ANIMA v3

This was retrained to be used in my latest Hentai Dreams model. Reduced Dataset. WD14 Captioning. Cleaned some images with flux klein 9b. Trained with ai-toolkit.

The dataset was purley made with sythetic images using illustrious and LoRAs as well as artist tags to get a consistant style. Sometimes controlnet helped.

If you like: smooth skin; large insertions; excessive cum - you also might like this LoRA ;-)

!!!new trigger (not needed but helps): @hentaidrms

________________________________________________________________________________________________

Krea 2

was trained with musimi tuner in 1536x1536 bucketing enabled. My poor 32GB VRAM could not handle the FP16 Basemodel - so FP8 it was. I added the final Epoch 16 as well as Epoch13 (which i think is the best one) but i do not want to waste the 6h training.

I'll try with 1024x1024 and FP16 next time - after the next heatwave in Europe...

Best results with 0.7 (maybe overtrained - but somehow the style is very versatile)

SFW works great, NSFW is strange (tongues in vaginas, anal non existant - maybe because of the NSFW captioning). Krea 2 Conditioning Control node for comfyui recommended to play around - soetimes it helps sometimes it has the opposite effect.

________________________________________________________________________________________________

ANIMA v3

As promised I'll release the Loras I trained for my ANIMA Model.

Nothing special here. Trained with ~250 images, mostly of hentai scenes - be careful: this turns every ANIMA Checkpoint into a cum dripping hentai mess...
Resolution was 1536. Captioning with a custom Qwen 3 VL setup and pure natural language to describe the artstyle of the images. When Qwen VL recognized a female character it always chose woman or young woman - so keep this in mind when prompting.