v0.3.49

Comfy-Org/ComfyUIv0.3.49Aug 5, 2025by github-actions[bot]

AI Summary

Focuses on device placement accuracy and introduces initial support for the Qwen Image model alongside a new Veo3 video generation node.

Key Highlights

Initial support for qwen image model
Device placement fixes (conds and context)
Veo3 video generation node with audio support
Fix for broken controlnet

New Features

Veo3 video generation node
Qwen Image model support
Fix for qwen default shift and latent size
Fix for broken controlnet

Full Release Notes

## What's Changed
* API for Recently Used Items by @Myestery in https://github.com/comfyanonymous/ComfyUI/pull/8792
* Update template to 0.1.47 by @comfyui-wiki in https://github.com/comfyanonymous/ComfyUI/pull/9153
* Make sure all the conds are on the right device. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/9151
* Make sure context is on the right device. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/9154
* Cleanup. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/9160
* Lower cond vram use by casting at the same time as device transfer. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/9159
* Fix broken controlnet from last PR. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/9167
* Various fixes for broken things from earlier PR. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/9168
* Add some warnings and prevent crash when cond devices don't match. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/9169
* Fix another issue with the PR. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/9170
* Initial support for qwen image model. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/9179
* Add Veo3 video generation node with audio support by @christian-byrne in https://github.com/comfyanonymous/ComfyUI/pull/9110
* Update template to 0.1.48 by @comfyui-wiki in https://github.com/comfyanonymous/ComfyUI/pull/9182
* Fix default shift and any latent size for qwen image model. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/9186
* Update template to 0.1.51 by @comfyui-wiki in https://github.com/comfyanonymous/ComfyUI/pull/9187

## New Contributors
* @Myestery made their first contribution in https://github.com/comfyanonymous/ComfyUI/pull/8792

**Full Changelog**: https://github.com/comfyanonymous/ComfyUI/compare/v0.3.48...v0.3.49