v2 / v2A / v2B

The prompt requires a trigger word.

This is a v-prediction model. it must be used in a v-prediction support program.

v1

recommend CFG - 1.5~2

This checkpoint is merged with DPO LoRA.

Recommended Prompt - hdr 8k analog photo,

Recommended Negative Prompt : big eyes, jpeg artifacts, (airbrushed, cartoon, anime, manga:1.4), (worst quality, low quality, normal quality, lowres, low details, oversaturated, undersaturated, overexposed, underexposed, grayscale, bw, bad photo, bad photography, bad art:1.4)