Spaces:
Runtime error
Runtime error
File size: 11,051 Bytes
5845270 aabfbe0 5845270 aabfbe0 5845270 aabfbe0 d4c4c25 aabfbe0 d4c4c25 aabfbe0 d4c4c25 aabfbe0 07db937 aabfbe0 07db937 aabfbe0 07db937 aabfbe0 07db937 aabfbe0 3103d69 aabfbe0 9e3e77c aabfbe0 862266f aabfbe0 d4c4c25 aabfbe0 d4c4c25 aabfbe0 07db937 aabfbe0 07db937 aabfbe0 3103d69 aabfbe0 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 |
import gradio as gr
import spaces
from gradio_litmodel3d import LitModel3D
import os
import shutil
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
from trellis.pipelines import TrellisImageTo3DPipeline
from trellis.representations import Gaussian, MeshExtractResult
from trellis.utils import render_utils, postprocessing_utils
MAX_SEED = np.iinfo(np.int32).max
TMP_DIR = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'tmp')
# os.makedirs(TMP_DIR, exist_ok=True)
# def start_session(req: gr.Request):
# gr.Warning('start start session')
# user_dir = os.path.join(TMP_DIR, str(req.session_hash))
# os.makedirs(user_dir, exist_ok=True)
# gr.Warning('end start session')
# def end_session(req: gr.Request):
# user_dir = os.path.join(TMP_DIR, str(req.session_hash))
# shutil.rmtree(user_dir)
# def preprocess_image(image: Image.Image) -> Image.Image:
# """
# Preprocess the input image.
# Args:
# image (Image.Image): The input image.
# Returns:
# Image.Image: The preprocessed image.
# """
# processed_image = pipeline.preprocess_image(image)
# return processed_image
# def pack_state(gs: Gaussian, 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(
# 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:
# """
# Get the random seed.
# """
# return np.random.randint(0, MAX_SEED) if randomize_seed else seed
# @spaces.GPU
# def image_to_3d(
# image: Image.Image,
# seed: int,
# ss_guidance_strength: float,
# ss_sampling_steps: int,
# slat_guidance_strength: float,
# slat_sampling_steps: int,
# req: gr.Request,
# ) -> Tuple[dict, str]:
# """
# Convert an image to a 3D model.
# Args:
# image (Image.Image): The input image.
# 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.
# 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))
# 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))]
# 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])
# torch.cuda.empty_cache()
# return state, video_path
# @spaces.GPU(duration=90)
# def extract_glb(
# state: dict,
# mesh_simplify: float,
# texture_size: int,
# req: gr.Request,
# ) -> Tuple[str, str]:
# """
# Extract a GLB file from the 3D model.
# Args:
# state (dict): The state of the generated 3D model.
# mesh_simplify (float): The mesh simplification factor.
# texture_size (int): The texture resolution.
# Returns:
# str: The path to the extracted GLB file.
# """
# 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)
# glb_path = os.path.join(user_dir, 'sample.glb')
# glb.export(glb_path)
# torch.cuda.empty_cache()
# return glb_path, glb_path
# @spaces.GPU
# def extract_gaussian(state: dict, req: gr.Request) -> Tuple[str, str]:
# """
# Extract a Gaussian file from the 3D model.
# Args:
# state (dict): The state of the generated 3D model.
# Returns:
# str: The path to the extracted Gaussian file.
# """
# user_dir = os.path.join(TMP_DIR, str(req.session_hash))
# gs, _ = unpack_state(state)
# gaussian_path = os.path.join(user_dir, 'sample.ply')
# gs.save_ply(gaussian_path)
# torch.cuda.empty_cache()
# return gaussian_path, gaussian_path
# 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):
# 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("""
## Text to 3D Asset with Mistral + Flux + Trellis
* Upload an image and click "Generate" to create a 3D asset
""")
with gr.Row():
with gr.Column():
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)
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)
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)
with gr.Row():
extract_glb_btn = gr.Button("Extract GLB", interactive=False)
extract_gs_btn = gr.Button("Extract Gaussian", interactive=False)
with gr.Column():
video_output = gr.Video(label="Generated 3D Asset", autoplay=True, loop=True, height=300)
model_output = LitModel3D(label="Extracted GLB/Gaussian", exposure=10.0, height=300)
with gr.Row():
download_glb = gr.DownloadButton(label="Download GLB", interactive=False)
download_gs = gr.DownloadButton(label="Download Gaussian", interactive=False)
# output_buf = gr.State()
# Handlers
# demo.load(start_session)
# demo.unload(end_session)
# image_prompt.upload(
# preprocess_image,
# inputs=[image_prompt],
# outputs=[image_prompt],
# )
# generate_btn.click(
# get_seed,
# inputs=[randomize_seed, seed],
# outputs=[seed],
# ).then(
# image_to_3d,
# inputs=[image_prompt, seed, ss_guidance_strength, ss_sampling_steps, slat_guidance_strength, slat_sampling_steps],
# outputs=[output_buf, video_output],
# ).then(
# lambda: tuple([gr.Button(interactive=True), gr.Button(interactive=True)]),
# outputs=[extract_glb_btn, extract_gs_btn],
# )
# video_output.clear(
# lambda: tuple([gr.Button(interactive=False), gr.Button(interactive=False)]),
# outputs=[extract_glb_btn, extract_gs_btn],
# )
# extract_glb_btn.click(
# extract_glb,
# inputs=[output_buf, mesh_simplify, texture_size],
# outputs=[model_output, download_glb],
# ).then(
# lambda: gr.Button(interactive=True),
# outputs=[download_glb],
# )
# extract_gs_btn.click(
# extract_gaussian,
# inputs=[output_buf],
# outputs=[model_output, download_gs],
# ).then(
# lambda: gr.Button(interactive=True),
# outputs=[download_gs],
# )
# model_output.clear(
# lambda: gr.Button(interactive=False),
# outputs=[download_glb],
# )
# Launch the Gradio app
if __name__ == "__main__":
pipeline = TrellisImageTo3DPipeline.from_pretrained("JeffreyXiang/TRELLIS-image-large")
pipeline.cuda()
# try:
# pipeline.preprocess_image(Image.fromarray(np.zeros((512, 512, 3), dtype=np.uint8))) # Preload rembg
# except:
# pass
demo.launch()
|