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
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.