-
-            only_cross_attention = [only_cross_attention] * len(down_block_types)
-
-        if mid_block_only_cross_attention is None:
-            mid_block_only_cross_attention = False
-
-        if isinstance(num_attention_heads, int):
-            num_attention_heads = (num_attention_heads,) * len(down_block_types)
-
-        if isinstance(attention_head_dim, int):
-            attention_head_dim = (attention_head_dim,) * len(down_block_types)
-
-        if isinstance(cross_attention_dim, int):
-            cross_attention_dim = (cross_attention_dim,) * len(down_block_types)
-
-        if isinstance(layers_per_block, int):
-            layers_per_block = [layers_per_block] * len(down_block_types)
-
-        if isinstance(transformer_layers_per_block, int):
-            transformer_layers_per_block = [transformer_layers_per_block] * len(down_block_types)
-
-        if class_embeddings_concat:
-            # The time embeddings are concatenated with the class embeddings. The dimension of the
-            # time embeddings passed to the down, middle, and up blocks is twice the dimension of the
-            # regular time embeddings
-            blocks_time_embed_dim = time_embed_dim * 2
-        else:
-            blocks_time_embed_dim = time_embed_dim
-
-        # down
-        output_channel = block_out_channels[0]
-
-
-        for i, down_block_type in enumerate(down_block_types):
-            input_channel = output_channel
-            output_channel = block_out_channels[i]
-            is_final_block = i == len(block_out_channels) - 1
-            down_block_kwargs = {"down_block_type":down_block_type,
-                                    "num_layers":layers_per_block[i],
-                                    "transformer_layers_per_block":transformer_layers_per_block[i],
-                                    "in_channels":input_channel,
-                                    "out_channels":output_channel,
-                                    "temb_channels":blocks_time_embed_dim,
-                                    "add_downsample":not is_final_block,
-                                    "resnet_eps":norm_eps,
-                                    "resnet_act_fn":act_fn,
-                                    "resnet_groups":norm_num_groups,
-                                    "cross_attention_dim":cross_attention_dim[i],
-                                    "num_attention_heads":num_attention_heads[i],
-                                    "downsample_padding":downsample_padding,
-                                    "dual_cross_attention":dual_cross_attention,
-                                    "use_linear_projection":use_linear_projection,
-                                    "only_cross_attention":only_cross_attention[i],
-                                    "upcast_attention":upcast_attention,
-                                    "resnet_time_scale_shift":resnet_time_scale_shift,
-                                    "attention_type":attention_type,
-                                    "resnet_skip_time_act":resnet_skip_time_act,
-                                    "resnet_out_scale_factor":resnet_out_scale_factor,
-                                    "cross_attention_norm":cross_attention_norm,
-                                    "attention_head_dim":attention_head_dim[i] if attention_head_dim[i] is not None else output_channel,
-                                    "dropout":dropout}
-
-            if i == 0:
-                self.head_img = get_down_block(**down_block_kwargs)
-                # same architecture as the head_img but different weights
-                self.head_dem = get_down_block(**down_block_kwargs)
-            # elif i == 1:
-            #     down_block_kwargs["in_channels"] = input_channel *2 # concatenate the output of the head_img and head_dem
-            #     down_block = get_down_block(**down_block_kwargs)
-            #     self.down_blocks.append(down_block)
-            else:
-                down_block = get_down_block(**down_block_kwargs)
-                self.down_blocks.append(down_block)
-
-        # mid
-        self.mid_block = get_mid_block(
-            mid_block_type,
-            temb_channels=blocks_time_embed_dim,
-            in_channels=block_out_channels[-1],
-            resnet_eps=norm_eps,
-            resnet_act_fn=act_fn,
-            resnet_groups=norm_num_groups,
-            output_scale_factor=mid_block_scale_factor,
-            transformer_layers_per_block=transformer_layers_per_block[-1],
-            num_attention_heads=num_attention_heads[-1],
-            cross_attention_dim=cross_attention_dim[-1],
-            dual_cross_attention=dual_cross_attention,
-            use_linear_projection=use_linear_projection,
-            mid_block_only_cross_attention=mid_block_only_cross_attention,
-            upcast_attention=upcast_attention,
-            resnet_time_scale_shift=resnet_time_scale_shift,
-            attention_type=attention_type,
-            resnet_skip_time_act=resnet_skip_time_act,
-            cross_attention_norm=cross_attention_norm,
-            attention_head_dim=attention_head_dim[-1],
-            dropout=dropout,
-        )
-
-        # count how many layers upsample the images
-        self.num_upsamplers = 0
-
-        # up
-        reversed_block_out_channels = list(reversed(block_out_channels))
-        reversed_num_attention_heads = list(reversed(num_attention_heads))
-        reversed_layers_per_block = list(reversed(layers_per_block))
-        reversed_cross_attention_dim = list(reversed(cross_attention_dim))
-        reversed_transformer_layers_per_block = (
-            list(reversed(transformer_layers_per_block))
-            if reverse_transformer_layers_per_block is None
-            else reverse_transformer_layers_per_block
-        )
-        only_cross_attention = list(reversed(only_cross_attention))
-
-        output_channel = reversed_block_out_channels[0]
-        for i, up_block_type in enumerate(up_block_types):
-            is_final_block = i == len(block_out_channels) - 1
-
-            prev_output_channel = output_channel
-            output_channel = reversed_block_out_channels[i]
-            input_channel = reversed_block_out_channels[min(i + 1, len(block_out_channels) - 1)]
-
-            # add upsample block for all BUT final layer
-            if not is_final_block:
-                add_upsample = True
-                self.num_upsamplers += 1
-            else:
-                add_upsample = False
-
-            up_block_kwargs = {"up_block_type":up_block_type,
-                "num_layers":reversed_layers_per_block[i] + 1,
-                "transformer_layers_per_block":reversed_transformer_layers_per_block[i],
-                "in_channels":input_channel,
-                "out_channels":output_channel,
-                "prev_output_channel":prev_output_channel,
-                "temb_channels":blocks_time_embed_dim,
-                "add_upsample":add_upsample,
-                "resnet_eps":norm_eps,
-                "resnet_act_fn":act_fn,
-                "resolution_idx":i,
-                "resnet_groups":norm_num_groups,
-                "cross_attention_dim":reversed_cross_attention_dim[i],
-                "num_attention_heads":reversed_num_attention_heads[i],
-                "dual_cross_attention":dual_cross_attention,
-                "use_linear_projection":use_linear_projection,
-                "only_cross_attention":only_cross_attention[i],
-                "upcast_attention":upcast_attention,
-                "resnet_time_scale_shift":resnet_time_scale_shift,
-                "attention_type":attention_type,
-                "resnet_skip_time_act":resnet_skip_time_act,
-                "resnet_out_scale_factor":resnet_out_scale_factor,
-                "cross_attention_norm":cross_attention_norm,
-                "attention_head_dim":attention_head_dim[i] if attention_head_dim[i] is not None else output_channel,
-                "dropout":dropout,}
-
-            # if i == len(block_out_channels) - 2:
-            #     up_block_kwargs["in_channels"] = input_channel*2
-            #     up_block = get_up_block(**up_block_kwargs)
-            #     self.up_blocks.append(up_block)
-
-            if is_final_block :
-
-                self.head_out_img = get_up_block(**up_block_kwargs)
-                self.head_out_dem = get_up_block(**up_block_kwargs)
-
-            else :
-                up_block = get_up_block(**up_block_kwargs)
-                self.up_blocks.append(up_block)
-        
-
-        # out
-        if norm_num_groups is not None:
-            self.conv_norm_out_img = nn.GroupNorm(
-                num_channels=block_out_channels[0], num_groups=norm_num_groups, eps=norm_eps
-            )
-            self.conv_norm_out_dem = nn.GroupNorm(
-                num_channels=block_out_channels[0], num_groups=norm_num_groups, eps=norm_eps
-            )
-
-            self.conv_act = get_activation(act_fn)
-
-        else:
-            self.conv_norm_out_img = None
-            self.conv_norm_out_dem = None
-            self.conv_act = None
-
-        conv_out_padding = (conv_out_kernel - 1) // 2
-        self.conv_out_img = nn.Conv2d(
-            block_out_channels[0], out_channels, kernel_size=conv_out_kernel, padding=conv_out_padding
-        )
-        self.conv_out_dem = nn.Conv2d(
-            block_out_channels[0], out_channels, kernel_size=conv_out_kernel, padding=conv_out_padding
-        )
-
-        self._set_pos_net_if_use_gligen(attention_type=attention_type, cross_attention_dim=cross_attention_dim)
-
-    def _check_config(
-        self,
-        down_block_types: Tuple[str],
-        up_block_types: Tuple[str],
-        only_cross_attention: Union[bool, Tuple[bool]],
-        block_out_channels: Tuple[int],
-        layers_per_block: Union[int, Tuple[int]],
-        cross_attention_dim: Union[int, Tuple[int]],
-        transformer_layers_per_block: Union[int, Tuple[int], Tuple[Tuple[int]]],
-        reverse_transformer_layers_per_block: bool,
-        attention_head_dim: int,
-        num_attention_heads: Optional[Union[int, Tuple[int]]],
-    ):
-        if len(down_block_types) != len(up_block_types):
-            raise ValueError(
-                f"Must provide the same number of `down_block_types` as `up_block_types`. `down_block_types`: {down_block_types}. `up_block_types`: {up_block_types}."
-            )
-
-        if len(block_out_channels) != len(down_block_types):
-            raise ValueError(
-                f"Must provide the same number of `block_out_channels` as `down_block_types`. `block_out_channels`: {block_out_channels}. `down_block_types`: {down_block_types}."
-            )
-
-        if not isinstance(only_cross_attention, bool) and len(only_cross_attention) != len(down_block_types):
-            raise ValueError(
-                f"Must provide the same number of `only_cross_attention` as `down_block_types`. `only_cross_attention`: {only_cross_attention}. `down_block_types`: {down_block_types}."
-            )
-
-        if not isinstance(num_attention_heads, int) and len(num_attention_heads) != len(down_block_types):
-            raise ValueError(
-                f"Must provide the same number of `num_attention_heads` as `down_block_types`. `num_attention_heads`: {num_attention_heads}. `down_block_types`: {down_block_types}."
-            )
-
-        if not isinstance(attention_head_dim, int) and len(attention_head_dim) != len(down_block_types):
-            raise ValueError(
-                f"Must provide the same number of `attention_head_dim` as `down_block_types`. `attention_head_dim`: {attention_head_dim}. `down_block_types`: {down_block_types}."
-            )
-
-        if isinstance(cross_attention_dim, list) and len(cross_attention_dim) != len(down_block_types):
-            raise ValueError(
-                f"Must provide the same number of `cross_attention_dim` as `down_block_types`. `cross_attention_dim`: {cross_attention_dim}. `down_block_types`: {down_block_types}."
-            )
-
-        if not isinstance(layers_per_block, int) and len(layers_per_block) != len(down_block_types):
-            raise ValueError(
-                f"Must provide the same number of `layers_per_block` as `down_block_types`. `layers_per_block`: {layers_per_block}. `down_block_types`: {down_block_types}."
-            )
-        if isinstance(transformer_layers_per_block, list) and reverse_transformer_layers_per_block is None:
-            for layer_number_per_block in transformer_layers_per_block:
-                if isinstance(layer_number_per_block, list):
-                    raise ValueError("Must provide 'reverse_transformer_layers_per_block` if using asymmetrical UNet.")
-
-    def _set_time_proj(
-        self,
-        time_embedding_type: str,
-        block_out_channels: int,
-        flip_sin_to_cos: bool,
-        freq_shift: float,
-        time_embedding_dim: int,
-    ) -> Tuple[int, int]:
-        if time_embedding_type == "fourier":
-            time_embed_dim = time_embedding_dim or block_out_channels[0] * 2
-            if time_embed_dim % 2 != 0:
-                raise ValueError(f"`time_embed_dim` should be divisible by 2, but is {time_embed_dim}.")
-            self.time_proj = GaussianFourierProjection(
-                time_embed_dim // 2, set_W_to_weight=False, log=False, flip_sin_to_cos=flip_sin_to_cos
-            )
-            timestep_input_dim = time_embed_dim
-        elif time_embedding_type == "positional":
-            time_embed_dim = time_embedding_dim or block_out_channels[0] * 4
-
-            self.time_proj = Timesteps(block_out_channels[0], flip_sin_to_cos, freq_shift)
-            timestep_input_dim = block_out_channels[0]
-        else:
-            raise ValueError(
-                f"{time_embedding_type} does not exist. Please make sure to use one of `fourier` or `positional`."
-            )
-
-        return time_embed_dim, timestep_input_dim
-
-    def _set_encoder_hid_proj(
-        self,
-        encoder_hid_dim_type: Optional[str],
-        cross_attention_dim: Union[int, Tuple[int]],
-        encoder_hid_dim: Optional[int],
-    ):
-        if encoder_hid_dim_type is None and encoder_hid_dim is not None:
-            encoder_hid_dim_type = "text_proj"
-            self.register_to_config(encoder_hid_dim_type=encoder_hid_dim_type)
-            logger.info("encoder_hid_dim_type defaults to 'text_proj' as `encoder_hid_dim` is defined.")
-
-        if encoder_hid_dim is None and encoder_hid_dim_type is not None:
-            raise ValueError(
