Update app.py

app.py

@@ -3,16 +3,20 @@ import spaces
 from gradio_litmodel3d import LitModel3D
 import os
 import shutil
-import numpy as np
+os.environ['SPCONV_ALGO'] = 'native'
+from typing import *
 import torch
+import numpy as np
+import imageio
+from easydict import EasyDict as edict
 from PIL import Image, ImageOps
 from trellis.pipelines import TrellisImageTo3DPipeline
-from trellis.representations import Gaussian, MeshExtractResult
+from trellis.representations import MeshExtractResult
 from trellis.utils import render_utils, postprocessing_utils
 from diffusers import ControlNetModel, StableDiffusionXLControlNetPipeline, AutoencoderKL
 from diffusers import EulerAncestralDiscreteScheduler
-
-os.environ['SPCONV_ALGO'] = 'native'
+from huggingface_hub import HfApi
+from pathlib import Path
 
 style_list = [
     {
@@ -20,9 +24,52 @@ style_list = [
         "prompt": "{prompt}",
         "negative_prompt": "longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
     },
-    # ... (resto de los estilos sin cambios)
+    {
+        "name": "Cinematic",
+        "prompt": "cinematic still {prompt} . emotional, harmonious, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy",
+        "negative_prompt": "anime, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured",
+    },
+    {
+        "name": "3D Model",
+        "prompt": "professional 3d model {prompt} . octane render, highly detailed, volumetric, dramatic lighting",
+        "negative_prompt": "ugly, deformed, noisy, low poly, blurry, painting",
+    },
+    {
+        "name": "Anime",
+        "prompt": "anime artwork {prompt} . anime style, key visual, vibrant, studio anime,  highly detailed",
+        "negative_prompt": "photo, deformed, black and white, realism, disfigured, low contrast",
+    },
+    {
+        "name": "Digital Art",
+        "prompt": "concept art {prompt} . digital artwork, illustrative, painterly, matte painting, highly detailed",
+        "negative_prompt": "photo, photorealistic, realism, ugly",
+    },
+    {
+        "name": "Photographic",
+        "prompt": "cinematic photo {prompt} . 35mm photograph, film, bokeh, professional, 4k, highly detailed",
+        "negative_prompt": "drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly",
+    },
+    {
+        "name": "Pixel art",
+        "prompt": "pixel-art {prompt} . low-res, blocky, pixel art style, 8-bit graphics",
+        "negative_prompt": "sloppy, messy, blurry, noisy, highly detailed, ultra textured, photo, realistic",
+    },
+    {
+        "name": "Fantasy art",
+        "prompt": "ethereal fantasy concept art of  {prompt} . magnificent, celestial, ethereal, painterly, epic, majestic, magical, fantasy art, cover art, dreamy",
+        "negative_prompt": "photographic, realistic, realism, 35mm film, dslr, cropped, frame, text, deformed, glitch, noise, noisy, off-center, deformed, cross-eyed, closed eyes, bad anatomy, ugly, disfigured, sloppy, duplicate, mutated, black and white",
+    },
+    {
+        "name": "Neonpunk",
+        "prompt": "neonpunk style {prompt} . cyberpunk, vaporwave, neon, vibes, vibrant, stunningly beautiful, crisp, detailed, sleek, ultramodern, magenta highlights, dark purple shadows, high contrast, cinematic, ultra detailed, intricate, professional",
+        "negative_prompt": "painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured",
+    },
+    {
+        "name": "Manga",
+        "prompt": "manga style {prompt} . vibrant, high-energy, detailed, iconic, Japanese comic style",
+        "negative_prompt": "ugly, deformed, noisy, blurry, low contrast, realism, photorealistic, Western comic style",
+    },
 ]
-
 styles = {k["name"]: (k["prompt"], k["negative_prompt"]) for k in style_list}
 STYLE_NAMES = list(styles.keys())
 DEFAULT_STYLE_NAME = "(No style)"
@@ -31,9 +78,7 @@ TMP_DIR = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'tmp')
 os.makedirs(TMP_DIR, exist_ok=True)
 
 def reset_canvas():
-    return gr.update(value={"background": Image.new("RGB", (512, 512), (255, 255, 255)), 
-                            "layers": [Image.new("RGB", (512, 512), (255, 255, 255))], 
-                            "composite": Image.new("RGB", (512, 512), (255, 255, 255))})
+    return gr.update(value={"background":Image.new("RGB", (512, 512), (255, 255, 255)), "layers":[Image.new("RGB", (512, 512), (255, 255, 255))], "composite":Image.new("RGB", (512, 512), (255, 255, 255))})
 
 def apply_style(style_name: str, positive: str, negative: str = "") -> tuple[str, str]:
     p, n = styles.get(style_name, styles[DEFAULT_STYLE_NAME])
@@ -74,41 +119,19 @@ def preprocess_image(image: Image.Image,
     processed_image = pipeline.preprocess_image(output)
     return (image, processed_image)
 
