Hi everyone!

This is the first version VividNS LoRa for Flux Klein 9B.

The version included furries, futanaries, and some images depicting sex as additions. However, not all of the categories are working perfectly just yet. I also encountered the issue that Flux has serious problems with anatomies—and sometimes it simply skips over what you are trying to get out of it.

Parameters I used for the generations

- Turbo LoRA r128

- Steps: 8

- Sampler: res_2s / euler a

This LoRA is not meant to be completely photorealistic.

The main goal is to explore and unlock things that were not possible with the original model.

The training set included 750 images, and none of them were taken from real people.

That is what made it possible to achieve such unusual body proportions or concepts.