Remove multi-image functionality

app.py

@@ -2,7 +2,6 @@ import os
 import shlex
 import shutil
 import subprocess
-from typing import Literal
 
 os.environ["SPCONV_ALGO"] = "native"
 
@@ -121,65 +120,44 @@ def get_seed(randomize_seed: bool, seed: int) -> int:
 @spaces.GPU
 def image_to_3d(
     image: Image.Image,
-    multiimages: list[tuple[Image.Image, str]],
-    is_multiimage: bool,
     seed: int,
     ss_guidance_strength: float,
     ss_sampling_steps: int,
     slat_guidance_strength: float,
     slat_sampling_steps: int,
-    multiimage_algo: Literal["multidiffusion", "stochastic"],
     req: gr.Request,
 ) -> tuple[dict, str]:
     """Convert an image to a 3D model.
 
     Args:
         image (Image.Image): The input image.
-        multiimages (List[Tuple[Image.Image, str]]): The input images in multi-image mode.
-        is_multiimage (bool): Whether is in multi-image mode.
         seed (int): The random seed.
         ss_guidance_strength (float): The guidance strength for sparse structure generation.
         ss_sampling_steps (int): The number of sampling steps for sparse structure generation.
         slat_guidance_strength (float): The guidance strength for structured latent generation.
         slat_sampling_steps (int): The number of sampling steps for structured latent generation.
-        multiimage_algo (Literal["multidiffusion", "stochastic"]): The algorithm for multi-image generation.
 
     Returns:
         dict: The information of the generated 3D model.
         str: The path to the video of the 3D model.
     """
     user_dir = os.path.join(TMP_DIR, str(req.session_hash))
-    if not is_multiimage:
-        outputs = pipeline.run(
-            image,
-            seed=seed,
-            formats=["gaussian", "mesh"],
-            preprocess_image=False,
-            sparse_structure_sampler_params={
-                "steps": ss_sampling_steps,
-                "cfg_strength": ss_guidance_strength,
-            },
-            slat_sampler_params={
-                "steps": slat_sampling_steps,
-                "cfg_strength": slat_guidance_strength,
-            },
-        )
-    else:
-        outputs = pipeline.run_multi_image(
-            [image[0] for image in multiimages],
-            seed=seed,
-            formats=["gaussian", "mesh"],
-            preprocess_image=False,
-            sparse_structure_sampler_params={
-                "steps": ss_sampling_steps,
-                "cfg_strength": ss_guidance_strength,
-            },
-            slat_sampler_params={
-                "steps": slat_sampling_steps,
-                "cfg_strength": slat_guidance_strength,
-            },
-            mode=multiimage_algo,
-        )
+
+    outputs = pipeline.run(
+        image,
+        seed=seed,
+        formats=["gaussian", "mesh"],
+        preprocess_image=False,
+        sparse_structure_sampler_params={
+            "steps": ss_sampling_steps,
+            "cfg_strength": ss_guidance_strength,
+        },
+        slat_sampler_params={
+            "steps": slat_sampling_steps,
+            "cfg_strength": slat_guidance_strength,
+        },
+    )
+
     video = render_utils.render_video(outputs["gaussian"][0], num_frames=120)["color"]
     video_geo = render_utils.render_video(outputs["mesh"][0], num_frames=120)["normal"]
     video = [np.concatenate([video[i], video_geo[i]], axis=1) for i in range(len(video))]
@@ -248,19 +226,6 @@ def prepare_multi_example() -> list[Image.Image]:
     return images
 
 
-def split_image(image: Image.Image) -> list[Image.Image]:
-    """Split an image into multiple views."""
-    image = np.array(image)
-    alpha = image[..., 3]
-    alpha = np.any(alpha > 0, axis=0)
-    start_pos = np.where(~alpha[:-1] & alpha[1:])[0].tolist()
-    end_pos = np.where(alpha[:-1] & ~alpha[1:])[0].tolist()
-    images = []
-    for s, e in zip(start_pos, end_pos, strict=False):
-        images.append(Image.fromarray(image[:, s : e + 1]))
-    return [preprocess_image(image) for image in images]
-
-
 with gr.Blocks(delete_cache=(600, 600)) as demo:
     gr.Markdown("""
     ## Image to 3D Asset with [TRELLIS](https://trellis3d.github.io/)
@@ -272,51 +237,35 @@ with gr.Blocks(delete_cache=(600, 600)) as demo:
 
     with gr.Row():
         with gr.Column():
-            with gr.Tabs() as input_tabs:
-                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,
-                    )
-                with gr.Tab(label="Multiple Images", id=1) as multiimage_input_tab:
-                    multiimage_prompt = gr.Gallery(
-                        label="Image Prompt",
-                        format="png",
-                        type="pil",
-                        height=300,
-                        columns=3,
-                    )
-                    gr.Markdown("""
-                        Input different views of the object in separate images.
-
-                        *NOTE: this is an experimental algorithm without training a specialized model. It may not produce the best results for all images, especially those having different poses or inconsistent details.*
-                    """)
+            image_prompt = gr.Image(
+                label="Image Prompt",
+                format="png",
+                image_mode="RGBA",
+                type="pil",
+                height=300,
+            )
 