-def pack_state(gs: Gaussian, mesh: MeshExtractResult) -> dict:
+def pack_state(mesh: MeshExtractResult) -> dict:
     return {
-        'gaussian': {
-            **gs.init_params,
-            '_xyz': gs._xyz.cpu().numpy(),
-            '_features_dc': gs._features_dc.cpu().numpy(),
-            '_scaling': gs._scaling.cpu().numpy(),
-            '_rotation': gs._rotation.cpu().numpy(),
-            '_opacity': gs._opacity.cpu().numpy(),
-        },
         'mesh': {
             'vertices': mesh.vertices.cpu().numpy(),
             'faces': mesh.faces.cpu().numpy(),
         },
     }
 
-def unpack_state(state: dict) -> Tuple[Gaussian, edict, str]:
-    gs = Gaussian(
-        aabb=state['gaussian']['aabb'],
-        sh_degree=state['gaussian']['sh_degree'],
-        mininum_kernel_size=state['gaussian']['mininum_kernel_size'],
-        scaling_bias=state['gaussian']['scaling_bias'],
-        opacity_bias=state['gaussian']['opacity_bias'],
-        scaling_activation=state['gaussian']['scaling_activation'],
-    )
-    gs._xyz = torch.tensor(state['gaussian']['_xyz'], device='cuda')
-    gs._features_dc = torch.tensor(state['gaussian']['_features_dc'], device='cuda')
-    gs._scaling = torch.tensor(state['gaussian']['_scaling'], device='cuda')
-    gs._rotation = torch.tensor(state['gaussian']['_rotation'], device='cuda')
-    gs._opacity = torch.tensor(state['gaussian']['_opacity'], device='cuda')
-    mesh = edict(
+def unpack_state(state: dict) -> edict:
+    return edict(
         vertices=torch.tensor(state['mesh']['vertices'], device='cuda'),
         faces=torch.tensor(state['mesh']['faces'], device='cuda'),
     )
-    return gs, mesh
 
 def get_seed(randomize_seed: bool, seed: int) -> int:
     return np.random.randint(0, MAX_SEED) if randomize_seed else seed
@@ -127,7 +150,7 @@ def image_to_3d(
     outputs = pipeline.run(
         image[1],
         seed=seed,
-        formats=["gaussian", "mesh"],
+        formats=["mesh"],
         preprocess_image=False,
         sparse_structure_sampler_params={
             "steps": ss_sampling_steps,
@@ -138,12 +161,10 @@ def image_to_3d(
             "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))]
+    video = render_utils.render_video(outputs['mesh'][0], num_frames=120)['normal']
     video_path = os.path.join(user_dir, 'sample.mp4')
     imageio.mimsave(video_path, video, fps=15)
-    state = pack_state(outputs['gaussian'][0], outputs['mesh'][0])
+    state = pack_state(outputs['mesh'][0])
     torch.cuda.empty_cache()
     return state, video_path
 
@@ -153,75 +174,68 @@ def extract_glb(
     mesh_simplify: float,
     texture_size: int,
     req: gr.Request,
-) -> Tuple[str, str]:
+) -> str:
     user_dir = os.path.join(TMP_DIR, str(req.session_hash))
-    gs, mesh = unpack_state(state)
-    glb = postprocessing_utils.to_glb(gs, mesh, simplify=mesh_simplify, texture_size=texture_size, verbose=False)
+    mesh = unpack_state(state)
+    glb = postprocessing_utils.to_glb(mesh, simplify=mesh_simplify, texture_size=texture_size, verbose=False)
     glb_path = os.path.join(user_dir, 'sample.glb')
     glb.export(glb_path)
     torch.cuda.empty_cache()
-    return glb_path, glb_path
+    return glb_path
+
+def reset_do_preprocess():
+    return True
 
