
Create lora for pony and flux if you want. Image Dataset is provided, not captioned
btw medusa has three costumes, so three trigger word for different outfit will be helpful.
this dataset has Ai generated images too but using them will reduce face likeness.
i suggest creating a separate lora using AI gen renders.
Also include short videos upscaled by topaz to extract images.
850 images, 1.2 GB
https://mega.nz/folder/cFIi3Zgb#hAytP9YrJ9z3BJDrUgRVwQ
Use this image dataset anyway you want, they are not captioned.
描述:
Initial Upload. Image only, no caption
训练词语:
名称: imageDatasetForMedusa_v10.zip
大小 (KB): 1269665
类型: Archive
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success
原文链接:https://1111down.com/1120501.html,转载请注明出处