v0.3.70

Comfy-Org/ComfyUIv0.3.70Nov 19, 2025by github-actions[bot]

AI Summary

Focuses on hardware support for CUDA 12.6 and bug fixes for specific AI models like Hunyuan 3D and EasyCache channel handling.

Key Highlights

Added release workflow for NVIDIA cu126
Fixed EasyCache mismatch in input/output channels
Fixed Hunyuan 3D 2.0
Added new Gemini models to API nodes

New Features

New Gemini models in API nodes

Full Release Notes

## What's Changed
* Add release workflow for NVIDIA cu126 by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/10777
* Update README with new portable download link by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/10778
* Fix the portable download link for CUDA 12.6 by @comfyui-wiki in https://github.com/comfyanonymous/ComfyUI/pull/10780
* Native block swap custom nodes considered harmful. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/10783
* [API nodes]: adjusted PR template; set min python version for pylint to 3.10 by @bigcat88 in https://github.com/comfyanonymous/ComfyUI/pull/10787
* EasyCache: Fix for mismatch in input/output channels with some models by @kijai in https://github.com/comfyanonymous/ComfyUI/pull/10788
* Fix hunyuan 3d 2.0 by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/10792
* feat(api-nodes): add new Gemini models by @bigcat88 in https://github.com/comfyanonymous/ComfyUI/pull/10789


**Full Changelog**: https://github.com/comfyanonymous/ComfyUI/compare/v0.3.69...v0.3.70