A LoRA(LyCORIS/LoCon) model of a realistic Japanese girl that trained with over 20Kpictures.
Run4.4K
Comments
Version Detail
SD 1.5
9811
2
We have increased the image count in the training dataset to 6,000. To retain this information capacity, we have significantly expanded the Network_dim to 256 and Conv_dim to 64. Although the size of LoRA has been proportionally increased, the response to prompts has improved.
Project Permissions
Use without crediting me
Share merges of this model
Use different permissions on merges
Use Permissions
Sell generated images
Use on generation services
Sell this model or merges
Commercial Use
Comments
Related Posts
Describe the image you want to generate, then press Enter to send.