A style LoRA based on the art of kame_3t (@kame_3t on X), go check out their work. All credit for the style goes to them.
Soft pastel colors, gentle flat shading and thin lineart, mostly furry characters.
There are versions for Krea 2, MOSS, Anima and Anima 2.9B, so pick the one for your base model and read its notes (each version also has its own).
Krea 2
Start the prompt with @kame_3t, kemono, soft colors, thin lineart, clean lines,soft shading, and then describe the scene in full sentences.
Strength 1.0 (0.8 if you want it subtler).
Trained locally on Krea 2 Raw, epoch 9 of 12.
MOSS
Finally, one that came out right on the first try! The style showed up from the very first epoch, and the final epoch is the one I kept.
Start the prompt with @kame_3t, a kemono-style digital illustration with soft pastel colors, thin clean lineart and soft shading. and then describe the scene in full sentences.
Strength 1.0 (up to 1.2 if your checkpoint pulls too hard toward its own look).
Trained locally on MOSS Image Base, final epoch (12). No turbo or detailer needed: it looks clean on plain MOSS SFT at 35 steps and CFG 4.
Anima
The fast one: under 1 h 30 min of training. Trained locally on Anima Base v1.0 with Danbooru tags, epoch 9 of 12.
Start the prompt with masterpiece, best quality, @kame_3t, and then use regular Danbooru tags. Add soft colors, thin lineart, soft shading if you want the pastel look stronger.
Strength 1.0.
Use a finetune (tested on waiANIMA at 25 steps, CFG 4). On plain Anima Base everything comes out washed out, with or without the LoRA.
It sometimes draws a white border around the image (a quarter of the original art has one). Put border, white border, outside border in the negative if you don't want it.
Anima 2.9B: there's a dedicated v1 (Anima 2.9B) version, the same epoch 9 remapped to the 40-block layout of the 2.9B models. Strength 0.8 to 1.2. If your loader already remaps older Anima LoRAs (LoRA Manager does), the regular version works too, and that's also the way to go for 3.8B models.
Description
Anima version, trained locally with sd-scripts on Anima Base v1.0 on a 16 GB RTX 5070 Ti. Same 144 images as the other versions, but captioned with Danbooru tags instead of sentences (character names included, like renamon or loona (helluva boss)).
Training: 2 repeats × 12 epochs, rank 32 / alpha 16, lr 1e-4. Anima is the fast one: about 7 minutes per epoch, under 1 h 30 min in total.
I compared all the epochs against a no-LoRA control on waiANIMA. The control has an anime-style face with a short muzzle; from epoch 6 on you get kame_3t's longer muzzle, half-closed eyes, fur tufts and soft pastel colors. Epoch 9 was the best balance. From epoch 10 on the proportions get exaggerated and the colors oversaturated.
How to use
Start the prompt with masterpiece, best quality, @kame_3t, and then use regular Danbooru tags. If you want the pastel look stronger, add soft colors, thin lineart, soft shading.
Strength 1.0.
Tested on waiANIMA v1.0 at 25 steps, CFG 4, euler / simple. Use a finetune rather than Anima Base: on the base model everything comes out washed out, with or without the LoRA.
Things to know
About a quarter of the original art has a white border, so it sometimes draws a frame around the image. Put border, white border, outside border in the negative if you don't want it.
For Anima 2.9B models there's a separate v1 (Anima 2.9B) version.





