Buckets:
| import os | |
| os.environ["PYTORCH_CUDA_ALLOC_CONF"] = "expandable_segments:True" # Can save GPU memory | |
| import trimesh | |
| from PIL import Image | |
| from trellis2.pipelines import Trellis2TexturingPipeline | |
| # 1. Load Pipeline | |
| pipeline = Trellis2TexturingPipeline.from_pretrained("microsoft/TRELLIS.2-4B", config_file="texturing_pipeline.json") | |
| pipeline.cuda() | |
| # 2. Load Mesh, image & Run | |
| mesh = trimesh.load("assets/example_texturing/the_forgotten_knight.ply") | |
| image = Image.open("assets/example_texturing/image.webp") | |
| output = pipeline.run(mesh, image) | |
| # 3. Render Mesh | |
| output.export("textured.glb", extension_webp=True) |
Xet Storage Details
- Size:
- 611 Bytes
- Xet hash:
- 3ac29883d811a3671f74aee713f58ff4fb2aefa2a5133d5b0a1058582a0436b7
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.