Upscale video on your own hardware. The real-time tier uses GPU shaders and works even on integrated graphics; the AI tier re-encodes frame by frame with a neural network and honestly reports that it runs slower than playback. Nothing is uploaded either way.
How it works
- Drop an image or video, or many images, or a ZIP, for a batch.
- Pick the scale and tier. The estimate tells you how long an export will take before you commit.
- Download the enlarged result, or the whole batch as a ZIP.
Questions
- Does my file get uploaded?
- No. The models and all processing run inside your browser on your own device. You can verify this yourself: open your browser’s DevTools, watch the Network tab, and process a file: there are no uploads. After the first visit most tools also work fully offline.
- What do the quality tiers mean?
- Fast is Lanczos resampling — not AI at all, instant, and nothing to download. Better is a tiny trained network (~14 KB) that runs as a shader, so it is quick enough for video. Best is Real-ESRGAN compact, a 5 MB model that takes tens of seconds per image and is the right answer for most photos, and the only AI tier that is practical on video. The model downloads once and is then cached for offline use.
- Does it work on old or blurry photos?
- Upscaling sharpens edges and adds plausible detail, and a source the tool measures as compressed is routed to a denoising model so its JPEG blocks are cleaned rather than sharpened. It cannot recover detail that was never captured, so faces enlarged from very small sizes will look smoothed, not restored.