-                f"`encoder_hid_dim` has to be defined when `encoder_hid_dim_type` is set to {encoder_hid_dim_type}."
-            )
-
-        if encoder_hid_dim_type == "text_proj":
-            self.encoder_hid_proj = nn.Linear(encoder_hid_dim, cross_attention_dim)
-        elif encoder_hid_dim_type == "text_image_proj":
-            # image_embed_dim DOESN'T have to be `cross_attention_dim`. To not clutter the __init__ too much
-            # they are set to `cross_attention_dim` here as this is exactly the required dimension for the currently only use
-            # case when `addition_embed_type == "text_image_proj"` (Kandinsky 2.1)`
-            self.encoder_hid_proj = TextImageProjection(
-                text_embed_dim=encoder_hid_dim,
-                image_embed_dim=cross_attention_dim,
-                cross_attention_dim=cross_attention_dim,
-            )
-        elif encoder_hid_dim_type == "image_proj":
-            # Kandinsky 2.2
-            self.encoder_hid_proj = ImageProjection(
-                image_embed_dim=encoder_hid_dim,
-                cross_attention_dim=cross_attention_dim,
-            )
-        elif encoder_hid_dim_type is not None:
-            raise ValueError(
-                f"`encoder_hid_dim_type`: {encoder_hid_dim_type} must be None, 'text_proj', 'text_image_proj', or 'image_proj'."
-            )
-        else:
-            self.encoder_hid_proj = None
-
-    def _set_class_embedding(
-        self,
-        class_embed_type: Optional[str],
-        act_fn: str,
-        num_class_embeds: Optional[int],
-        projection_class_embeddings_input_dim: Optional[int],
-        time_embed_dim: int,
-        timestep_input_dim: int,
-    ):
-        if class_embed_type is None and num_class_embeds is not None:
-            self.class_embedding = nn.Embedding(num_class_embeds, time_embed_dim)
-        elif class_embed_type == "timestep":
-            self.class_embedding = TimestepEmbedding(timestep_input_dim, time_embed_dim, act_fn=act_fn)
-        elif class_embed_type == "identity":
-            self.class_embedding = nn.Identity(time_embed_dim, time_embed_dim)
-        elif class_embed_type == "projection":
-            if projection_class_embeddings_input_dim is None:
-                raise ValueError(
-                    "`class_embed_type`: 'projection' requires `projection_class_embeddings_input_dim` be set"
-                )
-            # The projection `class_embed_type` is the same as the timestep `class_embed_type` except
-            # 1. the `class_labels` inputs are not first converted to sinusoidal embeddings
-            # 2. it projects from an arbitrary input dimension.
-            #
-            # Note that `TimestepEmbedding` is quite general, being mainly linear layers and activations.
-            # When used for embedding actual timesteps, the timesteps are first converted to sinusoidal embeddings.
-            # As a result, `TimestepEmbedding` can be passed arbitrary vectors.
-            self.class_embedding = TimestepEmbedding(projection_class_embeddings_input_dim, time_embed_dim)
-        elif class_embed_type == "simple_projection":
-            if projection_class_embeddings_input_dim is None:
-                raise ValueError(
-                    "`class_embed_type`: 'simple_projection' requires `projection_class_embeddings_input_dim` be set"
-                )
-            self.class_embedding = nn.Linear(projection_class_embeddings_input_dim, time_embed_dim)
-        else:
-            self.class_embedding = None
-
-    def _set_add_embedding(
-        self,
-        addition_embed_type: str,
-        addition_embed_type_num_heads: int,
-        addition_time_embed_dim: Optional[int],
-        flip_sin_to_cos: bool,
-        freq_shift: float,
-        cross_attention_dim: Optional[int],
-        encoder_hid_dim: Optional[int],
-        projection_class_embeddings_input_dim: Optional[int],
-        time_embed_dim: int,
-    ):
-        if addition_embed_type == "text":
-            if encoder_hid_dim is not None:
-                text_time_embedding_from_dim = encoder_hid_dim
-            else:
-                text_time_embedding_from_dim = cross_attention_dim
-
-            self.add_embedding = TextTimeEmbedding(
-                text_time_embedding_from_dim, time_embed_dim, num_heads=addition_embed_type_num_heads
-            )
-        elif addition_embed_type == "text_image":
-            # text_embed_dim and image_embed_dim DON'T have to be `cross_attention_dim`. To not clutter the __init__ too much
-            # they are set to `cross_attention_dim` here as this is exactly the required dimension for the currently only use
-            # case when `addition_embed_type == "text_image"` (Kandinsky 2.1)`
-            self.add_embedding = TextImageTimeEmbedding(
-                text_embed_dim=cross_attention_dim, image_embed_dim=cross_attention_dim, time_embed_dim=time_embed_dim
-            )
-        elif addition_embed_type == "text_time":
-            self.add_time_proj = Timesteps(addition_time_embed_dim, flip_sin_to_cos, freq_shift)
-            self.add_embedding = TimestepEmbedding(projection_class_embeddings_input_dim, time_embed_dim)
-        elif addition_embed_type == "image":
-            # Kandinsky 2.2
-            self.add_embedding = ImageTimeEmbedding(image_embed_dim=encoder_hid_dim, time_embed_dim=time_embed_dim)
-        elif addition_embed_type == "image_hint":
-            # Kandinsky 2.2 ControlNet
-            self.add_embedding = ImageHintTimeEmbedding(image_embed_dim=encoder_hid_dim, time_embed_dim=time_embed_dim)
-        elif addition_embed_type is not None:
-            raise ValueError(
-                f"`addition_embed_type`: {addition_embed_type} must be None, 'text', 'text_image', 'text_time', 'image', or 'image_hint'."
-            )
-
-    def _set_pos_net_if_use_gligen(self, attention_type: str, cross_attention_dim: int):
-        if attention_type in ["gated", "gated-text-image"]:
-            positive_len = 768
-            if isinstance(cross_attention_dim, int):
-                positive_len = cross_attention_dim
-            elif isinstance(cross_attention_dim, (list, tuple)):
-                positive_len = cross_attention_dim[0]
-
-            feature_type = "text-only" if attention_type == "gated" else "text-image"
-            self.position_net = GLIGENTextBoundingboxProjection(
-                positive_len=positive_len, out_dim=cross_attention_dim, feature_type=feature_type
-            )
-
-    @property
-    def attn_processors(self) -> Dict[str, AttentionProcessor]:
-        r"""
-        Returns:
-            `dict` of attention processors: A dictionary containing all attention processors used in the model with
-            indexed by its weight name.
-        """
-        # set recursively
-        processors = {}
-
-        def fn_recursive_add_processors(name: str, module: torch.nn.Module, processors: Dict[str, AttentionProcessor]):
-            if hasattr(module, "get_processor"):
-                processors[f"{name}.processor"] = module.get_processor()
-
-            for sub_name, child in module.named_children():
-                fn_recursive_add_processors(f"{name}.{sub_name}", child, processors)
-
-            return processors
-
-        for name, module in self.named_children():
-            fn_recursive_add_processors(name, module, processors)
-
-        return processors
-
-    def set_attn_processor(self, processor: Union[AttentionProcessor, Dict[str, AttentionProcessor]]):
-        r"""
-        Sets the attention processor to use to compute attention.
-
-        Parameters:
-            processor (`dict` of `AttentionProcessor` or only `AttentionProcessor`):
-                The instantiated processor class or a dictionary of processor classes that will be set as the processor
-                for **all** `Attention` layers.
-
-                If `processor` is a dict, the key needs to define the path to the corresponding cross attention
-                processor. This is strongly recommended when setting trainable attention processors.
-
-        """
-        count = len(self.attn_processors.keys())
-
-        if isinstance(processor, dict) and len(processor) != count:
-            raise ValueError(
-                f"A dict of processors was passed, but the number of processors {len(processor)} does not match the"
-                f" number of attention layers: {count}. Please make sure to pass {count} processor classes."
-            )
-
-        def fn_recursive_attn_processor(name: str, module: torch.nn.Module, processor):
-            if hasattr(module, "set_processor"):
-                if not isinstance(processor, dict):
-                    module.set_processor(processor)
-                else:
-                    module.set_processor(processor.pop(f"{name}.processor"))
-
-            for sub_name, child in module.named_children():
-                fn_recursive_attn_processor(f"{name}.{sub_name}", child, processor)
-
-        for name, module in self.named_children():
-            fn_recursive_attn_processor(name, module, processor)
-
-    def set_default_attn_processor(self):
-        """
-        Disables custom attention processors and sets the default attention implementation.
-        """
-        if all(proc.__class__ in ADDED_KV_ATTENTION_PROCESSORS for proc in self.attn_processors.values()):
-            processor = AttnAddedKVProcessor()
-        elif all(proc.__class__ in CROSS_ATTENTION_PROCESSORS for proc in self.attn_processors.values()):
-            processor = AttnProcessor()
-        else:
-            raise ValueError(
-                f"Cannot call `set_default_attn_processor` when attention processors are of type {next(iter(self.attn_processors.values()))}"
-            )
-
-        self.set_attn_processor(processor)
-
-    def set_attention_slice(self, slice_size: Union[str, int, List[int]] = "auto"):
-        r"""
-        Enable sliced attention computation.
-
-        When this option is enabled, the attention module splits the input tensor in slices to compute attention in
-        several steps. This is useful for saving some memory in exchange for a small decrease in speed.
-
-        Args:
-            slice_size (`str` or `int` or `list(int)`, *optional*, defaults to `"auto"`):
-                When `"auto"`, input to the attention heads is halved, so attention is computed in two steps. If
-                `"max"`, maximum amount of memory is saved by running only one slice at a time. If a number is
-                provided, uses as many slices as `attention_head_dim // slice_size`. In this case, `attention_head_dim`
-                must be a multiple of `slice_size`.
-        """
-        sliceable_head_dims = []
-
-        def fn_recursive_retrieve_sliceable_dims(module: torch.nn.Module):
-            if hasattr(module, "set_attention_slice"):
-                sliceable_head_dims.append(module.sliceable_head_dim)
-
-            for child in module.children():
-                fn_recursive_retrieve_sliceable_dims(child)
-
-        # retrieve number of attention layers
-        for module in self.children():
-            fn_recursive_retrieve_sliceable_dims(module)
-
-        num_sliceable_layers = len(sliceable_head_dims)
-
-        if slice_size == "auto":
-            # half the attention head size is usually a good trade-off between
-            # speed and memory
-            slice_size = [dim // 2 for dim in sliceable_head_dims]
-        elif slice_size == "max":
-            # make smallest slice possible
-            slice_size = num_sliceable_layers * [1]
-
-        slice_size = num_sliceable_layers * [slice_size] if not isinstance(slice_size, list) else slice_size
-
-        if len(slice_size) != len(sliceable_head_dims):
-            raise ValueError(
-                f"You have provided {len(slice_size)}, but {self.config} has {len(sliceable_head_dims)} different"
-                f" attention layers. Make sure to match `len(slice_size)` to be {len(sliceable_head_dims)}."
-            )
-
-        for i in range(len(slice_size)):
-            size = slice_size[i]
-            dim = sliceable_head_dims[i]
-            if size is not None and size > dim:
-                raise ValueError(f"size {size} has to be smaller or equal to {dim}.")
-
-        # Recursively walk through all the children.
-        # Any children which exposes the set_attention_slice method
-        # gets the message
-        def fn_recursive_set_attention_slice(module: torch.nn.Module, slice_size: List[int]):
-            if hasattr(module, "set_attention_slice"):
-                module.set_attention_slice(slice_size.pop())
-
-            for child in module.children():
-                fn_recursive_set_attention_slice(child, slice_size)
-
-        reversed_slice_size = list(reversed(slice_size))
-        for module in self.children():
-            fn_recursive_set_attention_slice(module, reversed_slice_size)
-
-    def _set_gradient_checkpointing(self, module, value=False):
-        if hasattr(module, "gradient_checkpointing"):
-            module.gradient_checkpointing = value
-
-    def enable_freeu(self, s1: float, s2: float, b1: float, b2: float):
-        r"""Enables the FreeU mechanism from https://arxiv.org/abs/2309.11497.
-
-        The suffixes after the scaling factors represent the stage blocks where they are being applied.
-
-        Please refer to the [official repository](https://github.com/ChenyangSi/FreeU) for combinations of values that
-        are known to work well for different pipelines such as Stable Diffusion v1, v2, and Stable Diffusion XL.
-
-        Args:
-            s1 (`float`):
-                Scaling factor for stage 1 to attenuate the contributions of the skip features. This is done to
-                mitigate the "oversmoothing effect" in the enhanced denoising process.
-            s2 (`float`):
-                Scaling factor for stage 2 to attenuate the contributions of the skip features. This is done to
-                mitigate the "oversmoothing effect" in the enhanced denoising process.
-            b1 (`float`): Scaling factor for stage 1 to amplify the contributions of backbone features.
-            b2 (`float`): Scaling factor for stage 2 to amplify the contributions of backbone features.
-        """
-        for i, upsample_block in enumerate(self.up_blocks):
-            setattr(upsample_block, "s1", s1)
-            setattr(upsample_block, "s2", s2)
-            setattr(upsample_block, "b1", b1)
-            setattr(upsample_block, "b2", b2)
-
-    def disable_freeu(self):
-        """Disables the FreeU mechanism."""
