fix

app.py

@@ -192,6 +192,5 @@ iface = gr.Interface(fn=sample,
                      inputs=gr.inputs.Textbox(label='enter text'), 
                      outputs=gr.outputs.Image(type="pil", label="..."),
                      title=title,
-                     description=description,
-                     enable_queue=True)
-iface.launch(debug=True)
+                     description=description)
+iface.launch(debug=True,enable_queue=True)

server.py

@@ -172,4 +172,4 @@ def sample(prompt):
 def to_base64(pil_image):
     buffered = BytesIO()
     pil_image.save(buffered, format="JPEG")
-    return base64.b64encode(buffered.getvalue())
+    return base64.b64encode(buffered.getvalue())

server.py~

@@ -0,0 +1,246 @@
+import base64
+from io import BytesIO
+from fastapi import FastAPI
+<<<<<<< HEAD
+
+from PIL import Image
+import torch as th
+
+=======
+from PIL import Image
+import torch as th
+>>>>>>> 8c239b8a9cdaf13e28c145e788b984c129547a37
+from glide_text2im.download import load_checkpoint
+from glide_text2im.model_creation import (
+    create_model_and_diffusion,
+    model_and_diffusion_defaults,
+    model_and_diffusion_defaults_upsampler
+)
+<<<<<<< HEAD
+
+print("Loading models...")
+app = FastAPI()
+
+# This notebook supports both CPU and GPU.
+# On CPU, generating one sample may take on the order of 20 minutes.
+# On a GPU, it should be under a minute.
+
+has_cuda = th.cuda.is_available()
+device = th.device('cpu' if not has_cuda else 'cuda')
+
+=======
+print("Loading models...")
+app = FastAPI()
+# This notebook supports both CPU and GPU.
+# On CPU, generating one sample may take on the order of 20 minutes.
+# On a GPU, it should be under a minute.
+has_cuda = th.cuda.is_available()
+device = th.device('cpu' if not has_cuda else 'cuda')
+>>>>>>> 8c239b8a9cdaf13e28c145e788b984c129547a37
+# Create base model.
+options = model_and_diffusion_defaults()
+options['use_fp16'] = has_cuda
+options['timestep_respacing'] = '100' # use 100 diffusion steps for fast sampling
+model, diffusion = create_model_and_diffusion(**options)
+model.eval()
+if has_cuda:
+    model.convert_to_fp16()
+model.to(device)
+model.load_state_dict(load_checkpoint('base', device))
+print('total base parameters', sum(x.numel() for x in model.parameters()))
+<<<<<<< HEAD
+
+=======
+>>>>>>> 8c239b8a9cdaf13e28c145e788b984c129547a37
+# Create upsampler model.
+options_up = model_and_diffusion_defaults_upsampler()
+options_up['use_fp16'] = has_cuda
+options_up['timestep_respacing'] = 'fast27' # use 27 diffusion steps for very fast sampling
+model_up, diffusion_up = create_model_and_diffusion(**options_up)
+model_up.eval()
+if has_cuda:
+    model_up.convert_to_fp16()
+model_up.to(device)
+model_up.load_state_dict(load_checkpoint('upsample', device))
+print('total upsampler parameters', sum(x.numel() for x in model_up.parameters()))
+<<<<<<< HEAD
+
+
+=======
+>>>>>>> 8c239b8a9cdaf13e28c145e788b984c129547a37
+def get_images(batch: th.Tensor):
+    """ Display a batch of images inline. """
+    scaled = ((batch + 1)*127.5).round().clamp(0,255).to(th.uint8).cpu()
+    reshaped = scaled.permute(2, 0, 3, 1).reshape([batch.shape[2], -1, 3])
+    Image.fromarray(reshaped.numpy())
+<<<<<<< HEAD
+
+
+# Create a classifier-free guidance sampling function
+guidance_scale = 3.0
+
+=======
+# Create a classifier-free guidance sampling function
+guidance_scale = 3.0
+>>>>>>> 8c239b8a9cdaf13e28c145e788b984c129547a37
+def model_fn(x_t, ts, **kwargs):
+    half = x_t[: len(x_t) // 2]
+    combined = th.cat([half, half], dim=0)
+    model_out = model(combined, ts, **kwargs)
+    eps, rest = model_out[:, :3], model_out[:, 3:]
+    cond_eps, uncond_eps = th.split(eps, len(eps) // 2, dim=0)
+    half_eps = uncond_eps + guidance_scale * (cond_eps - uncond_eps)
+    eps = th.cat([half_eps, half_eps], dim=0)
+    return th.cat([eps, rest], dim=1)
+<<<<<<< HEAD
+
+
+@app.get("/")
+def read_root():
+    return {"glide!"}
+
+=======
+@app.get("/")
+def read_root():
+    return {"glide!"}
+>>>>>>> 8c239b8a9cdaf13e28c145e788b984c129547a37
+@app.get("/{generate}")
+def sample(prompt):
+    # Sampling parameters
