Pixal3D-Comfy

Pixal3D model files repackaged for ComfyUI, in the ComfyUI models folder layout.

What it is for

This repo holds the Pixal3D weights repackaged as single safetensors files for ComfyUI. It has standard and multiview diffusion models in bf16 and int8 form, a DINO vision encoder, and the TRELLIS.2 shape and texture VAEs. The folders match the ComfyUI models subfolders, so a download drops into place. It also holds a JSON test file.

Provenance

Upstream model: TencentARC/Pixal3D, the base_model in the header.

Use

hf download chibifire/Pixal3D-Comfy --local-dir ComfyUI/models --include "diffusion_models/*" "clip_vision/*" "vae/*"

This puts the diffusion models in models/diffusion_models, the vision encoder in models/clip_vision and the VAEs in models/vae. For model details, read the upstream model card.

Licence

MIT, the upstream licence. Terms: https://opensource.org/license/mit.

Downloads last month: 103

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for chibifire/Pixal3D-Comfy

Base model

TencentARC/Pixal3D

Finetuned

(4)

this model