AIMZ-GFX

AIMZ-GFX / ComfyUI-FlowDenoise

Public

Professional motion-compensated temporal video denoising for ComfyUI ? AIMZ GFX Division

19
2
100% credibility
Found Apr 09, 2026 at 19 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

ComfyUI-FlowDenoise is a custom node pack for ComfyUI that denoises videos by aligning frames with motion tracking and selectively reducing color and brightness noise.

How It Works

1
🔍 Discover the tool

You find a helpful add-on for cleaning up shaky, flickery videos made by AI generators while browsing video editing tips.

2
🛠️ Add it easily

Search for it in your ComfyUI tool manager and install with a single click, no hassle.

3
📹 Load your video

Pick the noisy video clip you want to smooth out and bring it into your workspace.

4
✨ Smooth the motion

The tool aligns moving parts across frames and blends them gently to erase jitter and noise, feeling like magic.

5
👀 Preview the fixes

Peek at the removed noise, like color sparks or grain, to see exactly what's being cleaned.

6
🎨 Tune the cleanup

Slide controls to decide how much to fix colors versus brightness for a natural look.

✅ Enjoy clean video

Export your now smooth, professional video ready to share, with no more annoying flickers.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 19 to 19 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is ComfyUI-FlowDenoise?

ComfyUI-FlowDenoise is a Python extension for ComfyUI that delivers professional motion-compensated temporal video denoising from the AIMZ GFX Division's GitHub account. It aligns neighboring frames using optical flow models like MEMFOF or RAFT, then averages them into a clean reference while detecting scene changes to avoid artifacts. Users get separate chroma and luma noise extraction with independent strength controls across YCbCr, HSV, or LAB color spaces, perfect for scrubbing AI video flicker and spikes.

Why is it gaining traction?

Its batched high-VRAM processing and noise visualization modes (heatmap, signed, grayscale) make tuning straightforward without guesswork. Scene-aware averaging and per-channel blending stand out over basic filters, delivering crisp results on AI-generated footage. The professional GitHub README with workflow examples and install via ComfyUI-Manager lowers the entry barrier for video pros.

Who should use this?

ComfyUI users denoising AI videos from Kling or Seedance, where chroma flicker kills quality. Video editors chaining VHS nodes for temporal cleanup on high-res clips. GFX artists in AIMZ-style divisions needing flowdenoise precision without retraining models.

Verdict

Solid for targeted ComfyUI video denoising if you match the recommended settings—install and test on your artifacts. At 19 stars and 1.0% credibility score, it's early but backed by a professional GitHub profile; watch for updates as adoption grows.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.