 with gr.Blocks(delete_cache=(600, 600)) as demo:
     gr.Markdown("""
     ## Sketch to 3D with TRELLIS
     1. Fast sketch to image with SDXL Flash
     2. Scalable and versatile image to 3D generation using [TRELLIS](https://trellis3d.github.io/)
-    ### 🎨	Draw or upload a sketch and click "Generate" to create a 3D asset 💎
+    ### 🎨 Draw or upload a sketch and click "Generate" to create a 3D asset ✨
     """)
-    
     with gr.Row():
         with gr.Column():
-            image_prompt = gr.ImageMask(label="Input sketch", type="pil", image_mode="RGB", height=512, 
-                value={"background": Image.new("RGB", (512, 512), (255, 255, 255)), 
-                       "layers": [Image.new("RGB", (512, 512), (255, 255, 255))], 
-                       "composite": Image.new("RGB", (512, 512), (255, 255, 255))})
-            
+            image_prompt = gr.ImageMask(label="Input sketch", type="pil", image_mode="RGB", height=512, value=reset_canvas())
             with gr.Row():
                 sketch_btn = gr.Button("Process sketch")
                 generate_btn = gr.Button("Generate 3D")
-            
             with gr.Row():
                 prompt = gr.Textbox(label="Prompt")
                 style = gr.Dropdown(label="Style", choices=STYLE_NAMES, value=DEFAULT_STYLE_NAME)
-            
             with gr.Accordion(label="Generation Settings", open=False):
                 with gr.Tab(label="sketch-to-image generation"):
                     negative_prompt = gr.Textbox(label="Negative prompt")
                     num_steps = gr.Slider(1, 20, label="Number of steps", value=8, step=1)
                     guidance_scale = gr.Slider(0.1, 10.0, label="Guidance scale", value=5, step=0.1)
                     controlnet_conditioning_scale = gr.Slider(0.5, 5.0, label="ControlNet conditioning scale", value=0.85, step=0.01)
-                
                 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)
-            
             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)
-            
             with gr.Row():
                 extract_glb_btn = gr.Button("Extract GLB", interactive=False)
-        
+            gr.Markdown("")
+
         with gr.Column():
             video_output = gr.Video(label="Generated 3D Asset", autoplay=True, loop=True, height=300)
             image_prompt_processed = gr.Image(label="Processed sketch", interactive=False, type="pil", height=512)
             model_output = LitModel3D(label="Extracted GLB", exposure=10.0, height=300)
             download_glb = gr.DownloadButton(label="Download GLB", interactive=False)
-    
+
     output_buf = gr.State()
-    
-    with gr.Row():
+    do_preprocess = gr.State(True)
+
+    with gr.Row(visible=False) as single_image_example:
         examples = gr.Examples(
             examples=[f'assets/example_image/{image}' for image in os.listdir("assets/example_image")],
             inputs=[image_prompt],
@@ -233,9 +247,9 @@ with gr.Blocks(delete_cache=(600, 600)) as demo:
 
     demo.load(start_session)
     demo.unload(end_session)
-    
+
     image_prompt.clear(reset_canvas, outputs=[image_prompt])
-    
+
     sketch_btn.click(
         get_seed,
         inputs=[randomize_seed, seed],
@@ -245,7 +259,7 @@ with gr.Blocks(delete_cache=(600, 600)) as demo:
         inputs=[image_prompt, prompt, negative_prompt, style, num_steps, guidance_scale, controlnet_conditioning_scale],
         outputs=[image_prompt_processed],
     )
-    
+
     generate_btn.click(
         get_seed,
         inputs=[randomize_seed, seed],
@@ -258,12 +272,12 @@ with gr.Blocks(delete_cache=(600, 600)) as demo:
         lambda: gr.Button(interactive=True),
         outputs=[extract_glb_btn],
     )
-    
+
     video_output.clear(
         lambda: gr.Button(interactive=False),
         outputs=[extract_glb_btn],
     )
-    
+
     extract_glb_btn.click(
         extract_glb,
         inputs=[output_buf, mesh_simplify, texture_size],
@@ -272,7 +286,7 @@ with gr.Blocks(delete_cache=(600, 600)) as demo:
         lambda: gr.Button(interactive=True),
         outputs=[download_glb],
     )
-    
+
     model_output.clear(
         lambda: gr.Button(interactive=False),
         outputs=[download_glb],
@@ -281,23 +295,19 @@ with gr.Blocks(delete_cache=(600, 600)) as demo:
 if __name__ == "__main__":
     pipeline = TrellisImageTo3DPipeline.from_pretrained("JeffreyXiang/TRELLIS-image-large")
     pipeline.cuda()
-    
     device = "cuda" if torch.cuda.is_available() else "cpu"
     
     controlnet = ControlNetModel.from_pretrained(
         "xinsir/controlnet-scribble-sdxl-1.0",
         torch_dtype=torch.float16
     )
-    
     vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16)
-    
     pipe_control = StableDiffusionXLControlNetPipeline.from_pretrained(
         "sd-community/sdxl-flash",
         controlnet=controlnet,
         vae=vae,
         torch_dtype=torch.float16,
     )
-    
     pipe_control.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe_control.scheduler.config)
     pipe_control.to(device)