kantoku

StableDiffusion model with Dreambooth training based on an anime/illustration artstyle. Trained for 11000 steps using 110 total training images.

Usage

Can be used in StableDiffusion, including the extremely popular Web UI by Automatic1111, like any other model by placing the .CKPT file in the correct directory. Please consult the documentation for your installation of StableDiffusion for more specific instructions.

Safetensors version is identical to the .ckpt version aside from filetype and is the preferred version for safety if your SD installation supports this file type.

kntk_V3_mix75.safetensors is a merged version of this model. The formula for the merge is Elysium_Anime_V3 + (F222 - SD1.4) using Add Difference with a Multiplier of 1, then kntkV3_11000 is merged into the first result using Weighted Sum and a Multiplier of 0.75.

Use the following tokens in your prompt to achieve the desired output. Token: "kntk" Class: "artstyle"

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