license: creativeml-openrail-m
pipeline_tag: text-to-image
tags:
- art
Maka Fujiki Dreambooth + AnythingV4
This is a model trained with Dreambooth with TheLastBen and Anything V4 from andite (https://huggingface.co/andite/anything-v4.0) The model was trained based on the artist Oryou popular character Maka Fujiki from the manga Boku no Kanojo Sensei. The current model has been tuned with a learning rate of 2.0e-6 on 63 images collected from Danbooru and Pixiv from artist. It supports Danbooru tags.
Usage/Examples
These are some results you can get with the model.
e.g.
seed: 903184092
prompts: maka, outdoors, field, hat_flower, necklace, white_dress, sunflower, lying, on_grass, cleavage ugly, tiling, poorly drawn hands, poorly drawn arms, poorly drawn feet, poorly drawn face, out of frame, extra limbs, disfigured, deformed, bad anatomy, watermark, signature, low contrast, bad art, beginner, amateur, distorted face, underage, distorted tights, hands on floor
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:
- You can't use the model to deliberately produce nor share illegal or harmful outputs or content
- 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
- 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.
Thanks to
- TheLastBen for his fastDreamboothTraining
- Andite for his mix of models
- Zerocomes for testing the model generating examples