+    batch_size = 1
+<<<<<<< HEAD
+
+    # Tune this parameter to control the sharpness of 256x256 images.
+    # A value of 1.0 is sharper, but sometimes results in grainy artifacts.
+    upsample_temp = 0.997
+
+    ##############################
+    # Sample from the base model #
+    ##############################
+
+=======
+    # Tune this parameter to control the sharpness of 256x256 images.
+    # A value of 1.0 is sharper, but sometimes results in grainy artifacts.
+    upsample_temp = 0.997
+    ##############################
+    # Sample from the base model #
+    ##############################
+>>>>>>> 8c239b8a9cdaf13e28c145e788b984c129547a37
+    # Create the text tokens to feed to the model.
+    tokens = model.tokenizer.encode(prompt)
+    tokens, mask = model.tokenizer.padded_tokens_and_mask(
+        tokens, options['text_ctx']
+    )
+<<<<<<< HEAD
+
+=======
+>>>>>>> 8c239b8a9cdaf13e28c145e788b984c129547a37
+    # Create the classifier-free guidance tokens (empty)
+    full_batch_size = batch_size * 2
+    uncond_tokens, uncond_mask = model.tokenizer.padded_tokens_and_mask(
+        [], options['text_ctx']
+    )
+<<<<<<< HEAD
+
+=======
+>>>>>>> 8c239b8a9cdaf13e28c145e788b984c129547a37
+    # Pack the tokens together into model kwargs.
+    model_kwargs = dict(
+        tokens=th.tensor(
+            [tokens] * batch_size + [uncond_tokens] * batch_size, device=device
+        ),
+        mask=th.tensor(
+            [mask] * batch_size + [uncond_mask] * batch_size,
+            dtype=th.bool,
+            device=device,
+        ),
+    )
+<<<<<<< HEAD
+
+=======
+>>>>>>> 8c239b8a9cdaf13e28c145e788b984c129547a37
+    # Sample from the base model.
+    model.del_cache()
+    samples = diffusion.p_sample_loop(
+        model_fn,
+        (full_batch_size, 3, options["image_size"], options["image_size"]),
+        device=device,
+        clip_denoised=True,
+        progress=True,
+        model_kwargs=model_kwargs,
+        cond_fn=None,
+    )[:batch_size]
+    model.del_cache()
+<<<<<<< HEAD
+
+
+    ##############################
+    # Upsample the 64x64 samples #
+    ##############################
+
+=======
+    ##############################
+    # Upsample the 64x64 samples #
+    ##############################
+>>>>>>> 8c239b8a9cdaf13e28c145e788b984c129547a37
+    tokens = model_up.tokenizer.encode(prompt)
+    tokens, mask = model_up.tokenizer.padded_tokens_and_mask(
+        tokens, options_up['text_ctx']
+    )
+<<<<<<< HEAD
+
+=======
+>>>>>>> 8c239b8a9cdaf13e28c145e788b984c129547a37
+    # Create the model conditioning dict.
+    model_kwargs = dict(
+        # Low-res image to upsample.
+        low_res=((samples+1)*127.5).round()/127.5 - 1,
+<<<<<<< HEAD
+
+=======
+>>>>>>> 8c239b8a9cdaf13e28c145e788b984c129547a37
+        # Text tokens
+        tokens=th.tensor(
+            [tokens] * batch_size, device=device
+        ),
+        mask=th.tensor(
+            [mask] * batch_size,
+            dtype=th.bool,
+            device=device,
+        ),
+    )
+<<<<<<< HEAD
+
+=======
+>>>>>>> 8c239b8a9cdaf13e28c145e788b984c129547a37
+    # Sample from the base model.
+    model_up.del_cache()
+    up_shape = (batch_size, 3, options_up["image_size"], options_up["image_size"])
+    up_samples = diffusion_up.ddim_sample_loop(
+        model_up,
+        up_shape,
+        noise=th.randn(up_shape, device=device) * upsample_temp,
+        device=device,
+        clip_denoised=True,
+        progress=True,
+        model_kwargs=model_kwargs,
+        cond_fn=None,
+    )[:batch_size]
+    model_up.del_cache()
+<<<<<<< HEAD
+
+=======
+>>>>>>> 8c239b8a9cdaf13e28c145e788b984c129547a37
+    # Show the output
+    image = get_images(up_samples)
+    image = to_base64(image)
+    return {"image": image}
+<<<<<<< HEAD
+
+
+=======
+>>>>>>> 8c239b8a9cdaf13e28c145e788b984c129547a37
+def to_base64(pil_image):
+    buffered = BytesIO()
+    pil_image.save(buffered, format="JPEG")
+    return base64.b64encode(buffered.getvalue())

setup.py

@@ -1,5 +1,4 @@
 from setuptools import setup
-
 setup(
     name="glide-text2im",
     packages=["glide_text2im"],