Hi everyone!

This is the second version VividNS LoRa.

The second version included furries, futanaries, and some images depicting sex as additions. However, not all of the new categories are working perfectly just yet.

Parameters I used for the generations

- Lighting LoRA: 8 steps. LINK

- Steps: 8

- Sampler: res_2s / euler a

- Scheduler: beta57, normal, simple

I highly recommend using Lighting Lora 8 steps or 4 steps.

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 600 images, and none of them were taken from real people.

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