SnJake/Baikal-Swin-Anime

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.

Examples

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.
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 (For now)
• Dataset: 49,606 images from Danbooru2024: https://huggingface.co/datasets/deepghs/danbooru2024
• Perceptual backbone: convnextv2_tiny.fcmae_ft_in22k_in1k, fine‑tuned on anime to improve feature sensitivity.
• Loss schedule: gradual ramp‑in of perceptual/auxiliary losses for stable training.

V2.1:

• Removed Nearest from resample_methods
• Epochs: 30 (For now)

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.