Starstruk Logo MarkStarstruk

v0.3.50

Comfy-Org/ComfyUIv0.3.50Aug 13, 2025by github-actions[bot]

AI Summary

This release adds support for the Qwen Image model, introduces async API nodes, and fixes issues with multi-dimensional latents and AMD GPUs.

Key Highlights

  • Qwen Image model integration
  • Async API nodes
  • Fix for RepeatLatentBatch on multi-dim latents
  • Wan2.2 fun control support

New Features

  • Qwen Image model merging node
  • Async API nodes
  • Wan2.2 fun control support
  • gfx1201 bug fixes
  • torchaudio safety checks

Full Release Notes

## What's Changed
* Add Qwen Image model to readme. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/9191
* Qwen Image model merging node. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/9202
* qwenLora cannot load properly by @flybirdxx in https://github.com/comfyanonymous/ComfyUI/pull/9208
* Update template to 0.1.52 by @comfyui-wiki in https://github.com/comfyanonymous/ComfyUI/pull/9206
* Update frontend to v1.24.4 by @christian-byrne in https://github.com/comfyanonymous/ComfyUI/pull/9175
* Fix RepeatLatentBatch not working on multi dim latents. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/9227
* _ui.py import torchaudio safety check by @Kosinkadink in https://github.com/comfyanonymous/ComfyUI/pull/9234
* async API nodes  by @bigcat88 in https://github.com/comfyanonymous/ComfyUI/pull/9129
* Users report gfx1201 is buggy on flux with pytorch attention. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/9244
* Not sure if AMD actually support fp16 acc but it doesn't crash. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/9258
* Bump pytorch cuda and rocm versions in readme instructions. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/9273
* Only show feature flags log when verbose. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/9281
* remove creation of non-used asyncio_loop by @bigcat88 in https://github.com/comfyanonymous/ComfyUI/pull/9284
* Update template & embedded docs by @comfyui-wiki in https://github.com/comfyanonymous/ComfyUI/pull/9283
* Support SimpleTuner lycoris lora for Qwen-Image by @PsychoLogicAu in https://github.com/comfyanonymous/ComfyUI/pull/9280
* fix(Kling Image API Node): do not pass "image_type" when no image by @bigcat88 in https://github.com/comfyanonymous/ComfyUI/pull/9271
* Update template to 0.1.58 by @comfyui-wiki in https://github.com/comfyanonymous/ComfyUI/pull/9302
* Update test release package workflow with python 3.13 cu129. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/9306
* Wan2.2 fun control support. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/9292
* Make torchaudio exception catching less specific by @Kosinkadink in https://github.com/comfyanonymous/ComfyUI/pull/9309
* Update template to 0.1.59 by @comfyui-wiki in https://github.com/comfyanonymous/ComfyUI/pull/9313
* Update release workflow to python3.13 pytorch cu129 by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/9315
* Downgrade frontend for release. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/9316

## New Contributors
* @flybirdxx made their first contribution in https://github.com/comfyanonymous/ComfyUI/pull/9208

**Full Changelog**: https://github.com/comfyanonymous/ComfyUI/compare/v0.3.49...v0.3.50