Type | |
Stats | 99 8 |
Reviews | (21) |
Published | Jul 23, 2024 |
Base Model | |
Training | Steps: 3,200 Epochs: 50 |
Usage Tips | Clip Skip: 1 Strength: 1 |
Hash | AutoV2 BC9D1F4114 |
![default creator card background decoration](/images/civitai-default-account-bg.png)
Please, check the description, there is a little bit of useful information.
Inеtroduction:
This LoRA is supposed to represent YanWan's artstyle.
Try not to use negative embeddings (textual inversions) with any style LoRA on SD 1.5 models.
Try not to use any "scores" with this style LoRA on PonyDiffusion-based models.
Make sure you're using "monochrome" in negatives on Pony-Diffusion-based models.
Artist has an extremely limited dataset, there is a lot of repeated characters on his art, so, some chars (especially, from cartoons), may fail a bit. In terms on style. Thanks for attention!
Compatibility (Pony):
Humans: great
Anthros: good
Ponies: good
Multiple characters: good
Character LoRAs; good
Unique characters: varies
Recommendations (Pony):
1.0 emphasis
Clip Skip 1
AutismMix - Pony for generations
score_9
as quality tag, nothing moremonochrome
in negativesBest result on simple background tag
Some characters or tags may have a lot of emphasis towards their own style, so, this LoRA may work not so good with those tags.
Recommendations (SD 1.5):
1.0 emphasis
Clip Skip 2
Best result on simple background tag
Credits:
Trained on NAI Anime Full. Dataset of 100 pictures. 20 Epochs. Clip Skip - 2. SD 1.5.
Trained on PonyDiffusionXL. Dataset of 64 pictures. 50 Epochs. Clip Skip - 1. PonyXL.
Really big thanks to:
eyangong for beautiful artwork
Some good folks from Discord server
You, for reading, downloading and reviewing this LoRA