RepoAlerts
SponsorGet alerts

Kablex/ComfyUI-Ref2VA-VSA

Get alerts like thisView on GitHubShare on X

Can I trust it?

Be careful with this one.

  • Stars from real accounts No data

    We haven't checked its stars for fakes yet.

  • Active OK

    Last change 3 days ago.

  • Licence Careful

    No licence: legally you can't reuse the code, unless the README says otherwise.

Quick checks from public data. They help, but they are no guarantee.

What it is

A ComfyUI custom node that applies a visual sparse attention patch to the MiniMax H3 reference-to-video (Ref2VA) model, keeping reference image and audio tokens dense while pruning generated-video tiles. The README reports about 72 s warm runs for a 5-second 1344x768 clip on an…

Who it's for

ComfyUI users running MiniMax H3 reference-to-video generation on 24GB NVIDIA GPUs

How to use it

Ask your AI to set it up

Paste this into Claude, ChatGPT or your coding assistant.

Help me install and set up Kablex/ComfyUI-Ref2VA-VSA in my project. Follow its README: https://github.com/Kablex/ComfyUI-Ref2VA-VSA. Explain each step and check it is safe before running anything.

Read the README

Star curve

831From 299 to 831 stars between 14 Sept 2026 and 20 Oct 2026.

Alternatives

Similar projects named in its profile. Each link searches the directory.

Get alerts for repos like this

We'll email you when something in Creative tools starts rising. Free, once a week, only what matches.

18,265 GitHub repos watched and ranked every hour. Figures as of 20 October 2026.

What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy

For maintainers

Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.

[![Kablex/ComfyUI-Ref2VA-VSA on RepoAlerts](https://repoalerts.com/badge/Kablex/ComfyUI-Ref2VA-VSA.svg)](https://repoalerts.com/repo/Kablex/ComfyUI-Ref2VA-VSA?ref=badge)
Share on X
  • jtydhr88/ComfyArt

    A browser-based design canvas that runs on a local ComfyUI server. It offers an infinite tldraw canvas, image, video, audio and 3D generation with local models, image editing tools, mockups, PPTX and

    Creative toolsTypeScript · 212 stars · +212 this week · 7 days old

  • hiroki-abe-58/ComfyUI-DBS

    A ComfyUI node pack that separates an audio soundtrack into music, sound effects and speech using the official Dynamic Band Splitting (DBS) models. It can remove or keep the dialogue of a video; the t

    Creative toolsPython · 40 stars · +40 this week · 2 days old

  • blendi-remade/prompt2rig

    Generates a short video clip from a text prompt using fal-hosted video models, estimates the human motion with GVHMR on a local GPU, and retargets it live onto a Mixamo rig in the browser, with GLB ex

    Creative toolsJavaScript · 83 stars · +83 this week · 1 day old

  • VAST-AI-Research/EdenLive

    Real-time generative renderer that turns a reference video from an interactive program into detailed frames, guided by a target first frame and a text prompt. Provides 5B and 14B model weights, stream

    Creative toolsPython · 261 stars · +198 this week · 9 days old

  • ashukae/ComfyUI-MangaScreen

    A ComfyUI node set that turns an image into a black-and-white manga page. Manga Finish separates lines, flattens values into paper, light, dark and solid black tones, and prints a single 45-degree hal

    Creative toolsPython · 148 stars · +148 this week · 6 days old

  • MaxLiu22/Motion2MixamoRig

    A command-line pipeline and Blender extension that extracts human motion from a single-person video or still photo and retargets it onto an Adobe Mixamo-rigged 3D character. Outputs preview videos and

    Creative toolsPython · 1,395 stars · +457 this week · 52 days old