ComfyUI 0.36 learns to join clips, loop, and edit video with Flux
Release notesComfyUI 0.36.0 release notes on GitHub

ComfyUI 0.36.0, released on 15 September, is mostly about what happens to a clip after it is generated.
In the core: Video Concatenate and Generic Loops
Video Concatenate joins clips end to end inside a workflow. Generic Loops adds a Start Loop and an End Loop node: the part of the graph between them runs a set number of times or once per item in a list, so one treatment can run over a batch of clips instead of being wired up once per clip.
Partner nodes for editing
The hosted side grows: BFL Flux Video Edit changes existing footage from a text instruction; Bria brings an image editor and a Video Eraser for removing objects; Pruna P-Video-2 adds text-to-video and image-to-video. The release also adds MAI Image 2.6 through OpenRouter and Gemini 3.8 Flash.
MiniMax H3 and more
MiniMax's open H3 video model gets further VAE optimisations that cut its memory use, and a fix for its fun-ControlNet. Outside video, the release adds the Yue2 music model and Marigold v2, with frontend 1.52.7 and templates 0.11.62.
ComfyUI 0.36 learns to join clips, loop, and edit video with Flux: questions
What is new in ComfyUI 0.36?
A core Video Concatenate node, Generic Loops, and partner nodes for BFL Flux Video Edit, Bria's image editor and Video Eraser, Pruna P-Video-2, MAI Image 2.6 and Gemini 3.8 Flash. It was released on 15 September 2026.
Source: ComfyUI on GitHub checked against the source
More AI video news

ComfyUI 0.38: Seedance drafts, H3 ControlNet
ComfyUI 0.38 brings Fun-ControlNet-Union 2.0 to MiniMax H3, a Draft mode for ByteDance's Seedance 2.5, film colour spaces for grading and a lighter install — and drops its Sora nodes now that OpenAI's AI video API is gone.

ComfyUI 0.32: LTX-2.5 and Grok Imagine
ComfyUI 0.32 shipped on 11 August with support for LTX-2.5, Lightricks' new open AI video model, partner nodes for Grok Imagine Image 2.0 and Qwen-Image 3.0 Pro, and a higher minimum PyTorch.

LTX-2.5 is out, with open weights
Lightricks released LTX-2.5 on 11 August: a 22-billion-parameter open-weights AI video model that generates sound with the picture, cuts between shots in one clip and upscales to 3840×2176. It ran in ComfyUI on day one.