Skip to main content
← Back to news

ComfyUI v0.45.0: Qwen 3.x performance, video input and two new image models

Tools & releases
Source:Comfy-Org
ComfyUI ships v0.45.0: the fourth part of its Qwen 3.x performance work (combined parallel linear weights), video input support for Qwen 3.x, and two new models, RelayVSR and WeVisOne-VL, among many partner nodes in the release.

Get the next local-AI briefing

Once a week, the top selection from iaLocale: articles, news and resources on local AI, and more.

After signing up you receive a confirmation email (double opt-in). Without confirmation we send nothing. No spam, we promise.