             with gr.Accordion(label="Generation Settings", open=False):
-                seed = gr.Slider(0, MAX_SEED, label="Seed", value=0, step=1)
+                seed = gr.Slider(label="Seed", minimum=0, maximum=MAX_SEED, step=1, value=0)
                 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)
+                    ss_guidance_strength = gr.Slider(
+                        label="Guidance Strength", minimum=0.0, maximum=10.0, step=0.1, value=7.5
+                    )
+                    ss_sampling_steps = gr.Slider(label="Sampling Steps", minimum=1, maximum=50, step=1, value=12)
                 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",
-                )
+                    slat_guidance_strength = gr.Slider(
+                        label="Guidance Strength", minimum=0.0, maximum=10.0, step=0.1, value=3.0
+                    )
+                    slat_sampling_steps = gr.Slider(label="Sampling Steps", minimum=1, maximum=50, step=1, value=12)
 
             generate_btn = gr.Button("Generate")
 
             with gr.Accordion(label="GLB Extraction Settings", open=False):
-                mesh_simplify = gr.Slider(0.9, 0.98, label="Simplify", value=0.95, step=0.01)
-                texture_size = gr.Slider(512, 2048, label="Texture Size", value=1024, step=512)
+                mesh_simplify = gr.Slider(label="Simplify", minimum=0.9, maximum=0.98, step=0.01, value=0.95)
+                texture_size = gr.Slider(label="Texture Size", minimum=512, maximum=2048, step=512, value=1024)
 
             with gr.Row():
                 extract_glb_btn = gr.Button("Extract GLB", interactive=False)
@@ -333,101 +282,72 @@ with gr.Blocks(delete_cache=(600, 600)) as demo:
                 download_glb = gr.DownloadButton(label="Download GLB", interactive=False)
                 download_gs = gr.DownloadButton(label="Download Gaussian", interactive=False)
 
-    is_multiimage = gr.State(False)  # noqa: FBT003
     output_buf = gr.State()
 
-    # Example images at the bottom of the page
-    with gr.Row() as single_image_example:
-        examples = gr.Examples(
-            examples=[f"assets/example_image/{image}" for image in os.listdir("assets/example_image")],
-            inputs=[image_prompt],
-            fn=preprocess_image,
-            outputs=[image_prompt],
-            run_on_click=True,
-            examples_per_page=64,
-        )
-    with gr.Row(visible=False) as multiimage_example:
-        examples_multi = gr.Examples(
-            examples=prepare_multi_example(),
-            inputs=[image_prompt],
-            fn=split_image,
-            outputs=[multiimage_prompt],
-            run_on_click=True,
-            examples_per_page=8,
-        )
+    examples = gr.Examples(
+        examples=[f"assets/example_image/{image}" for image in os.listdir("assets/example_image")],
+        inputs=[image_prompt],
+        fn=preprocess_image,
+        outputs=[image_prompt],
+        run_on_click=True,
+        examples_per_page=64,
+    )
 
     # Handlers
     demo.load(start_session)
     demo.unload(end_session)
 
-    single_image_input_tab.select(
-        lambda: (False, gr.Row.update(visible=True), gr.Row.update(visible=False)),
-        outputs=[is_multiimage, single_image_example, multiimage_example],
-    )
-    multiimage_input_tab.select(
-        lambda: (True, gr.Row.update(visible=False), gr.Row.update(visible=True)),
-        outputs=[is_multiimage, single_image_example, multiimage_example],
-    )
-
     image_prompt.upload(
-        preprocess_image,
-        inputs=[image_prompt],
-        outputs=[image_prompt],
-    )
-    multiimage_prompt.upload(
-        preprocess_images,
-        inputs=[multiimage_prompt],
-        outputs=[multiimage_prompt],
+        fn=preprocess_image,
+        inputs=image_prompt,
+        outputs=image_prompt,
     )
 
     generate_btn.click(
-        get_seed,
+        fn=get_seed,
         inputs=[randomize_seed, seed],
-        outputs=[seed],
+        outputs=seed,
     ).then(
-        image_to_3d,
+        fn=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,
         ],
         outputs=[output_buf, video_output],
     ).then(
-        lambda: (gr.Button(interactive=True), gr.Button(interactive=True)),
+        fn=lambda: (gr.Button(interactive=True), gr.Button(interactive=True)),
         outputs=[extract_glb_btn, extract_gs_btn],
     )
 
     video_output.clear(
-        lambda: (gr.Button(interactive=False), gr.Button(interactive=False)),
+        fn=lambda: (gr.Button(interactive=False), gr.Button(interactive=False)),
         outputs=[extract_glb_btn, extract_gs_btn],
     )
 
     extract_glb_btn.click(
-        extract_glb,
+        fn=extract_glb,
         inputs=[output_buf, mesh_simplify, texture_size],
         outputs=[model_output, download_glb],
     ).then(
-        lambda: gr.Button(interactive=True),
+        fn=lambda: gr.Button(interactive=True),
         outputs=[download_glb],
     )
 
     extract_gs_btn.click(
-        extract_gaussian,
+        fn=extract_gaussian,
         inputs=[output_buf],
         outputs=[model_output, download_gs],
     ).then(
-        lambda: gr.Button(interactive=True),
+        fn=lambda: gr.Button(interactive=True),
         outputs=[download_gs],
     )
 
     model_output.clear(
-        lambda: gr.Button(interactive=False),
+        fn=lambda: gr.Button(interactive=False),
         outputs=[download_glb],
     )