acoustica

For best outputs:

• Sampler: DPM++ 2M SDE Karras.

• Steps: 40, cfg 7, CLIP skip 2.

• VAE: kl-f8-anime2_fp16.safetensors

• Pos prompt: add the LoRa "add_detail" with a weight of 0.8 at the end of your pos (can be found in my example runs).

• Neg prompt: "((nipples)), nsfw, low resolution, (monochrome:1.2), (grayscale:1.2), signature, watermark, (worst quality:2), (low quality:2), (normal quality:2)".

• Note: the model is capable of NSFW, but nothing beyong POV and the basic poses.

Checkpoint Merge.