
モデルを手直した感触だが、画像が多いとprodigyの結果は良くない,枚数が多いなら、Lionが結果が良い,
今回の例:
--optimizer_type="Lion8bit" --lr_warmup_steps=100 --max_grad_norm=1 --text_encoder_lr=0.00015 --unet_lr=0.00015
I have a feeling that I reworked the model, but if there are a lot of images, prodigy does not give good results. If there are many images, Lion has better results.
Example of this time:
--optimizer_type="Lion8bit" --lr_warmup_steps=100 --max_grad_norm=1 --text_encoder_lr=0.00015 --unet_lr=0.00015
描述:
训练词语: roon \(azur lane\),default,bikini,halloween costume, leotard, pantyhose,music dress,pelvic curtain, short dress,school uniform, pantyhose, short sleeves,idol,pantyhose, black gloves
名称: roon_pony_v1.safetensors
大小 (KB): 167427
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success