Anime & Illustration Upscaler

AI-powered 2x/4x upscale for anime, manga, and illustrations — runs entirely in your browser. No upload, no account, no watermark.

🔒 100% Private ✦ No Watermark ⚡ WebGL Accelerated 📥 PNG & JPEG Export 🆓 Completely Free
🖼️
Drop an image here
JPG · PNG · WebP — anime, manga, illustrations, line art
Browse files
Content type — choose for best defaults
1
Loading AI model…
How it works

This tool uses ESRGAN (Enhanced Super-Resolution Generative Adversarial Network) in the lightweight RDN-slim variant, run via TensorFlow.js with WebGL acceleration. Your image never leaves your browser tab.

1 Select image Drop or browse a JPG/PNG/WebP. The file is decoded locally into a pixel buffer — nothing is sent to any server.
2 Choose a preset Pick a content type (Anime, Manga, Digital Art, Line Art, or Screenshot) to auto-configure optimal denoise and sharpening defaults for that style.
3 Noise reduction pre-pass A two-pass box blur (horizontal + vertical) smooths JPEG compression artefacts before the AI sees the image, preventing blocky noise from being amplified during upscaling.
4 AI upscale (ESRGAN) The model processes your image in 64-pixel tiles via WebGL. Each tile passes through a deep convolutional network trained on illustration datasets, recovering sharp edges and fine detail at 2× or 4× resolution.
5 Post-sharpening An optional unsharp-mask pass (levels 1–3) boosts perceived sharpness of the upscaled output, especially effective on line art and text.
6 Export Download as lossless PNG or JPEG at your chosen quality (60–100). Copy to clipboard is also available. No watermark is added.
Recommended settings by content type
Content Scale Denoise Sharpen Why
Anime / Cel 1 – Light 1 Clean gradients; light smooth prevents haloing
Manga Scan 2 – Medium 0 Screentone patterns amplify with sharpen off
Digital Art 0 – Off 1 Keep original grain; sharpen recovers line crispness
Line Art 0 – Off 2 Fast pass + strong sharpen brings out ink edges
Screenshot 1 – Light 0 Font antialiasing benefits from light smooth
Frequently asked questions
Does this upload my image to a server?
No. All processing happens inside your browser tab using WebGL-accelerated TensorFlow.js. Your image is never sent anywhere. You can verify this by turning off Wi-Fi after the page loads — the upscaler continues to work because both the AI model and your image are local. No analytics or pixel data are collected.
What is the difference between 2× and 4× upscaling?
2× doubles each dimension: a 512×512 image becomes 1024×1024 (4× the pixel count). 4× quadruples: 512×512 becomes 2048×2048 (16× the pixel count). 4× gives the best visible improvement but takes longer and produces a larger file. Use 2× for quick previews, line art, or screenshots where extreme enlargement is not needed.
What does the noise reduction level do exactly?
Before upscaling, a two-pass box blur (horizontal then vertical) smooths compression artefacts — the blocky JPEG noise common in low-quality scans and screenshots. Level 0 = off (preserves original texture). Level 1 = radius 1 px, ideal for clean digital art. Level 2 = radius 2 px, good for typical JPEG-saved fan art or manga scans. Level 3 = radius 3 px, best for heavily compressed or screentone-heavy pages where the AI would otherwise amplify the pattern noise. Higher levels trade a small amount of fine detail for cleaner edge upscaling.
What does post-sharpening do, and should I use it?
After ESRGAN upscales the image, an unsharp mask pass increases perceived edge contrast. Level 0 = off. Level 1 = subtle (safe for all anime/illustrations). Level 2 = medium, recommended for line art or pencil work. Level 3 = strong, best for very soft or blurry source images. Avoid sharpening on manga scans — it amplifies screentone dots into harsh patterns.
Should I export as PNG or JPEG?
PNG is lossless — ideal for images you plan to edit further or that have transparent backgrounds (note: transparency is flattened to white in this tool). JPEG at quality 90+ looks indistinguishable from PNG at a fraction of the file size, and is a better choice for sharing on social media or embedding in web pages. Quality 92 is a good default; go lower only if file size is a hard constraint.
Why does the first run take longer?
On the first upscale the browser compiles the ESRGAN model shaders for your GPU. Subsequent runs in the same session are faster because the compiled shaders are cached. The model weights (~880 KB per scale) are also cached by your browser after the first download, so reloading the page is fast.
What image sizes are supported?
There is no hard size limit, but very large images (over 2000×2000 px at 4× scale) can take several minutes and may cause the browser tab to run out of GPU memory on low-end devices. For best performance, upscale images under 1000×1000 px at 4×, or under 2000×2000 px at 2×. If processing fails, try reducing the source image first.