# ESRGAN Upscaler

Canonical page: https://fuser.studio/models/esrgan-upscaler

ESRGAN Upscaler in Fuser enlarges images 2x or 4x with Standard, Anime and V3 models. Run it after generation to prepare assets for print or web.

## Specs

| Spec | Value |
| --- | --- |
| Versions | Standard (4x upscaling), Standard (2x upscaling), Anime (4x upscaling), ESRGAN Upscaler V3 (4x upscaling), WDN V3 (4x upscaling), Anime V3 (4x upscaling) |
| Inputs | Image |
| Output | image |
| Cost | 2 credits per run |

Eliminate compression noise and restore crisp edges across illustrations, textures, and archival scans without altering original colors

Creator: Tencent ARC

Also known as: Real-ESRGAN

[Upscale your images](https://app.fuser.studio)

## How ESRGAN Upscaler works

From standard JPEG cleanups to high-ratio archival scaling, configure model architectures, tiling thresholds, and facial reconstruction in three straightforward steps.

### Upload source image

Select any compressed photo, concept art render, or 2D illustration up to 8x scale.

### Choose network model

Select the specialized anime, wide-denoise, or general photographic model and toggle face enhancement.

### Export clean resolution

Download your artifact-free PNG or JPEG output with sharp boundaries and preserved source lighting.

## What ESRGAN Upscaler is good at

Built on a residual-in-residual dense network, Real-ESRGAN delivers non-generative super-resolution with specialized sub-models for anime, denoising, and human faces.

### Dedicated Anime Architecture

The lightweight 6-block anime model eliminates ringing halos and compression noise while preserving razor-sharp contour line-art and pure flat fills.

### Real-World Denoising

The Wide Denoise pipeline cleans sensor noise and heavy JPEG blocking from vintage photos and low-light captures without blurring delicate micro-textures.

### Blind Face Reconstruction

Toggle facial restoration to automatically detect and reconstruct eyes, teeth, and skin fidelity in blurry historical portraits and group photographs.

### Configurable Tiling and Scaling

Scale images from 1x to 8x with Lanczos interpolation and configure tile sizes between 200 and 800 to eliminate GPU memory limits on high-resolution graphics.

## Made with ESRGAN Upscaler

Explore how diverse creative disciplines leverage super-resolution to sharpen product geometries, clean illustrative linework, and restore vintage archival slides.

### High-contrast cinematic still with restored dust and chrome detail

### Macro product footwear with crisp material edges

### Architectural staircase geometry with crisp shadow definition

### Dynamic action capture with frozen water spray droplets

### Archival studio console with sharp dial markings and cable details

## What people build with ESRGAN Upscaler

From game asset designers and digital comic publishers to print production artists, see how creators use deterministic upscaling across their pipelines.

### Game Texture Upscaling

Upscale environment textures, UI icons, and 3D asset maps up to 8x resolution without introducing diffusion hallucinations or shifting native diffuse color maps.

### Anime and Webtoon Publishing

Clean scan artifacts and upscale digital comic panels with the specialized 6-block anime model, keeping ink outlines needle-sharp and flat color fills pristine.

### Archival Photo Restoration

Reclaim lost detail from vintage family photos, scanned slides, and heavily compressed historical JPEGs using wide-denoising and blind facial restoration.

### E-Commerce Asset Enhancement

Upscale marketplace product shots and catalog assets to crisp 4K fidelity, eliminating compression blur while keeping typography and stitch details true to life.

### Fashion Campaign Prep

Prepare AI-generated concept portraits and high-fashion lookbooks for large-format print by removing pixelation and enhancing facial features seamlessly.

## Frequently Asked Questions

### What is Real-ESRGAN and how does it differ from original ESRGAN?

Real-ESRGAN is an enhanced super-resolution framework developed by Tencent ARC that models complex real-world corruptions like sensor blur, camera noise, and JPEG degradation. While the original ESRGAN was trained on clean, synthetically downsampled images, Real-ESRGAN uses a multi-stage degradation pipeline to reliably restore real-world degraded photos and digital graphics.

### Which sub-model should I choose for my images?

Choose the sub-model that matches your subject material: use RealESRGAN_x4plus as the standard default for general photography and natural scenery, RealESRGAN_x4_wdn_v3 for images with heavy sensor noise or JPEG compression blocks, and RealESRGAN_x4plus_anime_6B or RealESRGAN_x4_anime_v3 for 2D illustrations, manga, and line-art to prevent unwanted photo textures.

### How does Real-ESRGAN differ from diffusion-based upscalers?

Real-ESRGAN is a structural, non-generative upscaler that preserves the exact layout, colors, and identity of the original image without hallucinating new visual elements. Diffusion upscalers creatively synthesize intricate new micro-details (like skin pores or textile weaves), whereas Real-ESRGAN focuses purely on sharpening existing edges, eliminating compression blocks, and preserving source fidelity.

### When should I enable the face enhancement option?

Enable face enhancement whenever your source contains human faces, portraits, or group photos. This activates an integrated face restoration model (such as GFPGAN) that specifically reconstructs realistic eyes, teeth, and skin textures. Keep this option disabled for anime characters, stylized cartoons, or non-human subjects to avoid awkward realistic distortions.

### How do I prevent out-of-memory errors on large images?

Set the tile size parameter between 200 and 400 when processing high-resolution sources. While leaving the tile size at 0 processes images in a single unified GPU pass for optimal speed, enabling tiling divides larger compositions into manageable chunks to prevent memory limits.

### What types of images should I avoid running through Real-ESRGAN?

Avoid using Real-ESRGAN when you require newly hallucinated photorealistic textures or when upscaling complex typographic logos. The underlying network can introduce subtle organic waviness to perfectly straight font vectors, and it will not generate complex new textures that were absent in the source.

## Try ESRGAN Upscaler on Fuser

Eliminate compression noise and restore crisp edges across illustrations, textures, and archival scans without altering original colors

[Upscale your images](https://app.fuser.studio)

## Related models

- [Gemini Image](https://fuser.studio/models/gemini-image.md)
- [GPT Image](https://fuser.studio/models/gpt-image.md)
- [Seedream](https://fuser.studio/models/seedream.md)
- [FLUX.3 Image](https://fuser.studio/models/flux-3-image.md)
- [FLUX.2](https://fuser.studio/models/flux-2.md)
- [Topaz Image Upscale](https://fuser.studio/models/topaz-image-upscale.md)

Node reference: [ESRGAN Upscaler docs](https://docs.fuser.studio/docs/nodes/image/esrgan-upscaler.md)

## More articles

- [AI Image Generation Glossary: 31 Terms Explained](https://fuser.studio/articles/ai-image-generation-glossary.md)
- [Best AI Upscalers for Images and Video (2026)](https://fuser.studio/articles/best-ai-upscalers.md)