-        freeu_keys = {"s1", "s2", "b1", "b2"}
-        for i, upsample_block in enumerate(self.up_blocks):
-            for k in freeu_keys:
-                if hasattr(upsample_block, k) or getattr(upsample_block, k, None) is not None:
-                    setattr(upsample_block, k, None)
-
-    def fuse_qkv_projections(self):
-        """
-        Enables fused QKV projections. For self-attention modules, all projection matrices (i.e., query, key, value)
-        are fused. For cross-attention modules, key and value projection matrices are fused.
-
-        <Tip warning={true}>
-
-        This API is 🧪 experimental.
-
-        </Tip>
-        """
-        self.original_attn_processors = None
-
-        for _, attn_processor in self.attn_processors.items():
-            if "Added" in str(attn_processor.__class__.__name__):
-                raise ValueError("`fuse_qkv_projections()` is not supported for models having added KV projections.")
-
-        self.original_attn_processors = self.attn_processors
-
-        for module in self.modules():
-            if isinstance(module, Attention):
-                module.fuse_projections(fuse=True)
-
-        self.set_attn_processor(FusedAttnProcessor2_0())
-
-    def unfuse_qkv_projections(self):
-        """Disables the fused QKV projection if enabled.
-
-        <Tip warning={true}>
-
-        This API is 🧪 experimental.
-
-        </Tip>
-
-        """
-        if self.original_attn_processors is not None:
-            self.set_attn_processor(self.original_attn_processors)
-
-    def get_time_embed(
-        self, sample: torch.Tensor, timestep: Union[torch.Tensor, float, int]
-    ) -> Optional[torch.Tensor]:
-        timesteps = timestep
-        if not torch.is_tensor(timesteps):
-            # TODO: this requires sync between CPU and GPU. So try to pass timesteps as tensors if you can
-            # This would be a good case for the `match` statement (Python 3.10+)
-            is_mps = sample.device.type == "mps"
-            if isinstance(timestep, float):
-                dtype = torch.float32 if is_mps else torch.float64
-            else:
-                dtype = torch.int32 if is_mps else torch.int64
-            timesteps = torch.tensor([timesteps], dtype=dtype, device=sample.device)
-        elif len(timesteps.shape) == 0:
-            timesteps = timesteps[None].to(sample.device)
-
-        # broadcast to batch dimension in a way that's compatible with ONNX/Core ML
-        timesteps = timesteps.expand(sample.shape[0])
-
-        t_emb = self.time_proj(timesteps)
-        # `Timesteps` does not contain any weights and will always return f32 tensors
-        # but time_embedding might actually be running in fp16. so we need to cast here.
-        # there might be better ways to encapsulate this.
-        t_emb = t_emb.to(dtype=sample.dtype)
-        return t_emb
-
-    def get_class_embed(self, sample: torch.Tensor, class_labels: Optional[torch.Tensor]) -> Optional[torch.Tensor]:
-        class_emb = None
-        if self.class_embedding is not None:
-            if class_labels is None:
-                raise ValueError("class_labels should be provided when num_class_embeds > 0")
-
-            if self.config.class_embed_type == "timestep":
-                class_labels = self.time_proj(class_labels)
-
-                # `Timesteps` does not contain any weights and will always return f32 tensors
-                # there might be better ways to encapsulate this.
-                class_labels = class_labels.to(dtype=sample.dtype)
-
-            class_emb = self.class_embedding(class_labels).to(dtype=sample.dtype)
-        return class_emb
-
-    def get_aug_embed(
-        self, emb: torch.Tensor, encoder_hidden_states: torch.Tensor, added_cond_kwargs: Dict[str, Any]
-    ) -> Optional[torch.Tensor]:
-        aug_emb = None
-        if self.config.addition_embed_type == "text":
-            aug_emb = self.add_embedding(encoder_hidden_states)
-        elif self.config.addition_embed_type == "text_image":
-            # Kandinsky 2.1 - style
-            if "image_embeds" not in added_cond_kwargs:
-                raise ValueError(
-                    f"{self.__class__} has the config param `addition_embed_type` set to 'text_image' which requires the keyword argument `image_embeds` to be passed in `added_cond_kwargs`"
-                )
-
-            image_embs = added_cond_kwargs.get("image_embeds")
-            text_embs = added_cond_kwargs.get("text_embeds", encoder_hidden_states)
-            aug_emb = self.add_embedding(text_embs, image_embs)
-        elif self.config.addition_embed_type == "text_time":
-            # SDXL - style
-            if "text_embeds" not in added_cond_kwargs:
-                raise ValueError(
-                    f"{self.__class__} has the config param `addition_embed_type` set to 'text_time' which requires the keyword argument `text_embeds` to be passed in `added_cond_kwargs`"
-                )
-            text_embeds = added_cond_kwargs.get("text_embeds")
-            if "time_ids" not in added_cond_kwargs:
-                raise ValueError(
-                    f"{self.__class__} has the config param `addition_embed_type` set to 'text_time' which requires the keyword argument `time_ids` to be passed in `added_cond_kwargs`"
-                )
-            time_ids = added_cond_kwargs.get("time_ids")
-            time_embeds = self.add_time_proj(time_ids.flatten())
-            time_embeds = time_embeds.reshape((text_embeds.shape[0], -1))
-            add_embeds = torch.concat([text_embeds, time_embeds], dim=-1)
-            add_embeds = add_embeds.to(emb.dtype)
-            aug_emb = self.add_embedding(add_embeds)
-        elif self.config.addition_embed_type == "image":
-            # Kandinsky 2.2 - style
-            if "image_embeds" not in added_cond_kwargs:
-                raise ValueError(
-                    f"{self.__class__} has the config param `addition_embed_type` set to 'image' which requires the keyword argument `image_embeds` to be passed in `added_cond_kwargs`"
-                )
-            image_embs = added_cond_kwargs.get("image_embeds")
-            aug_emb = self.add_embedding(image_embs)
-        elif self.config.addition_embed_type == "image_hint":
-            # Kandinsky 2.2 ControlNet - style
-            if "image_embeds" not in added_cond_kwargs or "hint" not in added_cond_kwargs:
-                raise ValueError(
-                    f"{self.__class__} has the config param `addition_embed_type` set to 'image_hint' which requires the keyword arguments `image_embeds` and `hint` to be passed in `added_cond_kwargs`"
-                )
-            image_embs = added_cond_kwargs.get("image_embeds")
-            hint = added_cond_kwargs.get("hint")
-            aug_emb = self.add_embedding(image_embs, hint)
-        return aug_emb
-
-    def process_encoder_hidden_states(
-        self, encoder_hidden_states: torch.Tensor, added_cond_kwargs: Dict[str, Any]
-    ) -> torch.Tensor:
-        if self.encoder_hid_proj is not None and self.config.encoder_hid_dim_type == "text_proj":
-            encoder_hidden_states = self.encoder_hid_proj(encoder_hidden_states)
-        elif self.encoder_hid_proj is not None and self.config.encoder_hid_dim_type == "text_image_proj":
-            # Kandinsky 2.1 - style
-            if "image_embeds" not in added_cond_kwargs:
-                raise ValueError(
-                    f"{self.__class__} has the config param `encoder_hid_dim_type` set to 'text_image_proj' which requires the keyword argument `image_embeds` to be passed in `added_cond_kwargs`"
-                )
-
-            image_embeds = added_cond_kwargs.get("image_embeds")
-            encoder_hidden_states = self.encoder_hid_proj(encoder_hidden_states, image_embeds)
-        elif self.encoder_hid_proj is not None and self.config.encoder_hid_dim_type == "image_proj":
-            # Kandinsky 2.2 - style
-            if "image_embeds" not in added_cond_kwargs:
-                raise ValueError(
-                    f"{self.__class__} has the config param `encoder_hid_dim_type` set to 'image_proj' which requires the keyword argument `image_embeds` to be passed in `added_cond_kwargs`"
-                )
-            image_embeds = added_cond_kwargs.get("image_embeds")
-            encoder_hidden_states = self.encoder_hid_proj(image_embeds)
-        elif self.encoder_hid_proj is not None and self.config.encoder_hid_dim_type == "ip_image_proj":
-            if "image_embeds" not in added_cond_kwargs:
-                raise ValueError(
-                    f"{self.__class__} has the config param `encoder_hid_dim_type` set to 'ip_image_proj' which requires the keyword argument `image_embeds` to be passed in `added_cond_kwargs`"
-                )
-
-            if hasattr(self, "text_encoder_hid_proj") and self.text_encoder_hid_proj is not None:
-                encoder_hidden_states = self.text_encoder_hid_proj(encoder_hidden_states)
-
-            image_embeds = added_cond_kwargs.get("image_embeds")
-            image_embeds = self.encoder_hid_proj(image_embeds)
-            encoder_hidden_states = (encoder_hidden_states, image_embeds)
-        return encoder_hidden_states
-
-    def forward(
-        self,
-        sample: torch.Tensor,
-        timestep: Union[torch.Tensor, float, int],
-        encoder_hidden_states: torch.Tensor,
-        class_labels: Optional[torch.Tensor] = None,
-        timestep_cond: Optional[torch.Tensor] = None,
-        attention_mask: Optional[torch.Tensor] = None,
-        cross_attention_kwargs: Optional[Dict[str, Any]] = None,
-        added_cond_kwargs: Optional[Dict[str, torch.Tensor]] = None,
-        down_block_additional_residuals: Optional[Tuple[torch.Tensor]] = None,
-        mid_block_additional_residual: Optional[torch.Tensor] = None,
-        down_intrablock_additional_residuals: Optional[Tuple[torch.Tensor]] = None,
-        encoder_attention_mask: Optional[torch.Tensor] = None,
-        return_dict: bool = True,
-    ) -> Union[UNet2DConditionOutput, Tuple]:
-        r"""
-        The [`UNet2DConditionModel`] forward method.
-
-        Args:
-            sample (`torch.Tensor`):
-                The noisy input tensor with the following shape `(batch, channel, height, width)`.
-            timestep (`torch.Tensor` or `float` or `int`): The number of timesteps to denoise an input.
-            encoder_hidden_states (`torch.Tensor`):
-                The encoder hidden states with shape `(batch, sequence_length, feature_dim)`.
-            class_labels (`torch.Tensor`, *optional*, defaults to `None`):
-                Optional class labels for conditioning. Their embeddings will be summed with the timestep embeddings.
-            timestep_cond: (`torch.Tensor`, *optional*, defaults to `None`):
-                Conditional embeddings for timestep. If provided, the embeddings will be summed with the samples passed
-                through the `self.time_embedding` layer to obtain the timestep embeddings.
-            attention_mask (`torch.Tensor`, *optional*, defaults to `None`):
-                An attention mask of shape `(batch, key_tokens)` is applied to `encoder_hidden_states`. If `1` the mask
-                is kept, otherwise if `0` it is discarded. Mask will be converted into a bias, which adds large
-                negative values to the attention scores corresponding to "discard" tokens.
-            cross_attention_kwargs (`dict`, *optional*):
-                A kwargs dictionary that if specified is passed along to the `AttentionProcessor` as defined under
-                `self.processor` in
-                [diffusers.models.attention_processor](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py).
-            added_cond_kwargs: (`dict`, *optional*):
-                A kwargs dictionary containing additional embeddings that if specified are added to the embeddings that
-                are passed along to the UNet blocks.
-            down_block_additional_residuals: (`tuple` of `torch.Tensor`, *optional*):
-                A tuple of tensors that if specified are added to the residuals of down unet blocks.
-            mid_block_additional_residual: (`torch.Tensor`, *optional*):
-                A tensor that if specified is added to the residual of the middle unet block.
-            down_intrablock_additional_residuals (`tuple` of `torch.Tensor`, *optional*):
-                additional residuals to be added within UNet down blocks, for example from T2I-Adapter side model(s)
-            encoder_attention_mask (`torch.Tensor`):
-                A cross-attention mask of shape `(batch, sequence_length)` is applied to `encoder_hidden_states`. If
-                `True` the mask is kept, otherwise if `False` it is discarded. Mask will be converted into a bias,
-                which adds large negative values to the attention scores corresponding to "discard" tokens.
-            return_dict (`bool`, *optional*, defaults to `True`):
-                Whether or not to return a [`~models.unets.unet_2d_condition.UNet2DConditionOutput`] instead of a plain
-                tuple.
-
-        Returns:
-            [`~models.unets.unet_2d_condition.UNet2DConditionOutput`] or `tuple`:
-                If `return_dict` is True, an [`~models.unets.unet_2d_condition.UNet2DConditionOutput`] is returned,
-                otherwise a `tuple` is returned where the first element is the sample tensor.
-        """
-        # By default samples have to be AT least a multiple of the overall upsampling factor.
-        # The overall upsampling factor is equal to 2 ** (# num of upsampling layers).
-        # However, the upsampling interpolation output size can be forced to fit any upsampling size
-        # on the fly if necessary.
-        default_overall_up_factor = 2**self.num_upsamplers
-
-        # upsample size should be forwarded when sample is not a multiple of `default_overall_up_factor`
-        forward_upsample_size = False
-        upsample_size = None
-
-        for dim in sample.shape[-2:]:
-            if dim % default_overall_up_factor != 0:
-                # Forward upsample size to force interpolation output size.
-                forward_upsample_size = True
-                break
-
-        # ensure attention_mask is a bias, and give it a singleton query_tokens dimension
-        # expects mask of shape:
-        #   [batch, key_tokens]
-        # adds singleton query_tokens dimension:
-        #   [batch,                    1, key_tokens]
-        # this helps to broadcast it as a bias over attention scores, which will be in one of the following shapes:
