---
license: cc-by-nc-sa-4.0
pipeline_tag: image-to-image
tags:
- pytorch
- super-resolution
---
---
@News 

## 2x-AnimeSharpV3

**Scale:** 2

**Architecture:** ESRGAN

**Links:** [Github Release](<https://github.com/Kim2091/Kim2091-Models/releases/tag/2x-AnimeSharpV3>)


**Author:** Kim2091

**License:** CC BY-NC-SA 4.0

**Purpose:** Anime

**Subject:** 

**Input Type:** Images

**Date:** 10-24-24

**Size:** 

**I/O Channels:** 3(RGB)->3(RGB)


**Dataset:** ModernAnimation1080_v3

**Dataset Size:** 2-3k

**OTF (on the fly augmentations):** No

**Pretrained Model:** 4xESRGAN

**Iterations:** 140k

**Batch Size:** 8

**GT Size:** 64-128


**Description:** I gave up on having multiple architectures. This release is ESRGAN only, and provides superior quality compared to AnimeSharpV2 in nearly every scenario. It has most of the advantages of the old V2 Sharp models, while not having issues with depth of field. 


__Comparisons:__ <https://slow.pics/c/A2BRSa0U>


![image/png](https://cdn-uploads.huggingface.co/production/uploads/64987486f436b85fddbdc359/ihjsIOB2G5GDdiCrdpygG.png)