---
license: other
pipeline_tag: text-to-image
tags:
- Stable Diffusion
- not-for-all-audiences
---
Anime-focused ZeroDiffusion finetune. Intended for future training, NOT inference.
Finetuned on 14117 image-caption pairs.
NSFW images were not filtered.
[This](https://huggingface.co/mirav/newmoon/blob/main/NewMoon_clip_l.safetensors) was used as the text encoder, rather than ZeroDiffusion's own text encoder.
Trained on a single 24GB RTX 3090.
License: [Fair AI Public License 1.0-SD](https://freedevproject.org/faipl-1.0-sd/)
Versions:
* 0din-0.1: Trained on less than half of the dataset, purely for testing purposes.
* 0din-0.8: Trained on the full dataset for four epochs.