-        #   [batch,  heads, query_tokens, key_tokens] (e.g. torch sdp attn)
-        #   [batch * heads, query_tokens, key_tokens] (e.g. xformers or classic attn)
-        if attention_mask is not None:
-            # assume that mask is expressed as:
-            #   (1 = keep,      0 = discard)
-            # convert mask into a bias that can be added to attention scores:
-            #       (keep = +0,     discard = -10000.0)
-            attention_mask = (1 - attention_mask.to(sample.dtype)) * -10000.0
-            attention_mask = attention_mask.unsqueeze(1)
-
-        # convert encoder_attention_mask to a bias the same way we do for attention_mask
-        if encoder_attention_mask is not None:
-            encoder_attention_mask = (1 - encoder_attention_mask.to(sample.dtype)) * -10000.0
-            encoder_attention_mask = encoder_attention_mask.unsqueeze(1)
-
-        # 0. center input if necessary
-        if self.config.center_input_sample:
-            sample = 2 * sample - 1.0
-
-        # 1. time
-        t_emb = self.get_time_embed(sample=sample, timestep=timestep)
-        emb = self.time_embedding(t_emb, timestep_cond)
-
-        class_emb = self.get_class_embed(sample=sample, class_labels=class_labels)
-        if class_emb is not None:
-            if self.config.class_embeddings_concat:
-                emb = torch.cat([emb, class_emb], dim=-1)
-            else:
-                emb = emb + class_emb
-
-        aug_emb = self.get_aug_embed(
-            emb=emb, encoder_hidden_states=encoder_hidden_states, added_cond_kwargs=added_cond_kwargs
-        )
-        if self.config.addition_embed_type == "image_hint":
-            aug_emb, hint = aug_emb
-            sample = torch.cat([sample, hint], dim=1)
-        
-
-        emb = emb + aug_emb if aug_emb is not None else emb
-
-        if self.time_embed_act is not None:
-            emb = self.time_embed_act(emb)
-
-        encoder_hidden_states = self.process_encoder_hidden_states(
-            encoder_hidden_states=encoder_hidden_states, added_cond_kwargs=added_cond_kwargs
-        )
-
-        sample_img = sample[:, :4, :, :]
-        sample_dem = sample[:, 4:, :, :]
-        # 2. pre-process using the two different heads
-        sample_img = self.conv_in_img(sample_img)
-        sample_dem = self.conv_in_dem(sample_dem)
-
-        # 2.5 GLIGEN position net
-        if cross_attention_kwargs is not None and cross_attention_kwargs.get("gligen", None) is not None:
-            cross_attention_kwargs = cross_attention_kwargs.copy()
-            gligen_args = cross_attention_kwargs.pop("gligen")
-            cross_attention_kwargs["gligen"] = {"objs": self.position_net(**gligen_args)}
-
-        # 3. down
-        # we're popping the `scale` instead of getting it because otherwise `scale` will be propagated
-        # to the internal blocks and will raise deprecation warnings. this will be confusing for our users.
-        if cross_attention_kwargs is not None:
-            cross_attention_kwargs = cross_attention_kwargs.copy()
-            lora_scale = cross_attention_kwargs.pop("scale", 1.0)
-        else:
-            lora_scale = 1.0
-
-        if USE_PEFT_BACKEND:
-            # weight the lora layers by setting `lora_scale` for each PEFT layer
-            scale_lora_layers(self, lora_scale)
-
-        is_controlnet = mid_block_additional_residual is not None and down_block_additional_residuals is not None
-        # using new arg down_intrablock_additional_residuals for T2I-Adapters, to distinguish from controlnets
-        is_adapter = down_intrablock_additional_residuals is not None
-        if (down_intrablock_additional_residuals is not None) or is_adapter:
-            raise NotImplementedError("additional_residuals")
-    
-
-        # go through the heads
-        head_img_res_sample = (sample_img,)
-        # RGB head
-        if hasattr(self.head_img, "has_cross_attention") and self.head_img.has_cross_attention:
-            # For t2i-adapter CrossAttnDownBlock2D
-            additional_residuals = {}
-            sample_img, res_samples_img = self.head_img(
-                hidden_states=sample_img,
-                temb=emb,
-                encoder_hidden_states=encoder_hidden_states,
-                attention_mask=attention_mask,
-                cross_attention_kwargs=cross_attention_kwargs,
-                encoder_attention_mask=encoder_attention_mask,
-                **additional_residuals,
-            )
-        else:   
-            sample_img, res_samples_img = self.head_img(hidden_states=sample, temb=emb)
-        head_img_res_sample += res_samples_img[:2]
-
-
-
-        head_dem_res_sample = (sample_dem,)
-        # DEM head
-        if hasattr(self.head_dem, "has_cross_attention") and self.head_dem.has_cross_attention:
-            # For t2i-adapter CrossAttnDownBlock2D
-            additional_residuals = {}
-
-            sample_dem, res_samples_dem = self.head_dem(
-                hidden_states=sample_dem,
-                temb=emb,
-                encoder_hidden_states=encoder_hidden_states,
-                attention_mask=attention_mask,
-                cross_attention_kwargs=cross_attention_kwargs,
-                encoder_attention_mask=encoder_attention_mask,
-                **additional_residuals,
-            )
-        else:
-            # sample_dem, res_samples_dem = self.head_dem(hidden_states=sample, temb=emb)
-            sample_dem, res_samples_dem = self.head_img(hidden_states=sample, temb=emb) # shared weights
-        
-        head_dem_res_sample += res_samples_dem[:2]
-
-        #average the two heads and pass them through the down blocks
-        sample = (sample_img + sample_dem) / 2
-        #####
-        res_samples_img_dem = (res_samples_img[2] + res_samples_dem[2]) / 2
-        down_block_res_samples = (res_samples_img_dem,)
-        
-
-        for downsample_block in self.down_blocks:
-            if hasattr(downsample_block, "has_cross_attention") and downsample_block.has_cross_attention:
-                # For t2i-adapter CrossAttnDownBlock2D
-                additional_residuals = {}
-                if is_adapter and len(down_intrablock_additional_residuals) > 0:
-                    additional_residuals["additional_residuals"] = down_intrablock_additional_residuals.pop(0)
-
-                sample, res_samples = downsample_block(
-                    hidden_states=sample,
-                    temb=emb,
-                    encoder_hidden_states=encoder_hidden_states,
-                    attention_mask=attention_mask,
-                    cross_attention_kwargs=cross_attention_kwargs,
-                    encoder_attention_mask=encoder_attention_mask,
-                    **additional_residuals,
-                )
-            else:
-                sample, res_samples = downsample_block(hidden_states=sample, temb=emb)
-                if is_adapter and len(down_intrablock_additional_residuals) > 0:
-                    sample += down_intrablock_additional_residuals.pop(0)
-
-            down_block_res_samples += res_samples
-
-        if is_controlnet:
-            new_down_block_res_samples = ()
-
-            for down_block_res_sample, down_block_additional_residual in zip(
-                down_block_res_samples, down_block_additional_residuals
-            ):
-                down_block_res_sample = down_block_res_sample + down_block_additional_residual
-                new_down_block_res_samples = new_down_block_res_samples + (down_block_res_sample,)
-
-            down_block_res_samples = new_down_block_res_samples
-
-        
-        # 4. mid
-        if self.mid_block is not None:
-            if hasattr(self.mid_block, "has_cross_attention") and self.mid_block.has_cross_attention:
-                sample = self.mid_block(
-                    sample,
-                    emb,
-                    encoder_hidden_states=encoder_hidden_states,
-                    attention_mask=attention_mask,
-                    cross_attention_kwargs=cross_attention_kwargs,
-                    encoder_attention_mask=encoder_attention_mask,
-                )
-            else:
-                sample = self.mid_block(sample, emb)
-
-            # To support T2I-Adapter-XL
-            if (
-                is_adapter
-                and len(down_intrablock_additional_residuals) > 0
-                and sample.shape == down_intrablock_additional_residuals[0].shape
-            ):
-                sample += down_intrablock_additional_residuals.pop(0)
-
-        if is_controlnet:
-            sample = sample + mid_block_additional_residual
-
-        # 5. up
-        for i, upsample_block in enumerate(self.up_blocks):
-
-            res_samples = down_block_res_samples[-len(upsample_block.resnets) :]
-            down_block_res_samples = down_block_res_samples[: -len(upsample_block.resnets)]
-
-            # if we have not reached the final block and need to forward the
-            # upsample size, we do it here
-            if forward_upsample_size:
-                upsample_size = down_block_res_samples[-1].shape[2:]
-            if hasattr(upsample_block, "has_cross_attention") and upsample_block.has_cross_attention:
-                sample = upsample_block(
-                    hidden_states=sample,
-                    temb=emb,
-                    res_hidden_states_tuple=res_samples,
-                    encoder_hidden_states=encoder_hidden_states,
-                    cross_attention_kwargs=cross_attention_kwargs,
-                    upsample_size=upsample_size,
-                    attention_mask=attention_mask,
-                    encoder_attention_mask=encoder_attention_mask,
-                )
-
-            else:
-                sample = upsample_block(
-                    hidden_states=sample,
-                    temb=emb,
-                    res_hidden_states_tuple=res_samples,
-                    upsample_size=upsample_size)
-
-
-        # go through each head
-        
-        sample_img = sample
-
-        if hasattr(self.head_out_img, "has_cross_attention") and self.head_out_img.has_cross_attention:
-            sample_img = self.head_out_img(
-                hidden_states=sample_img,
-                temb=emb,
-                res_hidden_states_tuple=head_img_res_sample,
-                encoder_hidden_states=encoder_hidden_states,
-                cross_attention_kwargs=cross_attention_kwargs,
-                upsample_size=upsample_size,
-                attention_mask=attention_mask,
-                encoder_attention_mask=encoder_attention_mask,
-            )
-        else:
-            sample_img =  self.head_out_img(sample_img,
-                hidden_states=sample,
-                temb=emb,
-                res_hidden_states_tuple=head_img_res_sample,
-                upsample_size=upsample_size,
-            )
-        if self.conv_norm_out_img:
-            sample_img = self.conv_norm_out_img(sample_img)
-            sample_img = self.conv_act(sample_img)
-        sample_img = self.conv_out_img(sample_img)
-
-        sample_dem = sample
-
-        if hasattr(self.head_out_dem, "has_cross_attention") and self.head_out_dem.has_cross_attention:
-            sample_dem = self.head_out_dem(
-                hidden_states=sample_dem,
-                temb=emb,
-                res_hidden_states_tuple=head_dem_res_sample,
-                encoder_hidden_states=encoder_hidden_states,
-                cross_attention_kwargs=cross_attention_kwargs,
-                upsample_size=upsample_size,
-                attention_mask=attention_mask,
-                encoder_attention_mask=encoder_attention_mask,
-            )
-        else:
-            sample_dem =  self.head_out_dem(sample_dem,
-                hidden_states=sample,
-                temb=emb,
-                res_hidden_states_tuple=head_dem_res_sample,
-                upsample_size=upsample_size,
-            )
-        
-        if self.conv_norm_out_dem:
-            sample_dem = self.conv_norm_out_dem(sample_dem)
-            sample_dem = self.conv_act(sample_dem)
-        sample_dem = self.conv_out_dem(sample_dem)
-
-        sample = torch.cat([sample_img,sample_dem],dim=1)
-
-        if USE_PEFT_BACKEND:
-            # remove `lora_scale` from each PEFT layer
-            unscale_lora_layers(self, lora_scale)
-
-        if not return_dict:
-            return (sample,)
-
-        return UNet2DConditionOutput(sample=sample)
-
-
-
-def load_weights_from_pretrained(pretrain_model,model_dem):
-    dem_state_dict = model_dem.state_dict()
-    for name, param in pretrain_model.named_parameters():
-        block = name.split(".")[0]
-        if block == "conv_in":
-            new_name_img = name.replace("conv_in","conv_in_img")
-            dem_state_dict[new_name_img] = param
-            new_name_dem = name.replace("conv_in","conv_in_dem")
-            dem_state_dict[new_name_dem] = param
-        if block == "down_blocks":
-            block_num = int(name.split(".")[1])
-            if block_num == 0:
-                new_name_img = name.replace("down_blocks.0","head_img")
-                dem_state_dict[new_name_img] = param
-                new_name_dem = name.replace("down_blocks.0","head_dem")
-                dem_state_dict[new_name_dem] = param
-            elif block_num > 0:
-                new_name = name.replace(f"down_blocks.{block_num}",f"down_blocks.{block_num-1}")
-                dem_state_dict[new_name] = param
-        if block == "mid_block":
-            dem_state_dict[name] = param
-        if block == "time_embedding":
-            dem_state_dict[name] = param
-        if block == "up_blocks":
-            block_num = int(name.split(".")[1])
-            if block_num == 3:
-                new_name = name.replace("up_blocks.3","head_out_img")
-                dem_state_dict[new_name] = param
-                new_name = name.replace("up_blocks.3","head_out_dem")
-                dem_state_dict[new_name] = param
-            else:
-                dem_state_dict[name] = param
-        if block == "conv_out":
-            new_name = name.replace("conv_out","conv_out_img")
-            dem_state_dict[new_name] = param
-            new_name = name.replace("conv_out","conv_out_dem")
-            dem_state_dict[new_name] = param
-        if block == "conv_norm_out":
-            new_name = name.replace("conv_norm_out","conv_norm_out_img")
-            dem_state_dict[new_name] = param
-            new_name = name.replace("conv_norm_out","conv_norm_out_dem")
-            dem_state_dict[new_name] = param
-
-    model_dem.load_state_dict(dem_state_dict)
-
-    return model_dem

