Update app.py

app.py

@@ -176,6 +176,7 @@ def extract_gaussian(state: dict, req: gr.Request) -> Tuple[str, str]:
     torch.cuda.empty_cache()
     return gaussian_path, gaussian_path
 
+# Gradio Interface
 # Gradio Interface
 # Gradio Interface
 with gr.Blocks() as demo:
@@ -183,10 +184,8 @@ with gr.Blocks() as demo:
     ## Game Asset Generation to 3D with FLUX and TRELLIS
     * Enter a prompt to generate a game asset image, then convert it to 3D
     * If you find the generated 3D asset satisfactory, click "Extract GLB" to extract the GLB file and download it.
-    * [TRELLIS Model](https://huggingface.co/JeffreyXiang/TRELLIS-image-large) [Trellis Github](https://github.com/microsoft/TRELLIS) [Flux-Dev](https://huggingface.co/black-forest-labs/FLUX.1-dev) 
-    * [Flux Game Assets LoRA](https://huggingface.co/gokaygokay/Flux-Game-Assets-LoRA-v2) [Hyper FLUX 8Steps LoRA](https://huggingface.co/ByteDance/Hyper-SD) [safetensors to GGUF for Flux](https://github.com/ruSauron/to-gguf-bat) [Thanks to John6666](https://huggingface.co/John6666)
     """)
-    
+
     with gr.Row():
         with gr.Column():
             # Flux image generation inputs
@@ -199,7 +198,7 @@ with gr.Blocks() as demo:
                     height = gr.Slider(512, 1024, label="Height", value=1024, step=16)
                 with gr.Row():
                     guidance_scale = gr.Slider(0.0, 10.0, label="Guidance Scale", value=3.5, step=0.1)
-            
+
             # Botones separados
             generate_image_btn = gr.Button("Generar Imagen")
             generate_video_btn = gr.Button("Generar Video", interactive=False)
@@ -207,17 +206,28 @@ with gr.Blocks() as demo:
         with gr.Column():
             generated_image = gr.Image(label="Generated Asset", type="pil")
             video_output = gr.Video(label="Generated 3D Asset", autoplay=True, loop=True)
-        
+
         model_output = LitModel3D(label="Extracted GLB/Gaussian", exposure=8.0, height=400)
-    
+
     with gr.Row():
         extract_glb_btn = gr.Button("Extract GLB", interactive=False)
         extract_gs_btn = gr.Button("Extract Gaussian", interactive=False)
-    
+
     with gr.Row():
         download_glb = gr.DownloadButton(label="Download GLB", interactive=False)
         download_gs = gr.DownloadButton(label="Download Gaussian", interactive=False)
-    
+
+    # Variables adicionales para la generación 3D
+    with gr.Accordion("3D Generation Settings", open=False):
+        gr.Markdown("Stage 1: Sparse Structure Generation")
+        with gr.Row():
+            ss_guidance_strength = gr.Slider(0.0, 10.0, label="Guidance Strength", value=7.5, step=0.1)
+            ss_sampling_steps = gr.Slider(1, 50, label="Sampling Steps", value=12, step=1)
+        gr.Markdown("Stage 2: Structured Latent Generation")
+        with gr.Row():
+            slat_guidance_strength = gr.Slider(0.0, 10.0, label="Guidance Strength", value=3.0, step=0.1)
+            slat_sampling_steps = gr.Slider(1, 50, label="Sampling Steps", value=12, step=1)
+
     # Estado para almacenar la imagen generada temporalmente
     temp_image_state = gr.State()
     output_buf = gr.State()
@@ -239,7 +249,14 @@ with gr.Blocks() as demo:
     # Generar video
     generate_video_btn.click(
         image_to_3d,
-        inputs=[temp_image_state, seed, ss_guidance_strength, ss_sampling_steps, slat_guidance_strength, slat_sampling_steps],
+        inputs=[
+            temp_image_state, 
+            seed, 
+            ss_guidance_strength, 
+            ss_sampling_steps, 
+            slat_guidance_strength, 
+            slat_sampling_steps
+        ],
         outputs=[output_buf, video_output],
     ).then(
         lambda: tuple([gr.Button(interactive=True), gr.Button(interactive=True)]),
@@ -265,7 +282,6 @@ with gr.Blocks() as demo:
         lambda: gr.Button(interactive=True),
         outputs=[download_gs],
     )
-
 # Initialize both pipelines
 if __name__ == "__main__":
     from diffusers import FluxTransformer2DModel, FluxPipeline, BitsAndBytesConfig, GGUFQuantizationConfig