Kohaku XL alpha
An anime SDXL model trained on 100kπ images.
Introduction
This model is trained from sdxl-1.0-base and merged with some other anime models to get optimal result.
I'm planing more training on more images (around 1.6M imgs) and some style lycoris models. so now it is just alpha version.
Usage Details
This model is very flexible on resolution, you can use the resolution you used in sd1.x/2.x to get normal result(like 512x768), you can also use the resolution that is more native for sdxl(like 896*1280) or even bigger (1024x1536 also ok for t2i).
recommended negative prompt for anime style:photorealistic, 3d model, cinematic, bad anatomy, blurry, disembodied limb
Acknowledgements
Datasets
280k imgs from Mynefactory
30k imgs from cybermeow
Models
Description
FAQ
Comments (11)
英雄联盟，很好的模型，爱来自瓷器(｡･ω･｡)ﾉ♡
OVO
Sorry. Let me check just to be sure.
1) Do I have to write "kblueleaf" somewhere every time I publish an image using this model?
2) Do I have to write "kblueleaf" every time I publish a new model merging this model?
3) Do I have to write "kblueleaf" every time I publish an image using a new composite model of this model?
I was using my SD 1.5 prompts, and... it works! Note: cfg 4.5 mimic 1 phi 0.3. Nice model to study anime style SDXL.
PS: so similar to nekorayxl
What training resolution did you use to get it to work with less than 1024x1024? I thought base xl was bad at going below that?
the BEST XL anime checkpoint model !
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.