src/.ipynb_checkpoints/pipeline_terrain-checkpoint.py

@@ -1,1057 +0,0 @@
-###########################################################################
-# References:
-# https://github.com/huggingface/diffusers/
-###########################################################################
-
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-import inspect
-from typing import Any, Callable, Dict, List, Optional, Union
-
-import torch
-from packaging import version
-from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer, CLIPVisionModelWithProjection
-
-from diffusers.callbacks import MultiPipelineCallbacks, PipelineCallback
-from diffusers.configuration_utils import FrozenDict
-from diffusers.image_processor import PipelineImageInput, VaeImageProcessor
-from diffusers.loaders import FromSingleFileMixin, IPAdapterMixin, StableDiffusionLoraLoaderMixin, TextualInversionLoaderMixin
-from diffusers.models import AutoencoderKL, ImageProjection, UNet2DConditionModel
-from diffusers.models.lora import adjust_lora_scale_text_encoder
-from diffusers.schedulers import KarrasDiffusionSchedulers
-from diffusers.utils import (
-    USE_PEFT_BACKEND,
-    deprecate,
-    is_torch_xla_available,
-    logging,
-    replace_example_docstring,
-    scale_lora_layers,
-    unscale_lora_layers,
-)
-from diffusers.utils.torch_utils import randn_tensor
-from diffusers.pipelines.pipeline_utils import DiffusionPipeline, StableDiffusionMixin
-from diffusers.pipelines.stable_diffusion.pipeline_output import StableDiffusionPipelineOutput
-from diffusers.pipelines.stable_diffusion.safety_checker import StableDiffusionSafetyChecker
-
-
-if is_torch_xla_available():
-    import torch_xla.core.xla_model as xm
-
-    XLA_AVAILABLE = True
-else:
-    XLA_AVAILABLE = False
-
-logger = logging.get_logger(__name__)  # pylint: disable=invalid-name
-
-EXAMPLE_DOC_STRING = """
-    Examples:
-        ```py
-        >>> import torch
-        >>> from diffusers import StableDiffusionPipeline
-
-        >>> pipe = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16)
-        >>> pipe = pipe.to("cuda")
-
-        >>> prompt = "a photo of an astronaut riding a horse on mars"
-        >>> image = pipe(prompt).images[0]
-        ```
-"""
-
-
-def rescale_noise_cfg(noise_cfg, noise_pred_text, guidance_rescale=0.0):
-    """
-    Rescale `noise_cfg` according to `guidance_rescale`. Based on findings of [Common Diffusion Noise Schedules and
-    Sample Steps are Flawed](https://arxiv.org/pdf/2305.08891.pdf). See Section 3.4
-    """
-    std_text = noise_pred_text.std(dim=list(range(1, noise_pred_text.ndim)), keepdim=True)
-    std_cfg = noise_cfg.std(dim=list(range(1, noise_cfg.ndim)), keepdim=True)
-    # rescale the results from guidance (fixes overexposure)
-    noise_pred_rescaled = noise_cfg * (std_text / std_cfg)
-    # mix with the original results from guidance by factor guidance_rescale to avoid "plain looking" images
-    noise_cfg = guidance_rescale * noise_pred_rescaled + (1 - guidance_rescale) * noise_cfg
-    return noise_cfg
-
-
-def retrieve_timesteps(
-    scheduler,
-    num_inference_steps: Optional[int] = None,
-    device: Optional[Union[str, torch.device]] = None,
-    timesteps: Optional[List[int]] = None,
-    sigmas: Optional[List[float]] = None,
-    **kwargs,
-):
-    """
-    Calls the scheduler's `set_timesteps` method and retrieves timesteps from the scheduler after the call. Handles
-    custom timesteps. Any kwargs will be supplied to `scheduler.set_timesteps`.
-
-    Args:
-        scheduler (`SchedulerMixin`):
-            The scheduler to get timesteps from.
-        num_inference_steps (`int`):
-            The number of diffusion steps used when generating samples with a pre-trained model. If used, `timesteps`
-            must be `None`.
-        device (`str` or `torch.device`, *optional*):
-            The device to which the timesteps should be moved to. If `None`, the timesteps are not moved.
-        timesteps (`List[int]`, *optional*):
-            Custom timesteps used to override the timestep spacing strategy of the scheduler. If `timesteps` is passed,
-            `num_inference_steps` and `sigmas` must be `None`.
-        sigmas (`List[float]`, *optional*):
-            Custom sigmas used to override the timestep spacing strategy of the scheduler. If `sigmas` is passed,
-            `num_inference_steps` and `timesteps` must be `None`.
-
-    Returns:
-        `Tuple[torch.Tensor, int]`: A tuple where the first element is the timestep schedule from the scheduler and the
-        second element is the number of inference steps.
-    """
-    if timesteps is not None and sigmas is not None:
-        raise ValueError("Only one of `timesteps` or `sigmas` can be passed. Please choose one to set custom values")
-    if timesteps is not None:
-        accepts_timesteps = "timesteps" in set(inspect.signature(scheduler.set_timesteps).parameters.keys())
-        if not accepts_timesteps:
-            raise ValueError(
-                f"The current scheduler class {scheduler.__class__}'s `set_timesteps` does not support custom"
-                f" timestep schedules. Please check whether you are using the correct scheduler."
-            )
-        scheduler.set_timesteps(timesteps=timesteps, device=device, **kwargs)
-        timesteps = scheduler.timesteps
-        num_inference_steps = len(timesteps)
-    elif sigmas is not None:
-        accept_sigmas = "sigmas" in set(inspect.signature(scheduler.set_timesteps).parameters.keys())
-        if not accept_sigmas:
-            raise ValueError(
-                f"The current scheduler class {scheduler.__class__}'s `set_timesteps` does not support custom"
-                f" sigmas schedules. Please check whether you are using the correct scheduler."
-            )
-        scheduler.set_timesteps(sigmas=sigmas, device=device, **kwargs)
-        timesteps = scheduler.timesteps
-        num_inference_steps = len(timesteps)
-    else:
-        scheduler.set_timesteps(num_inference_steps, device=device, **kwargs)
-        timesteps = scheduler.timesteps
-    return timesteps, num_inference_steps
-
-
-class TerrainDiffusionPipeline(
-    DiffusionPipeline,
-    StableDiffusionMixin,
-    TextualInversionLoaderMixin,
-    StableDiffusionLoraLoaderMixin,
-    IPAdapterMixin,
-    FromSingleFileMixin,
-):
-    r"""
-    Pipeline for text-to-image generation using Stable Diffusion.
-
-    This model inherits from [`DiffusionPipeline`]. Check the superclass documentation for the generic methods
-    implemented for all pipelines (downloading, saving, running on a particular device, etc.).
-
-    The pipeline also inherits the following loading methods:
-        - [`~loaders.TextualInversionLoaderMixin.load_textual_inversion`] for loading textual inversion embeddings
-        - [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] for loading LoRA weights
-        - [`~loaders.StableDiffusionLoraLoaderMixin.save_lora_weights`] for saving LoRA weights
-        - [`~loaders.FromSingleFileMixin.from_single_file`] for loading `.ckpt` files
-        - [`~loaders.IPAdapterMixin.load_ip_adapter`] for loading IP Adapters
-
-    Args:
-        vae ([`AutoencoderKL`]):
-            Variational Auto-Encoder (VAE) model to encode and decode images to and from latent representations.
-        text_encoder ([`~transformers.CLIPTextModel`]):
-            Frozen text-encoder ([clip-vit-large-patch14](https://huggingface.co/openai/clip-vit-large-patch14)).
-        tokenizer ([`~transformers.CLIPTokenizer`]):
-            A `CLIPTokenizer` to tokenize text.
-        unet ([`UNet2DConditionModel`]):
-            A `UNet2DConditionModel` to denoise the encoded image latents.
-        scheduler ([`SchedulerMixin`]):
-            A scheduler to be used in combination with `unet` to denoise the encoded image latents. Can be one of
-            [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
-        safety_checker ([`StableDiffusionSafetyChecker`]):
-            Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for more details
-            about a model's potential harms.
-        feature_extractor ([`~transformers.CLIPImageProcessor`]):
-            A `CLIPImageProcessor` to extract features from generated images; used as inputs to the `safety_checker`.
-    """
-
-    model_cpu_offload_seq = "text_encoder->image_encoder->unet->vae"
-    _optional_components = ["safety_checker", "feature_extractor", "image_encoder"]
-    _exclude_from_cpu_offload = ["safety_checker"]
-    _callback_tensor_inputs = ["latents", "prompt_embeds", "negative_prompt_embeds"]
-
-    def __init__(
-        self,
-        vae: AutoencoderKL,
-        text_encoder: CLIPTextModel,
-        tokenizer: CLIPTokenizer,
-        unet: UNet2DConditionModel,
-        scheduler: KarrasDiffusionSchedulers,
-        safety_checker: StableDiffusionSafetyChecker,
-        feature_extractor: CLIPImageProcessor,
-        image_encoder: CLIPVisionModelWithProjection = None,
-        requires_safety_checker: bool = True,
-    ):
-        super().__init__()
-
-        if hasattr(scheduler.config, "steps_offset") and scheduler.config.steps_offset != 1:
-            deprecation_message = (
-                f"The configuration file of this scheduler: {scheduler} is outdated. `steps_offset`"
-                f" should be set to 1 instead of {scheduler.config.steps_offset}. Please make sure "
-                "to update the config accordingly as leaving `steps_offset` might led to incorrect results"
-                " in future versions. If you have downloaded this checkpoint from the Hugging Face Hub,"
-                " it would be very nice if you could open a Pull request for the `scheduler/scheduler_config.json`"
-                " file"
-            )
-            deprecate("steps_offset!=1", "1.0.0", deprecation_message, standard_warn=False)
-            new_config = dict(scheduler.config)
-            new_config["steps_offset"] = 1
-            scheduler._internal_dict = FrozenDict(new_config)
-
-        if hasattr(scheduler.config, "clip_sample") and scheduler.config.clip_sample is True:
-            deprecation_message = (
-                f"The configuration file of this scheduler: {scheduler} has not set the configuration `clip_sample`."
-                " `clip_sample` should be set to False in the configuration file. Please make sure to update the"
-                " config accordingly as not setting `clip_sample` in the config might lead to incorrect results in"
-                " future versions. If you have downloaded this checkpoint from the Hugging Face Hub, it would be very"
-                " nice if you could open a Pull request for the `scheduler/scheduler_config.json` file"
-            )
-            deprecate("clip_sample not set", "1.0.0", deprecation_message, standard_warn=False)
-            new_config = dict(scheduler.config)
-            new_config["clip_sample"] = False
-            scheduler._internal_dict = FrozenDict(new_config)
-
-        if safety_checker is None and requires_safety_checker:
-            logger.warning(
-                f"You have disabled the safety checker for {self.__class__} by passing `safety_checker=None`. Ensure"
-                " that you abide to the conditions of the Stable Diffusion license and do not expose unfiltered"
-                " results in services or applications open to the public. Both the diffusers team and Hugging Face"
-                " strongly recommend to keep the safety filter enabled in all public facing circumstances, disabling"
-                " it only for use-cases that involve analyzing network behavior or auditing its results. For more"
-                " information, please have a look at https://github.com/huggingface/diffusers/pull/254 ."
-            )
-
-        if safety_checker is not None and feature_extractor is None:
-            raise ValueError(
-                "Make sure to define a feature extractor when loading {self.__class__} if you want to use the safety"
-                " checker. If you do not want to use the safety checker, you can pass `'safety_checker=None'` instead."
-            )
-
-        is_unet_version_less_0_9_0 = hasattr(unet.config, "_diffusers_version") and version.parse(
-            version.parse(unet.config._diffusers_version).base_version
-        ) < version.parse("0.9.0.dev0")
-        is_unet_sample_size_less_64 = hasattr(unet.config, "sample_size") and unet.config.sample_size < 64
-        if is_unet_version_less_0_9_0 and is_unet_sample_size_less_64:
-            deprecation_message = (
-                "The configuration file of the unet has set the default `sample_size` to smaller than"
-                " 64 which seems highly unlikely. If your checkpoint is a fine-tuned version of any of the"
-                " following: \n- CompVis/stable-diffusion-v1-4 \n- CompVis/stable-diffusion-v1-3 \n-"
-                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- runwayml/stable-diffusion-v1-5"
-                " \n- runwayml/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
-                " configuration file. Please make sure to update the config accordingly as leaving `sample_size=32`"
-                " in the config might lead to incorrect results in future versions. If you have downloaded this"
-                " checkpoint from the Hugging Face Hub, it would be very nice if you could open a Pull request for"
-                " the `unet/config.json` file"
-            )
-            deprecate("sample_size<64", "1.0.0", deprecation_message, standard_warn=False)
-            new_config = dict(unet.config)
-            new_config["sample_size"] = 64
-            unet._internal_dict = FrozenDict(new_config)
-
-        self.register_modules(
-            vae=vae,
-            text_encoder=text_encoder,
-            tokenizer=tokenizer,
-            unet=unet,
-            scheduler=scheduler,
-            safety_checker=safety_checker,
-            feature_extractor=feature_extractor,
-            image_encoder=image_encoder,
-        )
-        self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1)
-        self.image_processor = VaeImageProcessor(vae_scale_factor=self.vae_scale_factor)
-        self.register_to_config(requires_safety_checker=requires_safety_checker)
-
-    def _encode_prompt(
-        self,
-        prompt,
-        device,
-        num_images_per_prompt,
-        do_classifier_free_guidance,
-        negative_prompt=None,
-        prompt_embeds: Optional[torch.Tensor] = None,
-        negative_prompt_embeds: Optional[torch.Tensor] = None,
-        lora_scale: Optional[float] = None,
-        **kwargs,
-    ):
-        deprecation_message = "`_encode_prompt()` is deprecated and it will be removed in a future version. Use `encode_prompt()` instead. Also, be aware that the output format changed from a concatenated tensor to a tuple."
-        deprecate("_encode_prompt()", "1.0.0", deprecation_message, standard_warn=False)
-
-        prompt_embeds_tuple = self.encode_prompt(
-            prompt=prompt,
-            device=device,
-            num_images_per_prompt=num_images_per_prompt,
-            do_classifier_free_guidance=do_classifier_free_guidance,
-            negative_prompt=negative_prompt,
-            prompt_embeds=prompt_embeds,
-            negative_prompt_embeds=negative_prompt_embeds,
-            lora_scale=lora_scale,
-            **kwargs,
-        )
-
-        # concatenate for backwards comp
-        prompt_embeds = torch.cat([prompt_embeds_tuple[1], prompt_embeds_tuple[0]])
-
-        return prompt_embeds
-
-    def encode_prompt(
-        self,
-        prompt,
-        device,
-        num_images_per_prompt,
-        do_classifier_free_guidance,
-        negative_prompt=None,
-        prompt_embeds: Optional[torch.Tensor] = None,
-        negative_prompt_embeds: Optional[torch.Tensor] = None,
-        lora_scale: Optional[float] = None,
-        clip_skip: Optional[int] = None,
-    ):
-        r"""
-        Encodes the prompt into text encoder hidden states.
-
-        Args:
-            prompt (`str` or `List[str]`, *optional*):
-                prompt to be encoded
-            device: (`torch.device`):
-                torch device
-            num_images_per_prompt (`int`):
-                number of images that should be generated per prompt
-            do_classifier_free_guidance (`bool`):
-                whether to use classifier free guidance or not
-            negative_prompt (`str` or `List[str]`, *optional*):
-                The prompt or prompts not to guide the image generation. If not defined, one has to pass
-                `negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is
-                less than `1`).
-            prompt_embeds (`torch.Tensor`, *optional*):
-                Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
-                provided, text embeddings will be generated from `prompt` input argument.
-            negative_prompt_embeds (`torch.Tensor`, *optional*):
-                Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
-                weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
-                argument.
-            lora_scale (`float`, *optional*):
-                A LoRA scale that will be applied to all LoRA layers of the text encoder if LoRA layers are loaded.
-            clip_skip (`int`, *optional*):
-                Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that
-                the output of the pre-final layer will be used for computing the prompt embeddings.
-        """
-        # set lora scale so that monkey patched LoRA
-        # function of text encoder can correctly access it
-        if lora_scale is not None and isinstance(self, StableDiffusionLoraLoaderMixin):
-            self._lora_scale = lora_scale
-
-            # dynamically adjust the LoRA scale
-            if not USE_PEFT_BACKEND:
