Support SDXL

This LORA model is trained with HelloWorld SDXL. it works pretty well with any photorealistic models.

Recommend:

• Image Size: 1024x1024 or 1024x1536 or 1080x1350

• Steps: 20-30

• Sampler: DPM++ 2M Karras

• CFG scale: 7-9

• Weight: 0.4-0.6

• Prompt: food, nude, lying, breasts, sushi, food focus

Trigger Word: nyotaimori