app.py

import os
import spaces
import random
import shutil
import gradio as gr
from glob import glob
from pathlib import Path
import uuid
import argparse
import torch


parser = argparse.ArgumentParser()
parser.add_argument("--model_path", type=str, default='tencent/Hunyuan3D-2mini')
parser.add_argument("--subfolder", type=str, default='hunyuan3d-dit-v2-mini-turbo')
parser.add_argument("--texgen_model_path", type=str, default='tencent/Hunyuan3D-2')
parser.add_argument('--port', type=int, default=7860)
parser.add_argument('--host', type=str, default='0.0.0.0')
parser.add_argument('--device', type=str, default='cuda')
parser.add_argument('--mc_algo', type=str, default='mc')
parser.add_argument('--cache_path', type=str, default='gradio_cache')
parser.add_argument('--enable_t23d', action='store_true')
parser.add_argument('--disable_tex', action='store_true')
parser.add_argument('--enable_flashvdm', action='store_true')
parser.add_argument('--compile', action='store_true')
parser.add_argument('--low_vram_mode', action='store_true')
args = parser.parse_args()
args.enable_flashvdm = True

SAVE_DIR = args.cache_path
os.makedirs(SAVE_DIR, exist_ok=True)


def randomize_seed_fn(seed: int, randomize_seed: bool) -> int:
    if randomize_seed:
        seed = random.randint(0, MAX_SEED)
    return seed


def gen_save_folder(max_size=200):
    os.makedirs(SAVE_DIR, exist_ok=True)

    # 获取所有文件夹路径
    dirs = [f for f in Path(SAVE_DIR).iterdir() if f.is_dir()]

    # 如果文件夹数量超过 max_size，删除创建时间最久的文件夹
    if len(dirs) >= max_size:
        # 按创建时间排序，最久的排在前面
        oldest_dir = min(dirs, key=lambda x: x.stat().st_ctime)
        shutil.rmtree(oldest_dir)
        print(f"Removed the oldest folder: {oldest_dir}")

    # 生成一个新的 uuid 文件夹名称
    new_folder = os.path.join(SAVE_DIR, str(uuid.uuid4()))
    os.makedirs(new_folder, exist_ok=True)
    print(f"Created new folder: {new_folder}")

    return new_folder


from hy3dgen.shapegen import FaceReducer, FloaterRemover, DegenerateFaceRemover, MeshSimplifier, \
    Hunyuan3DDiTFlowMatchingPipeline
from hy3dgen.rembg import BackgroundRemover

rmbg_worker = BackgroundRemover()
i23d_worker = Hunyuan3DDiTFlowMatchingPipeline.from_pretrained(
    args.model_path,
    subfolder=args.subfolder,
    use_safetensors=True,
    device=args.device,
)
if args.enable_flashvdm:
    mc_algo = 'mc' if args.device in ['cpu', 'mps'] else args.mc_algo
    i23d_worker.enable_flashvdm(mc_algo=mc_algo)
if args.compile:
    i23d_worker.compile()

progress=gr.Progress()

@spaces.GPU(duration=60)
def gen_shape(
    image=None,
    steps=50,
    guidance_scale=7.5,
    seed=1234,
    octree_resolution=256,
    num_chunks=200000,
    target_face_num=10000,
    randomize_seed: bool = False,
):
    
    def callback(step_idx, timestep, outputs):
        progress_value = (step_idx+1.0)/steps
        progress(progress_value, desc=f"Mesh generating, {step_idx + 1}/{steps} steps")


    if image is None:
        raise gr.Error("Please provide either a caption or an image.")

    seed = int(randomize_seed_fn(seed, randomize_seed))
    octree_resolution = int(octree_resolution)
    save_folder = gen_save_folder()

    image = rmbg_worker(image.convert('RGB'))

    generator = torch.Generator()
    generator = generator.manual_seed(int(seed))
    outputs = i23d_worker(
        image=image,
        num_inference_steps=steps,
        guidance_scale=guidance_scale,
        generator=generator,
        octree_resolution=octree_resolution,
        num_chunks=num_chunks,
        output_type='mesh',
        callback=callback
    )
    print(outputs)



    
def get_example_img_list():
    print('Loading example img list ...')
    return sorted(glob('./assets/example_images/**/*.png', recursive=True))
example_imgs = get_example_img_list()

HTML_OUTPUT_PLACEHOLDER = f"""
<div style='height: {650}px; width: 100%; border-radius: 8px; border-color: #e5e7eb; border-style: solid; border-width: 1px; display: flex; justify-content: center; align-items: center;'>
    <div style='text-align: center; font-size: 16px; color: #6b7280;'>
    <p style="color: #8d8d8d;">No mesh here.</p>
    </div>
</div>
"""
MAX_SEED = 1e7

title = "## Image to 3D"
description = "A lightweight image to 3D converter"

with gr.Blocks().queue() as demo:
    gr.Markdown(title)
    gr.Markdown(description)
    with gr.Row():
        with gr.Column(scale=3):
            gr.Markdown("#### Image Prompt")
            image = gr.Image(sources=["upload"], label='Image', type='pil', image_mode='RGBA', height=290)
            gen_button = gr.Button(value='Generate Shape', variant='primary')
            with gr.Accordion("Advanced Options", open=False):
                with gr.Column():
                    seed = gr.Slider(
                        label="Seed",
                        minimum=0,
                        maximum=MAX_SEED,
                        step=1,
                        value=1234,
                        min_width=100,
                    )
                    randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
                with gr.Column():
                    num_steps = gr.Slider(maximum=100, minimum=1, value=5, step=1, label='Inference Steps')
                    octree_resolution = gr.Slider(maximum=512, minimum=16, value=256, label='Octree Resolution')
                with gr.Column():
                    cfg_scale = gr.Slider(maximum=20.0, minimum=1.0, value=5.5, step=0.1, label='Guidance Scale')
                    num_chunks = gr.Slider(maximum=5000000, minimum=1000, value=8000, label='Number of Chunks')
                target_face_num = gr.Slider(maximum=1000000, minimum=100, value=10000, label='Target Face Number')

        with gr.Column(scale=6):
            gr.Markdown("#### Generated Mesh")
            html_export_mesh = gr.HTML(HTML_OUTPUT_PLACEHOLDER, label='Output')
                
        with gr.Column(scale=3):
            gr.Markdown("#### Image Examples")
            gr.Examples(examples=example_imgs, inputs=[image],
                        label=None, examples_per_page=18)
            
    gen_button.click(
        fn=gen_shape,
        inputs=[image,num_steps,cfg_scale,seed,octree_resolution,num_chunks,target_face_num, randomize_seed], 
        outputs=[html_export_mesh]
    )    

demo.launch()