This model is made for messy cumshot photos with full facial and body coverage. The LORA aims for cum coverage over all else.
This is a third version of translating the Cumzilla dataset to a Flux LORA trained at 1024x1024 pixels. It was trained on the full flux1-dev model. The model needs a large amount of prompting help to render cum properly. See example images for help with prompting - e.g. if you don't tell it cum is white, you're going to get lots of random colors. See example images for prompting advice.
Improvements
Down-scaled original images to 1024x1024 instead of upscaling from 512x512 crops.
Removed several blurry images, which seems to have increased quality.
Removed several low-cum images in an effort to maximize coverage.
Trained on a new LORA config.
Trying Alpha=16 instead of Alpha=8 (v1)
NOTE: this LORA performs poorly against the flux1-dev-fp8 quantization of Flux. Don't be surprised if results are off. It was trained on and performs the best on flux1-dev. Not sure how to help this in terms of training. One user suggested using Heun with 8 steps for the fp8 quantized Flux.
