Update app.py

app.py

@@ -1,154 +1,104 @@
-import gradio as gr
+import os
+import tempfile
+import torch
 import numpy as np
-import random
-
-# import spaces #[uncomment to use ZeroGPU]
+import gradio as gr
+from PIL import Image
+import cv2
 from diffusers import DiffusionPipeline
-import torch
+from script import SatelliteModelGenerator
 
+# Initialize models and device
 device = "cuda" if torch.cuda.is_available() else "cpu"
-model_repo_id = "stabilityai/sdxl-turbo"  # Replace to the model you would like to use
-
-if torch.cuda.is_available():
-    torch_dtype = torch.float16
-else:
-    torch_dtype = torch.float32
-
-pipe = DiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype)
-pipe = pipe.to(device)
-
-MAX_SEED = np.iinfo(np.int32).max
-MAX_IMAGE_SIZE = 1024
-
-
-# @spaces.GPU #[uncomment to use ZeroGPU]
-def infer(
-    prompt,
-    negative_prompt,
-    seed,
-    randomize_seed,
-    width,
-    height,
-    guidance_scale,
-    num_inference_steps,
-    progress=gr.Progress(track_tqdm=True),
-):
-    if randomize_seed:
-        seed = random.randint(0, MAX_SEED)
-
-    generator = torch.Generator().manual_seed(seed)
-
-    image = pipe(
-        prompt=prompt,
-        negative_prompt=negative_prompt,
-        guidance_scale=guidance_scale,
-        num_inference_steps=num_inference_steps,
-        width=width,
-        height=height,
-        generator=generator,
-    ).images[0]
-
-    return image, seed
-
-
-examples = [
-    "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
-    "An astronaut riding a green horse",
-    "A delicious ceviche cheesecake slice",
-]
-
-css = """
-#col-container {
-    margin: 0 auto;
-    max-width: 640px;
-}
-"""
-
-with gr.Blocks(css=css) as demo:
-    with gr.Column(elem_id="col-container"):
-        gr.Markdown(" # Text-to-Image Gradio Template")
-
-        with gr.Row():
-            prompt = gr.Text(
-                label="Prompt",
-                show_label=False,
-                max_lines=1,
-                placeholder="Enter your prompt",
-                container=False,
-            )
-
-            run_button = gr.Button("Run", scale=0, variant="primary")
-
-        result = gr.Image(label="Result", show_label=False)
-
-        with gr.Accordion("Advanced Settings", open=False):
-            negative_prompt = gr.Text(
-                label="Negative prompt",
-                max_lines=1,
-                placeholder="Enter a negative prompt",
-                visible=False,
-            )
-
-            seed = gr.Slider(
-                label="Seed",
-                minimum=0,
-                maximum=MAX_SEED,
-                step=1,
-                value=0,
-            )
-
-            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
-
-            with gr.Row():
-                width = gr.Slider(
-                    label="Width",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,  # Replace with defaults that work for your model
-                )
-
-                height = gr.Slider(
-                    label="Height",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,  # Replace with defaults that work for your model
-                )
-
-            with gr.Row():
-                guidance_scale = gr.Slider(
-                    label="Guidance scale",
-                    minimum=0.0,
-                    maximum=10.0,
-                    step=0.1,
-                    value=0.0,  # Replace with defaults that work for your model
-                )
-
-                num_inference_steps = gr.Slider(
-                    label="Number of inference steps",
-                    minimum=1,
-                    maximum=50,
-                    step=1,
-                    value=2,  # Replace with defaults that work for your model
-                )
-
-        gr.Examples(examples=examples, inputs=[prompt])
-    gr.on(
-        triggers=[run_button.click, prompt.submit],
-        fn=infer,
-        inputs=[
-            prompt,
-            negative_prompt,
-            seed,
-            randomize_seed,
-            width,
-            height,
-            guidance_scale,
-            num_inference_steps,
-        ],
-        outputs=[result, seed],
+dtype = torch.bfloat16
+
+# Initialize FLUX model for satellite imagery
+flux_pipe = DiffusionPipeline.from_pretrained(
+    "jbilcke-hf/flux-satellite",
+    torch_dtype=dtype
+).to(device)
+
+def generate_and_process_map(prompt: str) -> str | None:
+    """Generate satellite image from prompt and convert to 3D model."""
+    try:
+        # Set dimensions
+        width = height = 1024
+        
+        # Generate random seed
+        seed = np.random.randint(0, np.iinfo(np.int32).max)
+        
+        # Set random seeds
+        torch.manual_seed(seed)
+        np.random.seed(seed)
+        
+        # Generate satellite image using FLUX
+        generator = torch.Generator(device=device).manual_seed(seed)
+        generated_image = flux_pipe(
+            prompt=prompt,
+            width=width,
+            height=height,
+            num_inference_steps=30,
+            generator=generator,
+            guidance_scale=7.5
+        ).images[0]
+        
+        # Convert PIL Image to OpenCV format
+        cv_image = cv2.cvtColor(np.array(generated_image), cv2.COLOR_RGB2BGR)
+        
+        # Initialize SatelliteModelGenerator
+        generator = SatelliteModelGenerator(building_height=0.09)
+        
+        # Process image
+        print("Segmenting image...")
+        segmented_img = generator.segment_image(cv_image, window_size=5)
+        
+        print("Estimating heights...")
+        height_map = generator.estimate_heights(cv_image, segmented_img)
+        
+        # Generate mesh
+        print("Generating mesh...")
+        mesh = generator.generate_mesh(height_map, cv_image, add_walls=True)
+        
+        # Export to GLB
+        temp_dir = tempfile.mkdtemp()
+        output_path = os.path.join(temp_dir, 'output.glb')
+        mesh.export(output_path)
+        
+        return output_path
+        
+    except Exception as e:
+        print(f"Error during generation: {str(e)}")
+        import traceback
+        traceback.print_exc()
+        return None
+
+# Create Gradio interface
+with gr.Blocks() as demo:
+    gr.Markdown("# Text to Map")
+    gr.Markdown("Generate 3D maps from text descriptions using FLUX and mesh generation.")
+    
+    with gr.Row():
+        prompt_input = gr.Text(
+            label="Enter your prompt",
+            placeholder="eg. satellite view of downtown Manhattan"
+        )
+    
+    with gr.Row():
+        generate_btn = gr.Button("Generate", variant="primary")
+    
+    with gr.Row():
+        model_output = gr.Model3D(
+            label="Generated 3D Map",
+            clear_color=[0.0, 0.0, 0.0, 0.0],
+        )
+    
+    # Event handler
+    generate_btn.click(
+        fn=generate_and_process_map,
+        inputs=[prompt_input],
+        outputs=[model_output],
+        api_name="generate"
     )
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.queue().launch()