-                adjust_lora_scale_text_encoder(self.text_encoder, lora_scale)
-            else:
-                scale_lora_layers(self.text_encoder, lora_scale)
-
-        if prompt is not None and isinstance(prompt, str):
-            batch_size = 1
-        elif prompt is not None and isinstance(prompt, list):
-            batch_size = len(prompt)
-        else:
-            batch_size = prompt_embeds.shape[0]
-
-        if prompt_embeds is None:
-            # textual inversion: process multi-vector tokens if necessary
-            if isinstance(self, TextualInversionLoaderMixin):
-                prompt = self.maybe_convert_prompt(prompt, self.tokenizer)
-
-            text_inputs = self.tokenizer(
-                prompt,
-                padding="max_length",
-                max_length=self.tokenizer.model_max_length,
-                truncation=True,
-                return_tensors="pt",
-            )
-            text_input_ids = text_inputs.input_ids
-            untruncated_ids = self.tokenizer(prompt, padding="longest", return_tensors="pt").input_ids
-
-            if untruncated_ids.shape[-1] >= text_input_ids.shape[-1] and not torch.equal(
-                text_input_ids, untruncated_ids
-            ):
-                removed_text = self.tokenizer.batch_decode(
-                    untruncated_ids[:, self.tokenizer.model_max_length - 1 : -1]
-                )
-                logger.warning(
-                    "The following part of your input was truncated because CLIP can only handle sequences up to"
-                    f" {self.tokenizer.model_max_length} tokens: {removed_text}"
-                )
-
-            if hasattr(self.text_encoder.config, "use_attention_mask") and self.text_encoder.config.use_attention_mask:
-                attention_mask = text_inputs.attention_mask.to(device)
-            else:
-                attention_mask = None
-
-            if clip_skip is None:
-                prompt_embeds = self.text_encoder(text_input_ids.to(device), attention_mask=attention_mask)
-                prompt_embeds = prompt_embeds[0]
-            else:
-                prompt_embeds = self.text_encoder(
-                    text_input_ids.to(device), attention_mask=attention_mask, output_hidden_states=True
-                )
-                # Access the `hidden_states` first, that contains a tuple of
-                # all the hidden states from the encoder layers. Then index into
-                # the tuple to access the hidden states from the desired layer.
-                prompt_embeds = prompt_embeds[-1][-(clip_skip + 1)]
-                # We also need to apply the final LayerNorm here to not mess with the
-                # representations. The `last_hidden_states` that we typically use for
-                # obtaining the final prompt representations passes through the LayerNorm
-                # layer.
-                prompt_embeds = self.text_encoder.text_model.final_layer_norm(prompt_embeds)
-
-        if self.text_encoder is not None:
-            prompt_embeds_dtype = self.text_encoder.dtype
-        elif self.unet is not None:
-            prompt_embeds_dtype = self.unet.dtype
-        else:
-            prompt_embeds_dtype = prompt_embeds.dtype
-
-        prompt_embeds = prompt_embeds.to(dtype=prompt_embeds_dtype, device=device)
-
-        bs_embed, seq_len, _ = prompt_embeds.shape
-        # duplicate text embeddings for each generation per prompt, using mps friendly method
-        prompt_embeds = prompt_embeds.repeat(1, num_images_per_prompt, 1)
-        prompt_embeds = prompt_embeds.view(bs_embed * num_images_per_prompt, seq_len, -1)
-
-        # get unconditional embeddings for classifier free guidance
-        if do_classifier_free_guidance and negative_prompt_embeds is None:
-            uncond_tokens: List[str]
-            if negative_prompt is None:
-                uncond_tokens = [""] * batch_size
-            elif prompt is not None and type(prompt) is not type(negative_prompt):
-                raise TypeError(
-                    f"`negative_prompt` should be the same type to `prompt`, but got {type(negative_prompt)} !="
-                    f" {type(prompt)}."
-                )
-            elif isinstance(negative_prompt, str):
-                uncond_tokens = [negative_prompt]
-            elif batch_size != len(negative_prompt):
-                raise ValueError(
-                    f"`negative_prompt`: {negative_prompt} has batch size {len(negative_prompt)}, but `prompt`:"
-                    f" {prompt} has batch size {batch_size}. Please make sure that passed `negative_prompt` matches"
-                    " the batch size of `prompt`."
-                )
-            else:
-                uncond_tokens = negative_prompt
-
-            # textual inversion: process multi-vector tokens if necessary
-            if isinstance(self, TextualInversionLoaderMixin):
-                uncond_tokens = self.maybe_convert_prompt(uncond_tokens, self.tokenizer)
-
-            max_length = prompt_embeds.shape[1]
-            uncond_input = self.tokenizer(
-                uncond_tokens,
-                padding="max_length",
-                max_length=max_length,
-                truncation=True,
-                return_tensors="pt",
-            )
-
-            if hasattr(self.text_encoder.config, "use_attention_mask") and self.text_encoder.config.use_attention_mask:
-                attention_mask = uncond_input.attention_mask.to(device)
-            else:
-                attention_mask = None
-
-            negative_prompt_embeds = self.text_encoder(
-                uncond_input.input_ids.to(device),
-                attention_mask=attention_mask,
-            )
-            negative_prompt_embeds = negative_prompt_embeds[0]
-
-        if do_classifier_free_guidance:
-            # duplicate unconditional embeddings for each generation per prompt, using mps friendly method
-            seq_len = negative_prompt_embeds.shape[1]
-
-            negative_prompt_embeds = negative_prompt_embeds.to(dtype=prompt_embeds_dtype, device=device)
-
-            negative_prompt_embeds = negative_prompt_embeds.repeat(1, num_images_per_prompt, 1)
-            negative_prompt_embeds = negative_prompt_embeds.view(batch_size * num_images_per_prompt, seq_len, -1)
-
-        if self.text_encoder is not None:
-            if isinstance(self, StableDiffusionLoraLoaderMixin) and USE_PEFT_BACKEND:
-                # Retrieve the original scale by scaling back the LoRA layers
-                unscale_lora_layers(self.text_encoder, lora_scale)
-
-        return prompt_embeds, negative_prompt_embeds
-
-    def encode_image(self, image, device, num_images_per_prompt, output_hidden_states=None):
-        dtype = next(self.image_encoder.parameters()).dtype
-
-        if not isinstance(image, torch.Tensor):
-            image = self.feature_extractor(image, return_tensors="pt").pixel_values
-
-        image = image.to(device=device, dtype=dtype)
-        if output_hidden_states:
-            image_enc_hidden_states = self.image_encoder(image, output_hidden_states=True).hidden_states[-2]
-            image_enc_hidden_states = image_enc_hidden_states.repeat_interleave(num_images_per_prompt, dim=0)
-            uncond_image_enc_hidden_states = self.image_encoder(
-                torch.zeros_like(image), output_hidden_states=True
-            ).hidden_states[-2]
-            uncond_image_enc_hidden_states = uncond_image_enc_hidden_states.repeat_interleave(
-                num_images_per_prompt, dim=0
-            )
-            return image_enc_hidden_states, uncond_image_enc_hidden_states
-        else:
-            image_embeds = self.image_encoder(image).image_embeds
-            image_embeds = image_embeds.repeat_interleave(num_images_per_prompt, dim=0)
-            uncond_image_embeds = torch.zeros_like(image_embeds)
-
-            return image_embeds, uncond_image_embeds
-
-    def prepare_ip_adapter_image_embeds(
-        self, ip_adapter_image, ip_adapter_image_embeds, device, num_images_per_prompt, do_classifier_free_guidance
-    ):
-        image_embeds = []
-        if do_classifier_free_guidance:
-            negative_image_embeds = []
-        if ip_adapter_image_embeds is None:
-            if not isinstance(ip_adapter_image, list):
-                ip_adapter_image = [ip_adapter_image]
-
-            if len(ip_adapter_image) != len(self.unet.encoder_hid_proj.image_projection_layers):
-                raise ValueError(
-                    f"`ip_adapter_image` must have same length as the number of IP Adapters. Got {len(ip_adapter_image)} images and {len(self.unet.encoder_hid_proj.image_projection_layers)} IP Adapters."
-                )
-
-            for single_ip_adapter_image, image_proj_layer in zip(
-                ip_adapter_image, self.unet.encoder_hid_proj.image_projection_layers
-            ):
-                output_hidden_state = not isinstance(image_proj_layer, ImageProjection)
-                single_image_embeds, single_negative_image_embeds = self.encode_image(
-                    single_ip_adapter_image, device, 1, output_hidden_state
-                )
-
-                image_embeds.append(single_image_embeds[None, :])
-                if do_classifier_free_guidance:
-                    negative_image_embeds.append(single_negative_image_embeds[None, :])
-        else:
-            for single_image_embeds in ip_adapter_image_embeds:
-                if do_classifier_free_guidance:
-                    single_negative_image_embeds, single_image_embeds = single_image_embeds.chunk(2)
-                    negative_image_embeds.append(single_negative_image_embeds)
-                image_embeds.append(single_image_embeds)
-
-        ip_adapter_image_embeds = []
-        for i, single_image_embeds in enumerate(image_embeds):
-            single_image_embeds = torch.cat([single_image_embeds] * num_images_per_prompt, dim=0)
-            if do_classifier_free_guidance:
-                single_negative_image_embeds = torch.cat([negative_image_embeds[i]] * num_images_per_prompt, dim=0)
-                single_image_embeds = torch.cat([single_negative_image_embeds, single_image_embeds], dim=0)
-
-            single_image_embeds = single_image_embeds.to(device=device)
-            ip_adapter_image_embeds.append(single_image_embeds)
-
-        return ip_adapter_image_embeds
-
-
-    def decode_latents(self, latents):
-        deprecation_message = "The decode_latents method is deprecated and will be removed in 1.0.0. Please use VaeImageProcessor.postprocess(...) instead"
-        deprecate("decode_latents", "1.0.0", deprecation_message, standard_warn=False)
-
-        latents = 1 / self.vae.config.scaling_factor * latents
-        image = self.vae.decode(latents, return_dict=False)[0]
-        image = (image / 2 + 0.5).clamp(0, 1)
-        # we always cast to float32 as this does not cause significant overhead and is compatible with bfloat16
-        image = image.cpu().permute(0, 2, 3, 1).float().numpy()
-        return image
-
-    def prepare_extra_step_kwargs(self, generator, eta):
-        # prepare extra kwargs for the scheduler step, since not all schedulers have the same signature
-        # eta (η) is only used with the DDIMScheduler, it will be ignored for other schedulers.
-        # eta corresponds to η in DDIM paper: https://arxiv.org/abs/2010.02502
-        # and should be between [0, 1]
-
-        accepts_eta = "eta" in set(inspect.signature(self.scheduler.step).parameters.keys())
-        extra_step_kwargs = {}
-        if accepts_eta:
-            extra_step_kwargs["eta"] = eta
-
-        # check if the scheduler accepts generator
-        accepts_generator = "generator" in set(inspect.signature(self.scheduler.step).parameters.keys())
-        if accepts_generator:
-            extra_step_kwargs["generator"] = generator
-        return extra_step_kwargs
-
-    def check_inputs(
-        self,
-        prompt,
-        height,
-        width,
-        callback_steps,
-        negative_prompt=None,
-        prompt_embeds=None,
-        negative_prompt_embeds=None,
-        ip_adapter_image=None,
-        ip_adapter_image_embeds=None,
-        callback_on_step_end_tensor_inputs=None,
-    ):
-        if height % 8 != 0 or width % 8 != 0:
-            raise ValueError(f"`height` and `width` have to be divisible by 8 but are {height} and {width}.")
-
-        if callback_steps is not None and (not isinstance(callback_steps, int) or callback_steps <= 0):
-            raise ValueError(
-                f"`callback_steps` has to be a positive integer but is {callback_steps} of type"
-                f" {type(callback_steps)}."
-            )
-        if callback_on_step_end_tensor_inputs is not None and not all(
-            k in self._callback_tensor_inputs for k in callback_on_step_end_tensor_inputs
-        ):
-            raise ValueError(
-                f"`callback_on_step_end_tensor_inputs` has to be in {self._callback_tensor_inputs}, but found {[k for k in callback_on_step_end_tensor_inputs if k not in self._callback_tensor_inputs]}"
-            )
-
-        if prompt is not None and prompt_embeds is not None:
-            raise ValueError(
-                f"Cannot forward both `prompt`: {prompt} and `prompt_embeds`: {prompt_embeds}. Please make sure to"
-                " only forward one of the two."
-            )
-        elif prompt is None and prompt_embeds is None:
-            raise ValueError(
-                "Provide either `prompt` or `prompt_embeds`. Cannot leave both `prompt` and `prompt_embeds` undefined."
-            )
-        elif prompt is not None and (not isinstance(prompt, str) and not isinstance(prompt, list)):
-            raise ValueError(f"`prompt` has to be of type `str` or `list` but is {type(prompt)}")
-
-        if negative_prompt is not None and negative_prompt_embeds is not None:
-            raise ValueError(
-                f"Cannot forward both `negative_prompt`: {negative_prompt} and `negative_prompt_embeds`:"
-                f" {negative_prompt_embeds}. Please make sure to only forward one of the two."
-            )
-
-        if prompt_embeds is not None and negative_prompt_embeds is not None:
-            if prompt_embeds.shape != negative_prompt_embeds.shape:
-                raise ValueError(
-                    "`prompt_embeds` and `negative_prompt_embeds` must have the same shape when passed directly, but"
-                    f" got: `prompt_embeds` {prompt_embeds.shape} != `negative_prompt_embeds`"
-                    f" {negative_prompt_embeds.shape}."
-                )
-
-        if ip_adapter_image is not None and ip_adapter_image_embeds is not None:
-            raise ValueError(
-                "Provide either `ip_adapter_image` or `ip_adapter_image_embeds`. Cannot leave both `ip_adapter_image` and `ip_adapter_image_embeds` defined."
-            )
-
-        if ip_adapter_image_embeds is not None:
-            if not isinstance(ip_adapter_image_embeds, list):
-                raise ValueError(
-                    f"`ip_adapter_image_embeds` has to be of type `list` but is {type(ip_adapter_image_embeds)}"
-                )
-            elif ip_adapter_image_embeds[0].ndim not in [3, 4]:
-                raise ValueError(
-                    f"`ip_adapter_image_embeds` has to be a list of 3D or 4D tensors but is {ip_adapter_image_embeds[0].ndim}D"
-                )
-
-    def prepare_latents(self, batch_size, num_channels_latents, height, width, dtype, device, generator, latents=None):
-        shape = (
-            batch_size,
-            num_channels_latents,
-            int(height) // self.vae_scale_factor,
-            int(width) // self.vae_scale_factor,
-        )
-        if isinstance(generator, list) and len(generator) != batch_size:
-            raise ValueError(
-                f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"
-                f" size of {batch_size}. Make sure the batch size matches the length of the generators."
-            )
-
-        if latents is None:
-            latents = randn_tensor(shape, generator=generator, device=device, dtype=dtype)
-        else:
-            latents = latents.to(device)
-
-        # scale the initial noise by the standard deviation required by the scheduler
-        latents = latents * self.scheduler.init_noise_sigma
-        return latents
-
-    # Copied from diffusers.pipelines.latent_consistency_models.pipeline_latent_consistency_text2img.LatentConsistencyModelPipeline.get_guidance_scale_embedding
-    def get_guidance_scale_embedding(
-        self, w: torch.Tensor, embedding_dim: int = 512, dtype: torch.dtype = torch.float32
-    ) -> torch.Tensor:
-        """
-        See https://github.com/google-research/vdm/blob/dc27b98a554f65cdc654b800da5aa1846545d41b/model_vdm.py#L298
-
-        Args:
-            w (`torch.Tensor`):
-                Generate embedding vectors with a specified guidance scale to subsequently enrich timestep embeddings.
-            embedding_dim (`int`, *optional*, defaults to 512):
-                Dimension of the embeddings to generate.
-            dtype (`torch.dtype`, *optional*, defaults to `torch.float32`):
-                Data type of the generated embeddings.
-
-        Returns:
-            `torch.Tensor`: Embedding vectors with shape `(len(w), embedding_dim)`.
-        """
-        assert len(w.shape) == 1
-        w = w * 1000.0
-
-        half_dim = embedding_dim // 2
-        emb = torch.log(torch.tensor(10000.0)) / (half_dim - 1)
-        emb = torch.exp(torch.arange(half_dim, dtype=dtype) * -emb)
-        emb = w.to(dtype)[:, None] * emb[None, :]
-        emb = torch.cat([torch.sin(emb), torch.cos(emb)], dim=1)
-        if embedding_dim % 2 == 1:  # zero pad
-            emb = torch.nn.functional.pad(emb, (0, 1))
-        assert emb.shape == (w.shape[0], embedding_dim)
-        return emb
-
-    @property
-    def guidance_scale(self):
-        return self._guidance_scale
-
-    @property
-    def guidance_rescale(self):
-        return self._guidance_rescale
-
-    @property
-    def clip_skip(self):
-        return self._clip_skip
-
-    # here `guidance_scale` is defined analog to the guidance weight `w` of equation (2)
-    # of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1`
-    # corresponds to doing no classifier free guidance.
-    @property
-    def do_classifier_free_guidance(self):
-        return self._guidance_scale > 1 and self.unet.config.time_cond_proj_dim is None
-
-    @property
-    def cross_attention_kwargs(self):
-        return self._cross_attention_kwargs
-
-    @property
-    def num_timesteps(self):
-        return self._num_timesteps
-
-    @property
-    def interrupt(self):
-        return self._interrupt
-    
-    def decode_rgbd(self, latents,generator,output_type="np"):
-        dem_latents = latents[:,4:,:,:]
-        img_latents = latents[:,:4,:,:]
-        image = self.vae.decode(img_latents / self.vae.config.scaling_factor, return_dict=False, generator=generator)[
-            0
-        ]
-        dem = self.vae.decode(dem_latents / self.vae.config.scaling_factor, return_dict=False, generator=generator)[
-            0
-        ]
-        do_denormalize = [True] * image.shape[0]
-        image = self.image_processor.postprocess(image, output_type=output_type, do_denormalize=do_denormalize)
-        dem = self.image_processor.postprocess(dem, output_type=output_type, do_denormalize=do_denormalize)
-        return image,dem
-
-    @torch.no_grad()
-    @replace_example_docstring(EXAMPLE_DOC_STRING)
-    def __call__(
-        self,
-        prompt: Union[str, List[str]] = None,
-        height: Optional[int] = None,
-        width: Optional[int] = None,
-        num_inference_steps: int = 50,
-        timesteps: List[int] = None,
-        sigmas: List[float] = None,
-        guidance_scale: float = 7.5,
-        negative_prompt: Optional[Union[str, List[str]]] = None,
-        num_images_per_prompt: Optional[int] = 1,
-        eta: float = 0.0,
-        generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
-        latents: Optional[torch.Tensor] = None,
-        prompt_embeds: Optional[torch.Tensor] = None,
-        negative_prompt_embeds: Optional[torch.Tensor] = None,
-        ip_adapter_image: Optional[PipelineImageInput] = None,
-        ip_adapter_image_embeds: Optional[List[torch.Tensor]] = None,
-        output_type: Optional[str] = "np",
-        return_dict: bool = True,
-        cross_attention_kwargs: Optional[Dict[str, Any]] = None,
-        guidance_rescale: float = 0.0,
-        clip_skip: Optional[int] = None,
-        callback_on_step_end: Optional[
-            Union[Callable[[int, int, Dict], None], PipelineCallback, MultiPipelineCallbacks]
-        ] = None,
-        callback_on_step_end_tensor_inputs: List[str] = ["latents"],
-        **kwargs,
-    ):
-        r"""
-        The call function to the pipeline for generation.
-
-        Args:
-            prompt (`str` or `List[str]`, *optional*):
-                The prompt or prompts to guide image generation. If not defined, you need to pass `prompt_embeds`.
-            height (`int`, *optional*, defaults to `self.unet.config.sample_size * self.vae_scale_factor`):
-                The height in pixels of the generated image.
-            width (`int`, *optional*, defaults to `self.unet.config.sample_size * self.vae_scale_factor`):
-                The width in pixels of the generated image.
-            num_inference_steps (`int`, *optional*, defaults to 50):
-                The number of denoising steps. More denoising steps usually lead to a higher quality image at the
-                expense of slower inference.
-            timesteps (`List[int]`, *optional*):
-                Custom timesteps to use for the denoising process with schedulers which support a `timesteps` argument
-                in their `set_timesteps` method. If not defined, the default behavior when `num_inference_steps` is
-                passed will be used. Must be in descending order.
-            sigmas (`List[float]`, *optional*):
-                Custom sigmas to use for the denoising process with schedulers which support a `sigmas` argument in
-                their `set_timesteps` method. If not defined, the default behavior when `num_inference_steps` is passed
-                will be used.
-            guidance_scale (`float`, *optional*, defaults to 7.5):
-                A higher guidance scale value encourages the model to generate images closely linked to the text
-                `prompt` at the expense of lower image quality. Guidance scale is enabled when `guidance_scale > 1`.
-            negative_prompt (`str` or `List[str]`, *optional*):
-                The prompt or prompts to guide what to not include in image generation. If not defined, you need to
-                pass `negative_prompt_embeds` instead. Ignored when not using guidance (`guidance_scale < 1`).
-            num_images_per_prompt (`int`, *optional*, defaults to 1):
-                The number of images to generate per prompt.
-            eta (`float`, *optional*, defaults to 0.0):
-                Corresponds to parameter eta (η) from the [DDIM](https://arxiv.org/abs/2010.02502) paper. Only applies
-                to the [`~schedulers.DDIMScheduler`], and is ignored in other schedulers.
-            generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
-                A [`torch.Generator`](https://pytorch.org/docs/stable/generated/torch.Generator.html) to make
-                generation deterministic.
-            latents (`torch.Tensor`, *optional*):
-                Pre-generated noisy latents sampled from a Gaussian distribution, to be used as inputs for image
-                generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
-                tensor is generated by sampling using the supplied random `generator`.
-            prompt_embeds (`torch.Tensor`, *optional*):
-                Pre-generated text embeddings. Can be used to easily tweak text inputs (prompt weighting). If not
-                provided, text embeddings are generated from the `prompt` input argument.
-            negative_prompt_embeds (`torch.Tensor`, *optional*):
-                Pre-generated negative text embeddings. Can be used to easily tweak text inputs (prompt weighting). If
-                not provided, `negative_prompt_embeds` are generated from the `negative_prompt` input argument.
-            ip_adapter_image: (`PipelineImageInput`, *optional*): Optional image input to work with IP Adapters.
-            ip_adapter_image_embeds (`List[torch.Tensor]`, *optional*):
-                Pre-generated image embeddings for IP-Adapter. It should be a list of length same as number of
-                IP-adapters. Each element should be a tensor of shape `(batch_size, num_images, emb_dim)`. It should
-                contain the negative image embedding if `do_classifier_free_guidance` is set to `True`. If not
-                provided, embeddings are computed from the `ip_adapter_image` input argument.
-            output_type (`str`, *optional*, defaults to `"pil"`):
-                The output format of the generated image. Choose between `PIL.Image` or `np.array`.
-            return_dict (`bool`, *optional*, defaults to `True`):
-                Whether or not to return a [`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] instead of a
-                plain tuple.
-            cross_attention_kwargs (`dict`, *optional*):
-                A kwargs dictionary that if specified is passed along to the [`AttentionProcessor`] as defined in
-                [`self.processor`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py).
-            guidance_rescale (`float`, *optional*, defaults to 0.0):
-                Guidance rescale factor from [Common Diffusion Noise Schedules and Sample Steps are
-                Flawed](https://arxiv.org/pdf/2305.08891.pdf). Guidance rescale factor should fix overexposure when
-                using zero terminal SNR.
-            clip_skip (`int`, *optional*):
-                Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that
-                the output of the pre-final layer will be used for computing the prompt embeddings.
-            callback_on_step_end (`Callable`, `PipelineCallback`, `MultiPipelineCallbacks`, *optional*):
-                A function or a subclass of `PipelineCallback` or `MultiPipelineCallbacks` that is called at the end of
-                each denoising step during the inference. with the following arguments: `callback_on_step_end(self:
-                DiffusionPipeline, step: int, timestep: int, callback_kwargs: Dict)`. `callback_kwargs` will include a
-                list of all tensors as specified by `callback_on_step_end_tensor_inputs`.
-            callback_on_step_end_tensor_inputs (`List`, *optional*):
-                The list of tensor inputs for the `callback_on_step_end` function. The tensors specified in the list
-                will be passed as `callback_kwargs` argument. You will only be able to include variables listed in the
-                `._callback_tensor_inputs` attribute of your pipeline class.
-
-        Examples:
-
-        Returns:
-            [`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] or `tuple`:
-                If `return_dict` is `True`, [`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] is returned,
-                otherwise a `tuple` is returned where the first element is a list with the generated images and the
-                second element is a list of `bool`s indicating whether the corresponding generated image contains
-                "not-safe-for-work" (nsfw) content.
-        """
-
-        callback = kwargs.pop("callback", None)
-        callback_steps = kwargs.pop("callback_steps", None)
-
-        if callback is not None:
-            deprecate(
-                "callback",
-                "1.0.0",
-                "Passing `callback` as an input argument to `__call__` is deprecated, consider using `callback_on_step_end`",
-            )
-        if callback_steps is not None:
-            deprecate(
-                "callback_steps",
-                "1.0.0",
-                "Passing `callback_steps` as an input argument to `__call__` is deprecated, consider using `callback_on_step_end`",
-            )
-
-        if isinstance(callback_on_step_end, (PipelineCallback, MultiPipelineCallbacks)):
-            callback_on_step_end_tensor_inputs = callback_on_step_end.tensor_inputs
-
-        # 0. Default height and width to unet
-        height = height or self.unet.config.sample_size * self.vae_scale_factor
-        width = width or self.unet.config.sample_size * self.vae_scale_factor
-        # to deal with lora scaling and other possible forward hooks
-
-        # 1. Check inputs. Raise error if not correct
-        self.check_inputs(
-            prompt,
-            height,
-            width,
-            callback_steps,
-            negative_prompt,
-            prompt_embeds,
-            negative_prompt_embeds,
-            ip_adapter_image,
-            ip_adapter_image_embeds,
-            callback_on_step_end_tensor_inputs,
-        )
-
-        self._guidance_scale = guidance_scale
-        self._guidance_rescale = guidance_rescale
-        self._clip_skip = clip_skip
-        self._cross_attention_kwargs = cross_attention_kwargs
-        self._interrupt = False
-
-        # 2. Define call parameters
-        if prompt is not None and isinstance(prompt, str):
-            batch_size = 1
-        elif prompt is not None and isinstance(prompt, list):
-            batch_size = len(prompt)
-        else:
-            batch_size = prompt_embeds.shape[0]
-
-        device = self._execution_device
-
-        # 3. Encode input prompt
-        lora_scale = (
-            self.cross_attention_kwargs.get("scale", None) if self.cross_attention_kwargs is not None else None
-        )
-
-        prompt_embeds, negative_prompt_embeds = self.encode_prompt(
-            prompt,
-            device,
-            num_images_per_prompt,
-            self.do_classifier_free_guidance,
-            negative_prompt,
-            prompt_embeds=prompt_embeds,
-            negative_prompt_embeds=negative_prompt_embeds,
-            lora_scale=lora_scale,
-            clip_skip=self.clip_skip,
-        )
-
-        # For classifier free guidance, we need to do two forward passes.
-        # Here we concatenate the unconditional and text embeddings into a single batch
-        # to avoid doing two forward passes
-        if self.do_classifier_free_guidance:
-            prompt_embeds = torch.cat([negative_prompt_embeds, prompt_embeds])
-
-        if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
-            image_embeds = self.prepare_ip_adapter_image_embeds(
-                ip_adapter_image,
-                ip_adapter_image_embeds,
-                device,
-                batch_size * num_images_per_prompt,
-                self.do_classifier_free_guidance,
-            )
-
-        # 4. Prepare timesteps
-        timesteps, num_inference_steps = retrieve_timesteps(
-            self.scheduler, num_inference_steps, device, timesteps, sigmas
-        )
-
-        # 5. Prepare latent variables
-        num_channels_latents = self.unet.config.in_channels*2
-        latents = self.prepare_latents(
-            batch_size * num_images_per_prompt,
-            num_channels_latents,
-            height,
-            width,
-            prompt_embeds.dtype,
-            device,
-            generator,
-            latents,
-        )
-
-        # 6. Prepare extra step kwargs. TODO: Logic should ideally just be moved out of the pipeline
-        extra_step_kwargs = self.prepare_extra_step_kwargs(generator, eta)
-
-        # 6.1 Add image embeds for IP-Adapter
-        added_cond_kwargs = (
-            {"image_embeds": image_embeds}
-            if (ip_adapter_image is not None or ip_adapter_image_embeds is not None)
-            else None
-        )
-
-        # 6.2 Optionally get Guidance Scale Embedding
-        timestep_cond = None
-        if self.unet.config.time_cond_proj_dim is not None:
-            guidance_scale_tensor = torch.tensor(self.guidance_scale - 1).repeat(batch_size * num_images_per_prompt)
-            timestep_cond = self.get_guidance_scale_embedding(
-                guidance_scale_tensor, embedding_dim=self.unet.config.time_cond_proj_dim
-            ).to(device=device, dtype=latents.dtype)
-
-        # 7. Denoising loop
-        num_warmup_steps = len(timesteps) - num_inference_steps * self.scheduler.order
-        self._num_timesteps = len(timesteps)
-#        intermediate_latents = []
-        with self.progress_bar(total=num_inference_steps) as progress_bar:
-            for i, t in enumerate(timesteps):
-                if self.interrupt:
-                    continue
-
-                # expand the latents if we are doing classifier free guidance
-                latent_model_input = torch.cat([latents] * 2) if self.do_classifier_free_guidance else latents
-                latent_model_input = self.scheduler.scale_model_input(latent_model_input, t)
-
-                # predict the noise residual
-                noise_pred = self.unet(
-                    latent_model_input,
-                    t,
-                    encoder_hidden_states=prompt_embeds,
-                    timestep_cond=timestep_cond,
-                    cross_attention_kwargs=self.cross_attention_kwargs,
-                    added_cond_kwargs=added_cond_kwargs,
-                    return_dict=False,
-                )[0]
-
-                # perform guidance
-                if self.do_classifier_free_guidance:
-                    noise_pred_uncond, noise_pred_text = noise_pred.chunk(2)
-                    noise_pred = noise_pred_uncond + self.guidance_scale * (noise_pred_text - noise_pred_uncond)
-
-                if self.do_classifier_free_guidance and self.guidance_rescale > 0.0:
-                    # Based on 3.4. in https://arxiv.org/pdf/2305.08891.pdf
-                    noise_pred = rescale_noise_cfg(noise_pred, noise_pred_text, guidance_rescale=self.guidance_rescale)
-
-                # compute the previous noisy sample x_t -> x_t-1
-                scheduler_output = self.scheduler.step(noise_pred, t, latents, **extra_step_kwargs, return_dict=True)
-                latents = scheduler_output.prev_sample
-#                if i % 10 == 0:
-#                   intermediate_latents.append(scheduler_output.pred_original_sample)
-                if callback_on_step_end is not None:
-                    callback_kwargs = {}
-                    for k in callback_on_step_end_tensor_inputs:
-                        callback_kwargs[k] = locals()[k]
-                    callback_outputs = callback_on_step_end(self, i, t, callback_kwargs)
-
-                    latents = callback_outputs.pop("latents", latents)
-                    prompt_embeds = callback_outputs.pop("prompt_embeds", prompt_embeds)
-                    negative_prompt_embeds = callback_outputs.pop("negative_prompt_embeds", negative_prompt_embeds)
-
-                # call the callback, if provided
-                if i == len(timesteps) - 1 or ((i + 1) > num_warmup_steps and (i + 1) % self.scheduler.order == 0):
-                    progress_bar.update()
-                    if callback is not None and i % callback_steps == 0:
-                        step_idx = i // getattr(self.scheduler, "order", 1)
-                        callback(step_idx, t, latents)
-
-                if XLA_AVAILABLE:
-                    xm.mark_step()
-
-        image,dem = self.decode_rgbd(latents,generator,output_type)
-
-     #   intermediate = [self.decode_rgbd(latent,generator,output_type)for latent in intermediate_latents]
-
-        # Offload all models
-        self.maybe_free_model_hooks()
-
-        return image,dem

