Update app.py

app.py

@@ -130,7 +130,7 @@ def preprocess_image(image: Image.Image,
                     num_steps: int = 25,
                     guidance_scale: float = 5,
                     controlnet_conditioning_scale: float = 1.0,
-                    do_preprocess: bool = True) -> Image.Image:
+                    ) -> Image.Image:
     """
     Preprocess the input image.
 
@@ -141,35 +141,32 @@ def preprocess_image(image: Image.Image,
         Image.Image: The preprocessed image.
     """
         
-    if do_preprocess:
-        width, height  = image['composite'].size
-        ratio = np.sqrt(1024. * 1024. / (width * height))
-        new_width, new_height = int(width * ratio), int(height * ratio)
-        image = image['composite'].resize((new_width, new_height))
+    width, height  = image['composite'].size
+    ratio = np.sqrt(1024. * 1024. / (width * height))
+    new_width, new_height = int(width * ratio), int(height * ratio)
+    image = image['composite'].resize((new_width, new_height))
+
+    print("image:",type(image))
+
+    prompt, negative_prompt = apply_style(style_name, prompt, negative_prompt)
     
-        print("image:",type(image))
+    print("params:", prompt, negative_prompt, style_name, num_steps, guidance_scale, controlnet_conditioning_scale)
+    image = pipe_control(
+        prompt=prompt,
+        negative_prompt=negative_prompt,
+        image=image,
+        num_inference_steps=num_steps,
+        controlnet_conditioning_scale=controlnet_conditioning_scale,
+        guidance_scale=guidance_scale,
+        width=new_width,
+        height=new_height).images[0]
     
-        prompt, negative_prompt = apply_style(style_name, prompt, negative_prompt)
-        
-        print("params:", prompt, negative_prompt, style_name, num_steps, guidance_scale, controlnet_conditioning_scale)
-        image = pipe_control(
-            prompt=prompt,
-            negative_prompt=negative_prompt,
-            image=image,
-            num_inference_steps=num_steps,
-            controlnet_conditioning_scale=controlnet_conditioning_scale,
-            guidance_scale=guidance_scale,
-            width=new_width,
-            height=new_height).images[0]
         
-            
-        processed_image = pipeline.preprocess_image(image)
-        return processed_image, False
-    else:
-        return image, False
+    processed_image = pipeline.preprocess_image(image)
+    return processed_image
 
 
-def preprocess_images(images: List[Tuple[Image.Image, str]], do_preprocess = True) -> List[Image.Image]:
+def preprocess_images(images: List[Tuple[Image.Image, str]]) -> List[Image.Image]:
     """
     Preprocess a list of input images.
     
@@ -394,12 +391,13 @@ with gr.Blocks(delete_cache=(600, 600), js=js_func) as demo:
                 with gr.Tab(label="Single Image", id=0) as single_image_input_tab:
                     #image_prompt = gr.Image(label="Image Prompt", format="png", image_mode="RGBA", type="pil", height=300)
                     image_prompt = gr.ImageEditor(type="pil", image_mode="L", crop_size=(512, 512))
-                    sketch_btn = gr.Button("process sketch")
-                    with gr.Column():
+                    with gr.Row():
+                        sketch_btn = gr.Button("process sketch")
+                        generate_btn = gr.Button("Generate 3D")
+                    with gr.Row():
                         prompt = gr.Textbox(label="Prompt")
-                        with gr.Row():
-                            style = gr.Dropdown(label="Style", choices=STYLE_NAMES, value=DEFAULT_STYLE_NAME)
-                            negative_prompt = gr.Textbox(label="Negative prompt")
+                        style = gr.Dropdown(label="Style", choices=STYLE_NAMES, value=DEFAULT_STYLE_NAME)
+                            
                 with gr.Tab(label="Multiple Images", id=1, visible=False) as multiimage_input_tab:
                     multiimage_prompt = gr.Gallery(label="Image Prompt", format="png", type="pil", height=300, columns=3)
                     gr.Markdown("""
@@ -409,18 +407,43 @@ with gr.Blocks(delete_cache=(600, 600), js=js_func) as demo:
                     """)
             
             with gr.Accordion(label="Generation Settings", open=False):
-                seed = gr.Slider(0, MAX_SEED, label="Seed", value=0, step=1)
-                randomize_seed = gr.Checkbox(label="Randomize Seed", value=True)
-                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)
-                multiimage_algo = gr.Radio(["stochastic", "multidiffusion"], label="Multi-image Algorithm", value="stochastic")
-
+                with gr.Tab(label="sketch-to-image generation"):
+                    negative_prompt = gr.Textbox(label="Negative prompt")
+                    
+                    num_steps = gr.Slider(
+                    label="Number of steps",
+                    minimum=1,
+                    maximum=20,
+                    step=1,
+                    value=10,
+                )
+                    guidance_scale = gr.Slider(
+                        label="Guidance scale",
+                        minimum=0.1,
+                        maximum=10.0,
+                        step=0.1,
+                        value=5,
+                    )
+                    controlnet_conditioning_scale = gr.Slider(
+                        label="controlnet conditioning scale",
+                        minimum=0.5,
+                        maximum=5.0,
+                        step=0.1,
+                        value=0.9,
+                    )
+                with gr.Tab(label="3D generation"):
+                    seed = gr.Slider(0, MAX_SEED, label="Seed", value=0, step=1)
+                    randomize_seed = gr.Checkbox(label="Randomize Seed", value=True)
+                    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)
+                    multiimage_algo = gr.Radio(["stochastic", "multidiffusion"], label="Multi-image Algorithm", value="stochastic")
+               
             generate_btn = gr.Button("Generate")
             
             with gr.Accordion(label="GLB Extraction Settings", open=False):
@@ -489,13 +512,13 @@ with gr.Blocks(delete_cache=(600, 600), js=js_func) as demo:
     # )
     sketch_btn.click(
         preprocess_image,
-        inputs=[image_prompt, prompt, negative_prompt, style, do_preprocess],
-        outputs=[image_prompt, do_preprocess],
+        inputs=[image_prompt, prompt, negative_prompt, style, num_steps, guidance_scale, controlnet_conditioning_scale],
+        outputs=[image_prompt],
     )
     multiimage_prompt.upload(
         preprocess_images,
         inputs=[multiimage_prompt],
-        outputs=[multiimage_prompt, do_preprocess],
+        outputs=[multiimage_prompt],
     )
 
     generate_btn.click(
@@ -504,8 +527,8 @@ with gr.Blocks(delete_cache=(600, 600), js=js_func) as demo:
         outputs=[seed],
     ).then(
         image_to_3d,
-        inputs=[image_prompt, multiimage_prompt, is_multiimage, seed, ss_guidance_strength, ss_sampling_steps, slat_guidance_strength, slat_sampling_steps, multiimage_algo, do_preprocess],
-        outputs=[output_buf, video_output, do_preprocess],
+        inputs=[image_prompt, multiimage_prompt, is_multiimage, seed, ss_guidance_strength, ss_sampling_steps, slat_guidance_strength, slat_sampling_steps, multiimage_algo],
+        outputs=[output_buf, video_output],
     ).then(
         lambda: tuple([gr.Button(interactive=True), gr.Button(interactive=True)]),
         outputs=[extract_glb_btn, extract_gs_btn],