launch/model_generation.py

import os
import tempfile

import gradio as gr
import numpy as np
from launch.utils import find_cuda
import spaces
import torch
from diffusers import DiffusionPipeline, EulerAncestralDiscreteScheduler
from einops import rearrange
from huggingface_hub import hf_hub_download
from omegaconf import OmegaConf
from PIL import Image
from pytorch_lightning import seed_everything
from torchvision.transforms import v2

from src.utils.camera_util import (FOV_to_intrinsics, get_circular_camera_poses,
                                   get_zero123plus_input_cameras)
from src.utils.mesh_util import save_glb, save_obj
from src.utils.train_util import instantiate_from_config

# Configuration
cuda_path = find_cuda()
config_path = 'configs/instant-mesh-large.yaml'
config = OmegaConf.load(config_path)
config_name = os.path.basename(config_path).replace('.yaml', '')
model_config = config.model_config
infer_config = config.infer_config

IS_FLEXICUBES = config_name.startswith('instant-mesh')
device = torch.device('cuda')

# Load diffusion model
print('Loading diffusion model ...')
pipeline = DiffusionPipeline.from_pretrained(
    "sudo-ai/zero123plus-v1.2",
    custom_pipeline="zero123plus",
    torch_dtype=torch.float16,
)
pipeline.scheduler = EulerAncestralDiscreteScheduler.from_config(
    pipeline.scheduler.config, timestep_spacing='trailing'
)

unet_ckpt_path = hf_hub_download(
    repo_id="TencentARC/InstantMesh", filename="diffusion_pytorch_model.bin", repo_type="model")
state_dict = torch.load(unet_ckpt_path, map_location='cpu')
pipeline.unet.load_state_dict(state_dict, strict=True)

pipeline = pipeline.to(device)

# Load reconstruction model
print('Loading reconstruction model ...')
model_ckpt_path = hf_hub_download(
    repo_id="TencentARC/InstantMesh", filename="instant_mesh_large.ckpt", repo_type="model")
model = instantiate_from_config(model_config)
state_dict = torch.load(model_ckpt_path, map_location='cpu')['state_dict']
state_dict = {k[14:]: v for k, v in state_dict.items() if k.startswith(
    'lrm_generator.') and 'source_camera' not in k}
model.load_state_dict(state_dict, strict=True)

model = model.to(device)


def get_render_cameras(batch_size=1, M=120, radius=2.5, elevation=10.0, is_flexicubes=False):
    c2ws = get_circular_camera_poses(M=M, radius=radius, elevation=elevation)
    if is_flexicubes:
        cameras = torch.linalg.inv(c2ws)
        cameras = cameras.unsqueeze(0).repeat(batch_size, 1, 1, 1)
    else:
        extrinsics = c2ws.flatten(-2)
        intrinsics = FOV_to_intrinsics(50.0).unsqueeze(
            0).repeat(M, 1, 1).float().flatten(-2)
        cameras = torch.cat([extrinsics, intrinsics], dim=-1)
        cameras = cameras.unsqueeze(0).repeat(batch_size, 1, 1)
    return cameras


@spaces.GPU
def generate_mvs(input_image, sample_steps, sample_seed):
    seed_everything(sample_seed)

    z123_image = pipeline(
        input_image, num_inference_steps=sample_steps).images[0]

    show_image = np.asarray(z123_image, dtype=np.uint8)
    show_image = torch.from_numpy(show_image)
    show_image = rearrange(
        show_image, '(n h) (m w) c -> (n m) h w c', n=3, m=2)
    show_image = rearrange(
        show_image, '(n m) h w c -> (n h) (m w) c', n=2, m=3)
    show_image = Image.fromarray(show_image.numpy())

    return z123_image, show_image


@spaces.GPU
def make3d(images):
    global model
    if IS_FLEXICUBES:
        model.init_flexicubes_geometry(device, use_renderer=False)
    model = model.eval()

    images = np.asarray(images, dtype=np.float32) / 255.0
    images = torch.from_numpy(images).permute(2, 0, 1).contiguous().float()
    images = rearrange(images, 'c (n h) (m w) -> (n m) c h w', n=3, m=2)

    input_cameras = get_zero123plus_input_cameras(
        batch_size=1, radius=4.0).to(device)
    render_cameras = get_render_cameras(
        batch_size=1, radius=2.5, is_flexicubes=IS_FLEXICUBES).to(device)

    images = images.unsqueeze(0).to(device)
    images = v2.functional.resize(
        images, (320, 320), interpolation=3, antialias=True).clamp(0, 1)

    mesh_fpath = tempfile.NamedTemporaryFile(suffix=f".obj", delete=False).name
    print(mesh_fpath)
    mesh_basename = os.path.basename(mesh_fpath).split('.')[0]
    mesh_dirname = os.path.dirname(mesh_fpath)
    mesh_glb_fpath = os.path.join(mesh_dirname, f"{mesh_basename}.glb")

    with torch.no_grad():
        planes = model.forward_planes(images, input_cameras)
        mesh_out = model.extract_mesh(
            planes, use_texture_map=False, **infer_config)

        vertices, faces, vertex_colors = mesh_out
        vertices = vertices[:, [1, 2, 0]]

        save_glb(vertices, faces, vertex_colors, mesh_glb_fpath)
        save_obj(vertices, faces, vertex_colors, mesh_fpath)

        print(f"Mesh saved to {mesh_fpath}")

    return mesh_fpath, mesh_glb_fpath


def model_generation_ui(processed_image):
    with gr.Column():
        with gr.Row():
            with gr.Column():
                mv_show_images = gr.Image(
                    label="Generated Multi-views",
                    type="pil",
                    width=379,
                    interactive=False
                )
        with gr.Row():
            with gr.Group():
                sample_seed = gr.Number(
                    value=42, label="Seed Value", precision=0)
                sample_steps = gr.Slider(
                    label="Sample Steps", minimum=30, maximum=75, value=75, step=5)
        with gr.Row():
            submit_mesh = gr.Button(
                "Generate 3D Model", elem_id="generate", variant="primary")
        with gr.Row():
            with gr.Tab("OBJ"):
                output_model_obj = gr.Model3D(
                    label="Output Model (OBJ Format)",
                    interactive=False,
                )
                gr.Markdown(
                    "Note: Downloaded .obj model will be flipped. Export .glb instead or manually flip it before usage.")
            with gr.Tab("GLB"):
                output_model_glb = gr.Model3D(
                    label="Output Model (GLB Format)",
                    interactive=False,
                )
                gr.Markdown(
                    "Note: The model shown here has a darker appearance. Download to get correct results.")
        with gr.Row():
            gr.Markdown(
                '''Try a different <b>seed value</b> if the result is unsatisfying (Default: 42).''')

    mv_images = gr.State()

    submit_mesh.click(fn=generate_mvs, inputs=[processed_image, sample_steps, sample_seed], outputs=[mv_images, mv_show_images]).success(
        fn=make3d, inputs=[mv_images], outputs=[
            output_model_obj, output_model_glb]
    )

    return output_model_obj, output_model_glb