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
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.
As it is based on ANIMA - no commercial use. I wonder how it is with on site generation (you pay Buzz).
Description
trained with misumi tuner. Used pure natural language captioning with qwen 3.5 VL NSFW Captioner (which tends to ANALyze a bit too oddly).
Used 1536x1536 as resolution - Bucketing enabled. Which resulted in ~6h on a 5090... Next Time I'll use 1024 ;-)
I like the SFW result - NSFW tends to be better with a Basemodel trained on it or in combination with the "Krea 2 Condition Control" Node in ComfyUI.
Best Results at 0.7 to 0.8