Kim2091/AnimeSharpV2
By Kim2091 · ↓ 0 · ♥ 10 · Updated 2024-12-08
What's in this repo
This page lists the files in Kim2091/AnimeSharpV2, including 2x-AnimeSharpV2_ESRGAN_Soft_fp16.onnx, 2x-AnimeSharpV2_ESRGAN_Soft_fp32.onnx, 2x-AnimeSharpV2_MoSR_Sharp_fp16.onnx and more.
- 10 ONNX models (.onnx files)
- 17 files, including 10 .onnx, 5 .pth, 1 .md
- Last updated 2024-12-08
ONNX files
| File | Size | Download |
|---|---|---|
| 2x-AnimeSharpV2_ESRGAN_Soft_fp16.onnx | — | Download |
| 2x-AnimeSharpV2_ESRGAN_Soft_fp32.onnx | — | Download |
| 2x-AnimeSharpV2_MoSR_Sharp_fp16.onnx | — | Download |
| 2x-AnimeSharpV2_MoSR_Sharp_fp32.onnx | — | Download |
| 2x-AnimeSharpV2_MoSR_Soft_fp16.onnx | — | Download |
| 2x-AnimeSharpV2_MoSR_Soft_fp32.onnx | — | Download |
| 2x-AnimeSharpV2_RPLKSR_Sharp_fp16.onnx | — | Download |
| 2x-AnimeSharpV2_RPLKSR_Sharp_fp32.onnx | — | Download |
| 2x-AnimeSharpV2_RPLKSR_Soft_fp16.onnx | — | Download |
| 2x-AnimeSharpV2_RPLKSR_Soft_fp32.onnx | — | Download |
How to use
These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.
README
2x-AnimeSharpV2 Set
Scale: 2
Architecture: RealPLKSR, MoSR GPS, ESRGAN
Author: Kim2091
License: CC BY-NC-SA 4.0
Purpose: Anime
Subject:
Input Type: Images
Date: 10-3-24
Size:
I/O Channels: 3(RGB)->3(RGB)
Dataset: HFA2k modified
Dataset Size: 2-3k
OTF (on the fly augmentations): No
Pretrained Model: 4x_realplksr_mssim_pretrain & 4x-MoSR_GPS_Pretrain
Iterations: 100k & 75k
Batch Size: 6-10
GT Size: 64-256
Description: This is my first anime model in years. Hopefully you guys can find a good use-case for it. Included are 5 models:
- ESRGAN (Highest Quality, slowest)
- RealPLKSR (Higher quality, slower)
- MoSR (Lower quality, faster)
There are Sharp and Soft versions RPLSKR and MoSR, but only Soft for ESRGAN
When to use each:
- Sharp: For heavily degraded sources. Sharp models have issues depth of field but are best at removing artifacts
- Soft: For cleaner sources. Soft models preserve depth of field but may not remove other artifacts as well
Notes:
- MoSR doesn't work in chaiNNer currently
- To use MoSR:
- Use the ONNX version in tools like VideoJaNai
- Update spandrel in the latest version of ComfyUI
The ONNX version may produce slightly different results than the .pth version. If you have issues, try the .pth model.
Comparisons: https://slow.pics/c/4UI20Qlu
https://github.com/user-attachments/assets/001c0eb2-7558-4294-b722-a7371f87a912
Model info
Created: 2024-10-04
Updated: 2024-12-08
View on Hugging Face