Verified: a year ago
SafeTensor
Type | |
Stats | 378 |
Reviews | (37) |
Published | Jan 7, 2024 |
Base Model | |
Training | Steps: 11,750 Epochs: 50 |
Usage Tips | Clip Skip: 1 Strength: 0.8 |
Trigger Words | pinomyim |
Hash | AutoV2 CB9972AE81 |
This LORA model is trained with majicMIX realistic (SD1.5) and HelloWorld SDXL (SDXL). it works pretty well with any photorealistic models.
For SD1.5
Recommend:
Image Size: 512x512 or 512x768
Steps: 20-30
Sampler: DPM++ 2M Karras
CFG scale: 7-9
Weight: 0.65
Prompt: looking at viewer, bangs
Expression or Accessory: smile, glasses, round eyewear
For SDXL
Recommend:
Image Size: 1024x1024 or 1024x1536 or 1080x1350
Steps: 20-30
Sampler: DPM++ 2M Karras
CFG scale: 7-9
Weight: 0.2 - 0.8
Prompt: looking at viewer, bangs
Expression or Accessory: smile, glasses, round eyewear
Trigger Word: pinomyim