src/.ipynb_checkpoints/utils-checkpoint.py

@@ -1,59 +0,0 @@
-import numpy as np
-import trimesh
-import tempfile
-import torch
-from scipy.spatial import Delaunay
-from .build_pipe import *
-
-pipe = build_pipe()
-
-def generate_terrain(prompt, num_inference_steps, guidance_scale, seed, crop_size, prefix):
-    """Generates terrain data (RGB and elevation) from a text prompt."""
-    if prefix and not prefix.endswith(' '):
-        prefix += ' '  # Ensure prefix ends with a space
-
-    full_prompt = prefix + prompt
-    generator = torch.Generator("cuda").manual_seed(seed)
-    image, dem = pipe(full_prompt, num_inference_steps=num_inference_steps, guidance_scale=guidance_scale, generator=generator)
-
-    # Center crop the image and dem
-    h, w, c = image[0].shape
-    start_h = (h - crop_size) // 2
-    start_w = (w - crop_size) // 2
-    end_h = start_h + crop_size
-    end_w = start_w + crop_size
-
-    cropped_image = image[0][start_h:end_h, start_w:end_w, :]
-    cropped_dem = dem[0][start_h:end_h, start_w:end_w, :]
-
-    return (255 * cropped_image).astype(np.uint8), 500*cropped_dem.mean(-1)
-
-def simplify_mesh(mesh, target_face_count):
-    """Simplifies a mesh using quadric decimation."""
-    simplified_mesh = mesh.simplify_quadric_decimation(target_face_count)
-    return simplified_mesh
-
-def create_3d_mesh(rgb, elevation):
-    """Creates a 3D mesh from RGB and elevation data."""
-    x, y = np.meshgrid(np.arange(elevation.shape[1]), np.arange(elevation.shape[0]))
-    points = np.stack([x.flatten(), y.flatten()], axis=-1)
-    tri = Delaunay(points)
-
-    vertices = np.stack([x.flatten(), y.flatten(), elevation.flatten()], axis=-1)
-    faces = tri.simplices
-
-    mesh = trimesh.Trimesh(vertices=vertices, faces=faces, vertex_colors=rgb.reshape(-1, 3))
-
-    #mesh = simplify_mesh(mesh, target_face_count=100)
-    return mesh
-
-def generate_and_display(prompt, num_inference_steps, guidance_scale, seed, crop_size, prefix):
-    """Generates terrain and displays it as a 3D model."""
-    rgb, elevation = generate_terrain(prompt, num_inference_steps, guidance_scale, seed, crop_size, prefix)
-    mesh = create_3d_mesh(rgb, elevation)
-
-    with tempfile.NamedTemporaryFile(suffix=".obj", delete=False) as temp_file:
-        mesh.export(temp_file.name)
-        file_path = temp_file.name
-
-    return file_path

src/utils.py

@@ -3,13 +3,14 @@ import trimesh
 import tempfile
 import torch
 from scipy.spatial import Delaunay
+from sklearn.cluster import KMeans
 from .build_pipe import *
 import spaces
 
 pipe = build_pipe()
 
 @spaces.GPU
-def generate_terrain(prompt, num_inference_steps, guidance_scale, seed, crop_size, prefix):
+def generate_terrain(prompt, num_inference_steps, guidance_scale, seed, prefix, crop_size=None):
     """Generates terrain data (RGB and elevation) from a text prompt."""
     if prefix and not prefix.endswith(' '):
         prefix += ' '  # Ensure prefix ends with a space
@@ -18,44 +19,96 @@ def generate_terrain(prompt, num_inference_steps, guidance_scale, seed, crop_siz
     generator = torch.Generator("cuda").manual_seed(seed)
     image, dem = pipe(full_prompt, num_inference_steps=num_inference_steps, guidance_scale=guidance_scale, generator=generator)
 
-    # Center crop the image and dem
-    h, w, c = image[0].shape
-    start_h = (h - crop_size) // 2
-    start_w = (w - crop_size) // 2
-    end_h = start_h + crop_size
-    end_w = start_w + crop_size
+    if crop_size is not None:
+        # Center crop the image and dem
+        h, w, c = image[0].shape
+        start_h = (h - crop_size) // 2
+        start_w = (w - crop_size) // 2
+        end_h = start_h + crop_size
+        end_w = start_w + crop_size
+    
+        cropped_image = image[0][start_h:end_h, start_w:end_w, :]
+        cropped_dem = dem[0][start_h:end_h, start_w:end_w, :]
+    else:
+        cropped_image = image[0]
+        cropped_dem = dem[0]
 
-    cropped_image = image[0][start_h:end_h, start_w:end_w, :]
-    cropped_dem = dem[0][start_h:end_h, start_w:end_w, :]
+    return (255 * cropped_image).astype(np.uint8), cropped_dem.mean(-1)
 
-    return (255 * cropped_image).astype(np.uint8), 500*cropped_dem.mean(-1)
+def create_3d_mesh(rgb, elevation, n_clusters=1000):
+    """Creates a 3D mesh from RGB and elevation data.
+    If n_clusters is 0, generates the full mesh.
+    Otherwise, generates a simplified mesh using KMeans clustering with distinct colors.
+    """
+    rows, cols = elevation.shape
+    x, y = np.meshgrid(np.arange(cols), np.arange(rows))
+    points_2d = np.stack([x.flatten(), y.flatten()], axis=-1)
+    elevation_flat = elevation.flatten()
+    points_3d = np.column_stack([points_2d, elevation_flat])
+    original_colors = rgb.reshape(-1, 3)
 
-def simplify_mesh(mesh, target_face_count):
-    """Simplifies a mesh using quadric decimation."""
-    simplified_mesh = mesh.simplify_quadric_decimation(target_face_count)
-    return simplified_mesh
+    if n_clusters <= 0:
+        # Generate full mesh without clustering
+        vertices = points_3d
+        try:
+            tri = Delaunay(points_2d)
+            faces = tri.simplices
+            mesh = trimesh.Trimesh(vertices=vertices, faces=faces, vertex_colors=original_colors)
+            return mesh
+        except Exception as e:
+            print(f"Error during Delaunay triangulation (full mesh): {e}")
+            return None
+    else:
+        n_clusters = min(n_clusters, len(elevation_flat))
+        # Apply KMeans clustering for simplification
+        kmeans = KMeans(n_clusters=n_clusters, random_state=0, n_init='auto')
+        kmeans.fit(points_3d)
+        cluster_centers = kmeans.cluster_centers_
+        cluster_labels = kmeans.labels_
 
-def create_3d_mesh(rgb, elevation):
-    """Creates a 3D mesh from RGB and elevation data."""
-    x, y = np.meshgrid(np.arange(elevation.shape[1]), np.arange(elevation.shape[0]))
-    points = np.stack([x.flatten(), y.flatten()], axis=-1)
-    tri = Delaunay(points)
+        # Use the cluster centers as the simplified vertices
+        simplified_vertices = cluster_centers
 
-    vertices = np.stack([x.flatten(), y.flatten(), elevation.flatten()], axis=-1)
-    faces = tri.simplices
+        # Perform Delaunay triangulation on the X and Y coordinates of the cluster centers
+        simplified_points_2d = simplified_vertices[:, :2]
+        try:
+            tri = Delaunay(simplified_points_2d)
+            faces = tri.simplices
+            # Ensure the number of vertices in faces does not exceed the number of simplified vertices
+            valid_faces = faces[np.all(faces < len(simplified_vertices), axis=1)]
+        except Exception as e:
+            print(f"Error during Delaunay triangulation (clustered mesh): {e}")
+            return None
 
-    mesh = trimesh.Trimesh(vertices=vertices, faces=faces, vertex_colors=rgb.reshape(-1, 3))
+        # Assign a distinct color to each cluster
+        unique_labels = np.unique(cluster_labels)
+        cluster_colors = {}
+        for label in unique_labels:
+            cluster_indices = np.where(cluster_labels == label)[0]
+            if len(cluster_indices) > 0:
+                avg_color = np.mean(original_colors[cluster_indices], axis=0).astype(np.uint8)
+                cluster_colors[label] = avg_color
+            else:
+                cluster_colors[label] = np.array([255, 0, 0], dtype=np.uint8) # Red
 
-    #mesh = simplify_mesh(mesh, target_face_count=100)
-    return mesh
+        vertex_colors = np.array([cluster_colors[i] for i in range(n_clusters)])
 
-def generate_and_display(prompt, num_inference_steps, guidance_scale, seed, crop_size, prefix):
-    """Generates terrain and displays it as a 3D model."""
-    rgb, elevation = generate_terrain(prompt, num_inference_steps, guidance_scale, seed, crop_size, prefix)
-    mesh = create_3d_mesh(rgb, elevation)
+        # Create the trimesh object
+        mesh = trimesh.Trimesh(vertices=simplified_vertices, faces=valid_faces, vertex_colors=vertex_colors)
+        return mesh
+
+def generate_3d_view_output(prompt, num_inference_steps, guidance_scale, seed, crop_size, vertex_count, prefix):
+    rgb, elevation = generate_terrain(prompt, num_inference_steps, guidance_scale, seed, prefix, crop_size)
+    
+    mesh = create_3d_mesh(rgb, 500*elevation, n_clusters=vertex_count)
 
     with tempfile.NamedTemporaryFile(suffix=".obj", delete=False) as temp_file:
         mesh.export(temp_file.name)
         file_path = temp_file.name
 
     return file_path
+
+def generate_2d_view_output(prompt, num_inference_steps, guidance_scale, seed, prefix):
+    rgb, elevation = generate_terrain(prompt, num_inference_steps, guidance_scale, seed, prefix)
+
+    return rgb, elevation