All showcase images have WF embedded.
Trained on this type of prompt
Headscissors: a (digital camera snapshot / phone snapshot / video frame grab...) of a woman doing a headscissors on a man...
Reverse Headscissors: a (digital camera snapshot / phone snapshot / video frame grab...) of a woman doing a reverse headscissors on a man...
Recommended settings
Sampler: euler_ancestral
Scheduler: Beta57
Steps: 8-12
LoRA strength 1.0 (feel free to experiment)
Combine with
Krea2_TextFusion_Refusal_Reductionat 1.0 strength for better prompt adherenceFor NSFW elements, I also combine it with
KNP_000003000at 0.6 strenght
Note that these settings are experimental and based on my tests. There might be better combinations and LoRA strengths.
Known limitations (honest list)
You may need to adapt your prompt to clearly distinguish between reverse headscissors and regular headscissors. The model can struggle to tell the difference between reverse and classic headscissors. It’s recommended to describe the overall position in natural language to avoid the “casino effect,” as the LoRA was trained on various headscissors poses
Sometimes feet or hands can get messed up. You can try another seed, sampler, or resolution
The LoRA doesn’t have a great understanding of male anatomy. If a man is naked, try adding an NSFW LoRA or a penis helper to achieve better realism
Description
FAQ
Comments (3)
ALL HAIL KREA 2!
Now we need a Krea 2 for I2V with fast renderings then the internet will implode and change forever.
💕👍🏻
This is some fine work.
















