Instructions to use chibifire/pixal3d with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- TRELLIS.2
How to use chibifire/pixal3d with TRELLIS.2:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
pixal3d
Pointer repo for Pixal3D. The weights live in two shape-matched chibifire forks.
What it is for
The repo holds no weights. It stays as a redirect target because chibifire/pixal3d was referenced before.
Pixal3D is the TRELLIS.2 implementation. New consumers point at one of these forks:
- chibifire/Pixal3D-GGUF: Q4, Q5, Q6 and Q8 GGUF plus bf16 originals, for the C ggml consumers (
trellis2cpp,ggml-seethrough,nx-ggml). - chibifire/Pixal3D-Comfy: ComfyUI-shaped safetensors (
diffusion_models/,clip_vision/,vae/).
Provenance
- GGUF fork upstream: Aero-Ex/Pixal3D-GGUF, MIT.
- ComfyUI fork upstream: Comfy-Org/Pixal3D, MIT.
- Base weights: TencentARC/Pixal3D, which carries
extra_gated_eu_disallowed: true. Both repackagings sit downstream of that gate.
Use
hf download chibifire/Pixal3D-GGUF --local-dir Pixal3D-GGUF
hf download chibifire/Pixal3D-Comfy --local-dir Pixal3D-Comfy
Licence
MIT, as named in the header. See the MIT License terms. The forks follow their MIT upstreams, and the base weights keep the gate terms of TencentARC/Pixal3D.
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support