all images in sample were made with the model "ANIMA BASE"

USE THE TRIGGER WORDS BELOW:

trigger_word - @otmoroshka.

I use an image resolution around 960×1280.

I also highly recommend enabling Hires. fix (1.5× upscale, 0.3–0.4 denoising), as it produces noticeably better style similarity compared to standard generation. I recommend using REMARCI or any other custom upscaler of your choice.

Additionally, the LoRA strength can be increased to 1.2, or you can even choose not to use the trigger word at all.

Quality tags:
masterpiece, best quality, highres, absurdres, newest, perfect composition

Negative:
worst quality, low quality, lowres, score_1, score_2, score_3, blurry, jpeg artifacts, sepia, early, loli, bad hands, missing fingers, artist name, watermark, cross, bad details

If you want to reduce the furry influence from the dataset, you can also add tags such as:
furry, anthro, animal ears, tail, fur, muzzle

Recommended settings:

• ER SDE + SGM UNIFORM / BETA / NORMAL

• Euler A

• SHIFT 4/3

• CFG Scale 4/3

• CLIP Skip 1/2

All sample images were generated using a LoRA weight between 1.00 and 1.30.

Once again, always support the original artists.

This model is intended for artistic and educational purposes only. The included style is based on publicly available artwork and is not intended to infringe upon the intellectual property of any artist. It should not be used commercially or for monetary gain. Please respect the work of the original creators.