Type | |
Stats | 1,441 4,830 |
Reviews | (207) |
Published | Mar 22, 2024 |
Base Model | |
Training | Steps: 10,000 Epochs: 2 |
Usage Tips | Clip Skip: 1 Strength: 1 |
Hash | AutoV2 9BEC875B66 |
If you like more manga-like art styles, then this LoRA is for you.
Since meme50 is mainly an NSFW artist, the model does best with NSFW images, but is also able to generate SFW images.
If you like the LoRA, please leave a reaction, review and/or tip. Enjoy!
Usage
No activation/trigger needed. Simply include the LoRA in the prompt.
Recommended to use at strength 0.8 - 1.0
Use Clip skip=1 or Clip skip=2 (other values may also work, use at own risk).
Works best at 1024x1024. Struggles to get the style right at lower resolutions.
Generally no VAE needed. Use one according to your preferences and image contents.
Example
See preview images (generated with pruned version).
Unpruned vs. Pruned vs. Lite
I offer three variations of the model, which only differ in the file size and quality. Pick the one that best suits your preferences. If you cannot decide, simply pick the "pruned" version. Note that the quality is relative, even the lite version usually produces images which closely resemble the intended art style.
unpruned: The originally trained model. Largest file size, best quality. Pick if you want the best possible quality, at the cost of disk space.
pruned: Downsized model. Almost same quality as the unpruned version, with noticably smaller file size.
lite: Drastically downsized model. Smallest file size. Still has good quality, but noticeably worse than unpruned and pruned.
Notes
meme50 truly is one of the GOATs for h-manga. Even though it is hard to find good, colored art, the LoRA turned out pretty well. It does not quite have the "pencil drawn" look I expected, but that's probably because their colored images usually don't have that look. I'm still happy with the results though.
Maybe I'll make a version in the future where I mix in some manga panels and test how that will affect the style and quality.
Using training data
Feel free to contact me if you want access to the training data.
The training data (images and tags) have been mostly sourced from rule34.xxx and other images boards. They have been cleaned up manually by me. When using the training data or modified versions of it to create models or datasets, please credit both me and the original artist as appropriate.
Disclaimer
This LoRA is not affiliated with the artist it is based on. If you like the art style, please support the original artist:
They also make doujins, so a good way of supporting them is by buying one of their doujins from an official source