Interface cleaning + sanity check for 4 conditions

app.py

@@ -10,16 +10,18 @@ with gr.Blocks(theme=theme) as demo:
         gr.HTML('<img src="https://huggingface.co/spaces/mikonvergence/COP-GEN-Beta/resolve/main/logos/COP-GEN-logo.png" style="max-width: 300px;">')
         gr.Markdown("# 🔵 COP-GEN-Beta: Unified Generative Modelling of COPernicus Imagery Thumbnails")
         gr.Markdown("### Miguel Espinosa, Valerio Marsocci, Yuru Jia, Elliot J. Crowley, Mikolaj Czerkawski")
-        gr.Markdown('[[Website](https://miquel-espinosa.github.io/cop-gen-beta/)] [GitHub](https://github.com/miquel-espinosa/COP-GEN-Beta)] [[Model](https://huggingface.co/mespinosami/COP-GEN-Beta) [[Dataset](https://huggingface.co/Major-TOM)]')
-        gr.Markdown('> ## ⚠️ NOTE: This is a prototype Beta model of COP-GEN. It is based on image thumbnails of [[Major TOM](https://huggingface.co/Major-TOM)] and does not yet support raw source data. The hillshade visualisation is used for elevation. The full model COP-GEN is coming soon.')
+        gr.HTML('<a href="https://github.com/miquel-espinosa/COP-GEN-Beta" class="text-decoration-none site-link"><img alt="GitHub Repo stars" src="https://img.shields.io/github/stars/miquel-espinosa/COP-GEN-Beta"></a>')
+        #gr.Markdown('[[Website](https://miquel-espinosa.github.io/cop-gen-beta/)] [GitHub](https://github.com/miquel-espinosa/COP-GEN-Beta)] [[Model](https://huggingface.co/mespinosami/COP-GEN-Beta) [[Dataset](https://huggingface.co/Major-TOM)]')
+        gr.Markdown('> ## ⚠️ NOTE: This is a prototype Beta model of COP-GEN. It is based on image thumbnails of [Major TOM](https://huggingface.co/Major-TOM) and does not yet support raw source data. The hillshade visualisation is used for elevation. The full model COP-GEN is coming soon.')
     
     with gr.Column(elem_classes="Main app"):
 
         with gr.Accordion("Instructions", open=False) as abstract:
-            gr.Markdown("1. **Generate**: Click the `🏭 Generate` button to synthesize the output. The outputs will be shown below.")
-            gr.Markdown("2. **Define input**: If you want to condition your generation, you can upload your thumbnails manually or you can `🔄 Load` a random sample from Major TOM by clicking the button.")
-            gr.Markdown("3. **Select conditions**: Each input image can be used as a **conditioning** by selecting the `Active` checkbox. If no checkbox is selected, then you will still executy **unconditional generation**.")
-            gr.Markdown("4. **Additional Options**: You can control the number of generation steps (higher number might produce better quality, but will take more time), or set a fixed seed (for reproducible results).")
+            gr.Markdown("1. **Generate**: Click the `🏭 Generate` button to synthesize the output **without any conditions**. The outputs will be shown below - and that's it, you've generated your first sample! 🧑‍🎨️"+
+                        "<br/>2. **Optionally, define input**:  If you want to condition your generation, you can upload your thumbnails manually or you can `🔄 Load` a random sample from Major TOM by clicking the button."+
+                        "<br/>3. **Select conditions**: Each input image can be used as a **conditioning** when it's loaded into the inputs panel. The modalities you wish to generate should have no content in the input panel (you can empty each element by clicking `x` in the top right corner of the image)."+
+                        "<br/>4. **Additional Options**: You can control the number of generation steps (higher number might produce better quality, but will take more time), or set a fixed seed (for reproducible results)."+
+                       "<br/>5. You can also reuse any of the generated samples as input to the model by clicking `♻️ Reuse`")
         
         with gr.Column():
             generate_button = gr.Button("🏭 Generate", variant="primary")
@@ -32,14 +34,14 @@ with gr.Blocks(theme=theme) as demo:
                 dem_output = gr.Image(label="DEM (Elevation)", interactive=False)
 
             with gr.Row():
-                s2l1c_reuse_button = gr.Button("Reuse S2 L1C as input ⤵️", variant="primary")
-                s2l2a_reuse_button = gr.Button("Reuse S2 L2A as input ⤵️", variant="primary")
-                s1rtc_reuse_button = gr.Button("Reuse S1 RTC as input ⤵️", variant="primary")
-                dem_reuse_button = gr.Button("Reuse DEM as input ⤵️", variant="primary")
+                s2l1c_reuse_button = gr.Button("♻️ Reuse S2 L1C as input ⤵️", variant="primary")
+                s2l2a_reuse_button = gr.Button("♻️ Reuse S2 L2A as input ⤵️", variant="primary")
+                s1rtc_reuse_button = gr.Button("♻️ Reuse S1 RTC as input ⤵️", variant="primary")
+                dem_reuse_button = gr.Button("♻️ Reuse DEM as input ⤵️", variant="primary")
 
             gr.Markdown("---")
             with gr.Row():
-                gr.Markdown("## Input Conditions (Optional)")
+                gr.Markdown("## (Optional) Input Conditions")
                 load_button = gr.Button("🔄 Load a random sample from Major TOM 🗺", variant="secondary")
             with gr.Row():
                 s2l1c_input = gr.Image(label="S2 L1C (Optical - Top of Atmosphere)", interactive=True)
@@ -55,6 +57,7 @@ with gr.Blocks(theme=theme) as demo:
                 seed_checkbox = gr.Checkbox(value=True, label="Random")
         
         with gr.Accordion("Abstract", open=False) as abstract:
+            gr.HTML('<a href="https://arxiv.org/abs/2504.08548/" class="text-decoration-none site-link"><img alt="Arxiv Link" src="https://img.shields.io/badge/Open_Access-arxiv:2504.08548-b31b1b"></a>')
             gr.Markdown("In remote sensing, multi-modal data from various sensors capturing the same scene offers rich opportunities, but learning a unified representation across these modalities remains a significant challenge. Traditional methods have often been limited to single or dual-modality approaches. In this paper, we introduce COP-GEN-Beta, a generative diffusion model trained on optical, radar, and elevation data from the Major TOM dataset. What sets COP-GEN-Beta apart is its ability to map any subset of modalities to any other, enabling zero-shot modality translation after training. This is achieved through a sequence-based diffusion transformer, where each modality is controlled by its own timestep embedding. We extensively evaluate COP-GEN-Beta on thumbnail images from the Major TOM dataset, demonstrating its effectiveness in generating high-quality samples. Qualitative and quantitative evaluations validate the model's performance, highlighting its potential as a powerful pre-trained model for future remote sensing tasks.")
             
         load_button.click(

src/backend.py

@@ -1,6 +1,7 @@
 import os
 import torch
 import spaces
+import gradio as gr
 import numpy as np
 from PIL import Image
 import ml_collections
@@ -237,6 +238,10 @@ def generate_output(s2l1c_input, s2l2a_input, s1rtc_input, dem_input, num_infere
     s1rtc_active = s1rtc_input is not None
     dem_active = dem_input is not None
 
+    if s2l2a_active and s2l1c_active and s1rtc_active and dem_active:
+        gr.Warning("You need to remove some of the inputs that you would like to generate. If all modalities are known, there is nothing to generate.")
+        return s2l2a_input, s2l1c_input, s1rtc_input, dem_input
+
     images=[]
     condition_modalities=[]
     if s2l2a_active: