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
chibifire/pixal3d
Pointer repo. Pixal3D is TRELLIS.2's implementation (see workspace memory pixal3d-is-trellis2-implementation); the actual weight forks live under distinct chibifire repos matching upstream shape:
- chibifire/Pixal3D-GGUF โ Q4/Q5/Q6/Q8 GGUF + bf16 originals. Matches the workspace's C-ggml consumers (
trellis2cpp,ggml-seethrough,nx-ggml). Upstream:Aero-Ex/Pixal3D-GGUFunder MIT. - chibifire/Pixal3D-Comfy โ ComfyUI-shaped safetensors (
diffusion_models/,clip_vision/,vae/). Upstream:Comfy-Org/Pixal3Dunder MIT.
This lowercase repo is retained as a redirect target because chibifire/pixal3d was previously referenced. New consumers should point at one of the shape-matched forks above instead.
Upstream base weights (TencentARC/Pixal3D) carry extra_gated_eu_disallowed: true. The GGUF and ComfyUI repackagings above sit downstream of that gate.
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support