v0.8.1

Comfy-Org/ComfyUIv0.8.1Jan 8, 2026by github-actions[bot]

AI Summary

Fixes stable release workflow issues and introduces support for Gemma 12B quantized weights while improving LTXV text encoder efficiency.

Key Highlights

Gemma 12B with quant weights support
LTXAV Text Encoder device selection
FP8MM performance fix
Warning for old PyTorch versions

New Features

Gemma 12B with quant weights support
Device selection for LTXAVTextEncoderLoader

Full Release Notes

## What's Changed
* Fix stable release workflow not pulling latest comfy kitchen. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/11695
* Support gemma 12B with quant weights. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/11696
* model_patcher: Remove confusing load stat by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/11710
* Add device selection for LTXAVTextEncoderLoader by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/11700
* Lower ltxv text encoder vram use. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/11713
* Bump required comfy-kitchen version. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/11714
* Increase ltxav mem estimation by a bit. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/11715
* Add memory estimation function to ltxav text encoder. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/11716
* ops: Fix offloading with FP8MM performance by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/11697
* Add warning for old pytorch and comfy kitchen. Update your pytorch to cu130 to get a performance boost. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/11718
* Update template to 0.7.69 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/11719


**Full Changelog**: https://github.com/Comfy-Org/ComfyUI/compare/v0.8.0...v0.8.1