TenStrip

TenStrip / 10S-Comfy-nodes

Public

Vibe coded nodes for LTX2.3

16
1
100% credibility
Found May 07, 2026 at 16 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

Custom ComfyUI nodes that process video and audio latents from LTX 2.3 models to reduce motion artifacts and enable high-quality 30fps output from 24fps generations.

How It Works

1
😕 Spot motion problems

Your AI-generated videos show ghosting and blur on fast-moving parts when played at normal speed.

2
🔍 Discover 10S Nodes

You find these special tools made to smooth out jerky motions in LTX videos.

3
📥 Add to your studio

Simply place the tools into your AI video program's add-ons area and refresh.

4
🧩 Build the fix chain

Connect the sharpener, time stretcher, ghost fixer, and polisher nodes in sequence.

5
⚡ Run the magic

Start the process to sharpen edges, add smooth in-between frames, and blend perfectly.

6
🎵 Match the sound

Stretch the audio part to fit the new smoother pace without any glitches.

🎥 Enjoy smooth videos

Watch your crisp, natural 30fps videos play perfectly without blur or stutters.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 16 to 16 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 10S-Comfy-nodes?

10S-Comfy-nodes delivers custom Python nodes for ComfyUI, targeting LTX 2.3's audio-video latent pipeline to fix motion artifacts when upsampling from 24fps samples to 30fps output. It sharpens motion in latents, upsamples frames with retiming, stretches audio latents, and inpaints ghosted intermediates via a corrective sampler pass—all preserving LTX metadata for seamless decoding. Vibe coded nodes like these handle the baked-in 24fps priors without altering the core sampler.

Why is it gaining traction?

Unlike generic upscalers, these nodes chain into a precise workflow: sharpen before upsampling, auto-retime for natural pacing, and ghost-detect for targeted noise injection that locks real frames as anchors. Users notice crisper edges on fast objects, no phasing in audio, and artifact-free 30fps playback. The github vibe coding framework shines in quick LTX tweaks, with params like motion_thresh and ghost_sigma letting you dial quality without trial-and-error.

Who should use this?

ComfyUI power users generating LTX 2.3 videos who hit ghosting on 30fps exports. AI video artists fixing pacing in 10s clips, or vibe coding enthusiasts prototyping motion-heavy demos. Skip if you're not deep in LTX latents or prefer end-to-end models.

Verdict

Grab it for LTX 2.3 workflows—16 stars and 1.0% credibility reflect early days, but thorough docs and tested nodes make it production-ready for niche fixes. Test the full pipeline first; it's raw but effective.

(178 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.