I've captured the tokenized identity NatureVRM as a full-body LoRA. The training process is described in this blogpost https://hackmd.io/@reneil1337/avatar-lora and can be applied to your own VRM avatars. Publishing the SD LoRAs under cc0 licence. Enjoy the model and please share your creations.
Prompt via ".. NatureVRM a person.. "
Image training dataset
- SD15 v1.0 was trained with 100 images in 512x512 resolution
- SDXL v1.0 was trained with 100 images in 1024x1024 resolution
- Flux.1 D Beta was trained with 100 images in 1024x1024 resolution
Description
Prompt with "NatureVRM a person"
100 images (1024px) to captured the avatar in 3D software
1500 per epoch + class regulation (1024px) via aitrepreneur