Verified: 2 years ago
SafeTensor
Type | |
Stats | 1,972 0 |
Reviews | (234) |
Published | Jun 11, 2023 |
Base Model | |
Training | Steps: 1,500 Epochs: 6 |
Trigger Words | qipao |
Hash | AutoV2 3B56962683 |
Trained on 30 photos with ChillOutMix, work best on DPM++ SDE Karras sampling steps 20-30 CFG Scale 6. weight 0.7 is recommended for better results. if you use higher weight the model will lose their heads . try to experiment with different weights that works for you.
it works together with all of my other LoRA models. have fun trying to mix & match
example setting :
HashimotoKanna_JP_Idol : weight 0.7
Qipao Traditional Dress : weight 0.4
lightweight LoRA, works on any generator (easydiffusion,stablediffusion etc). share your results.
Thank you for downloading.please leave a rating and comment if you like my models. also leave a comment on what model would you like to see next. Please consider to leave a tip if you like my work ๐โ๏ธ enjoy