This is what it sounds like it is. It was captioned with jailbroken Gemini 2.5 Pro, so you will get better results from prompting with natural language. Recommended strength is around 0.6 to 0.8. The dataset was intentionally as diverse as I could possibly make it, so it should be pretty flexible in terms of ethnicity / appearances / ages / etc.
Version Detail
Trained by Tensor
FLUX.1 Krea Dev
80
Project Permissions
Use in TENSOR Online
As a online training base model on TENSOR
Use without crediting me
Share merges of this model
Use different permissions on merges
Use Permissions
Sell generated contents
Use on generation services
Sell this model or merges