Model Details

• License: The CreativeML OpenRAIL M license is an Open RAIL M license, adapted from the work that BigScience and the RAIL Initiative are jointly carrying in the area of responsible AI licensing. See also the article about the BLOOM Open RAIL license on which our license is based.

• Training : This model is fine-tuned from the vae use in this stable-diffusion checkpoint CompVis/stable-diffusion-v1-4

  • Dataset: a subset of Danbooru2017, can be downloaded from kaggle.
  • Compute: The training using only one RTX 3090. Training was stopped at about 17 hours. And the latest checkpoint is exported.
  • Training code: The code used for training can be found in this github repo: cccntu/fine-tune-models

Usage

• this model can be loaded using stable_diffusion_jax

from stable_diffusion_jax import AutoencoderKL
vae, vae_params = AutoencoderKL.from_pretrained(
    "ttj/stable-diffusion-vae-anime", _do_init=False, dtype=dtype, use_auth_token=True
)

For example on using this model, please refer to this notebook in the github repo.