How AI Per-Frame Style Transfer Works
Apply a style transfer per-frame with seed-locking for temporal coherence. Experimental — 15 s/frame at 512 px.
Try it free →Step-by-step process
- 1
Add your video
Drop or select the video you want to process — it stays on your device.
- 2
Run the model in-browser
AI Per-Frame Style Transfer loads its model (~2.1 GB) once, caches it, then runs locally in a worker. No upload.
- 3
Download the video
Preview the result and download the video. Re-run with different settings anytime.
Frequently asked questions
Is it flicker-free?
Recipes are applied consistently per frame; temporal smoothing keeps the look stable.
Is it free to use?
Yes — AI Per-Frame Style Transfer is completely free. No account, no watermark, no credits, and no usage limits.
Do my files or prompts ever leave my device?
No. Everything runs locally in your browser via WebAssembly/WebGPU — there is no server that receives your files, prompts, or results.
Which browser and hardware do I need?
A modern browser. Chrome and Edge get WebGPU acceleration for the fastest results; Firefox and Safari run via WebAssembly. The model (~2.1 GB) downloads once, then is cached for offline use.
Can I use the results commercially?
Yes. You own everything you create — NSS makes no claim to the images, videos, or text you process or export.
Does it work on mobile?
Lightweight tools run on phones; heavier models prefer a desktop with a GPU. The tool picks the best path for your device and falls back gracefully where needed.
Where can I see a step-by-step guide?
Yes — there is a full walkthrough at /how-it-works/ai-video-style.