Sydney Sweeney SDXL (collab with MachineMinded)
Trained on BigLust 1.7
Uses DMD2 LoRA (https://huggingface.co/tianweiy/DMD2/blob/main/dmd2_sdxl_4step_lora_fp16.safetensors)
Recommended:
use ADetailer for face
blur: 20-25
padding: 120-200
denoising: 0.14-0.25
LoRA strength set to 1
(optional) Hires Fix (helps for ADetailer)
upscale by: 1.5-1.75
hires steps: 0-3
denoising: 0-0.3
CFG: 1
Description
trained on biglust 1.7
96 images, florence captioning, bucket sizes:
bucket 0: resolution (704, 1216), count: 1
bucket 1: resolution (768, 1152), count: 2
bucket 2: resolution (768, 1216), count: 2
bucket 3: resolution (768, 1280), count: 1
bucket 4: resolution (768, 1344), count: 8
bucket 5: resolution (832, 1088), count: 1
bucket 6: resolution (832, 1152), count: 2
bucket 7: resolution (832, 1216), count: 21
bucket 8: resolution (896, 1088), count: 34
bucket 9: resolution (896, 1152), count: 3
bucket 10: resolution (960, 960), count: 1
bucket 11: resolution (960, 1024), count: 2
bucket 12: resolution (1024, 1024), count: 4
bucket 13: resolution (1088, 832), count: 9
bucket 14: resolution (1088, 896), count: 1
bucket 15: resolution (1216, 832), count: 1
bucket 16: resolution (1280, 768), count: 1
bucket 17: resolution (1344, 768), count: 2