This flux LoRA was created to allow the user to have more control over blood when generating realistic violence. The dataset consisted of 31 high resolution movie stills captioned in natural language.

Bloody Flux

I felt like the V1 was a hit or miss. It didn't grasp the concept well enough. So I started from scratch! Introducing the new and improved BLOODY FLUX featuring an all new training dataset consisting of carefully selected high res images depicting bloody violence in an assortment of different ways. The captions are more detailed and contains both booru tags and natural language styles. No trigger word this time. Enjoy!

Files with SHA256: 2b7eb28c03ff540f2bc3432095203d6b203b5eabdc2b1ad4f5c0a6cb51727a57