tuwonga / blythy

This is a fine-tuned LoRA checkpoint model (based on Stable Diffusion 1.5) trained on blythe doll figures: use the token blythy in your prompts to use the style.

Download the safetensor file from "files and versions" tab into the stable diffusion/models/Lora folder of your web-ui of choice.

Basically a style but also works well with characters. I'm still working on parameters on img2img, sounds interesting.

Please feel free to test and give me feedback.

Thank you.

This model was trained with Kohya-SS using 20 images, 4 epoch, 40 repeats (3200 steps).

Characters rendered with this model:

--

License

This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage. The CreativeML OpenRAIL License specifies:

1. You can't use the model to deliberately produce nor share illegal or harmful outputs or content
2. The authors claims no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in the license
3. You may re-distribute the weights and use the model commercially and/or as a service. If you do, please be aware you have to include the same use restrictions as the ones in the license and share a copy of the CreativeML OpenRAIL-M to all your users (please read the license entirely and carefully) Please read the full license here