---
license: mit
pipeline_tag: image-to-image
library_name: pytorch
tags:
  - computer-vision
  - image-to-image
  - image-restoration
  - image-enhancement
  - super-resolution
  - comfyui
  - pytorch
  - swinir
  - swinfir
  - transformer
  - anime-upscale
---

# SnJake Anime Upscale

A **experimental** lightweight upscaler (x2) for anime/illustration images. Designed for clean, sharp results with minimal artifacts. V2 is slightly sharper and removes edge noise artifacts.

![Baikal Swin Anime](https://cdn-uploads.huggingface.co/production/uploads/658814fd586088fd274d8cc1/R3AU887ILEP5o6a_4NIPj.png)

## Examples


![Comparison_1](https://cdn-uploads.huggingface.co/production/uploads/658814fd586088fd274d8cc1/b7BWEDHPCWlk-83nQ0NEL.png)


![Comparison_2](https://cdn-uploads.huggingface.co/production/uploads/658814fd586088fd274d8cc1/rdxxhjXDpH786kSmgE60z.png)

![Comparison_3](https://cdn-uploads.huggingface.co/production/uploads/658814fd586088fd274d8cc1/KqfRD0Dk3miTVmISPJTZF.png)

# How to use in ComfyUI

The model is designed to work with the **SnJake Anime Upscale** ComfyUI node.

1. Install the node from [GITHUB REPO](https://github.com/SnJake/SnJake_Baikal_Swin_Anime).
2. Download the weights from this repository.
3. Place the file(s) into `ComfyUI/models/anime_upscale/`.
4. Select the weights in the node dropdown and run the workflow.

# Training Details
V1:
- Dataset: 40,000 images from Danbooru2024: https://huggingface.co/datasets/deepghs/danbooru2024
- Validation: 600 images
- Epochs: 70

V2: 
- Slightly sharper output, no edge noise artifacts.
- Epochs: 20
- Dataset: 49,606 images from Danbooru2024: https://huggingface.co/datasets/deepghs/danbooru2024
- Perceptual backbone: Custom SimSiam pre-trained convnextv2_tiny (Experimental)
- Loss schedule: gradual ramp‑in of perceptual/auxiliary losses for stable training.

V2.1:
- Removed Nearest from resample_methods
- Epochs: 30

V2.2:
- Epochs: 40 (For now)

V3 (SwinFIR):
- Epochs: Stage 1 - 20; Stage 2 - 18
- Perceptual backbone: Custom SimSiam pre-trained convnextv2_base (Experimental).
- Dataset: ~50,000 images from Danbooru2024: https://huggingface.co/datasets/deepghs/danbooru2024

V3.1 (Current Best - SwinFIR): 🏆
- Epochs: Stage 1 (Charbonnier) - 20; Stage 2 (GAN Fine-tuning) - 16.
- Perceptual backbone: Reverted to the robust ImageNet-pretrained convnextv2_base.fcmae_ft_in22k_in1k for superior high-frequency feature extraction.
- Dataset: ~50,000 images from Danbooru2024: https://huggingface.co/datasets/deepghs/danbooru2024
 
Training code is included in `training_code/` for reference.

## Disclaimer

This project was made purely for curiosity and personal interest. The code was written by GPT-5.2 Codex.