Anime-focused ZeroDiffusion finetune. Don't expect anything great from this.
Finetuned on 14117 image-caption pairs at 768 resolution (with bucketing). NSFW images were not filtered.
This 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

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.