Try size: 768 x 1024 or 1024 x 1024
Weights: 0.8~1.0
Clip skip: 2
Training material from screenshot, gemini and danbooru pics
Pictures from kantanmix_v16VakedVAE
Note: The success rate is about 1/10~1/2, especially when the LoRA weight is too low.
Version Detail
Illustrious
Project Permissions
Use in TENSOR Online
As a online training base model on TENSOR
Use without crediting me
Share merges of this model
Use different permissions on merges
Use Permissions
Sell generated contents
Use on generation services
Sell this model or merges