Civitai
The image model hub: checkpoints, LoRAs and the example images that show what they actually do. Indispensable, and volatile.
- Hosted
- Opt-in
Pony Diffusion V6 XL
An SDXL fine-tune that became the base model for a large share of community art checkpoints.
- Open weights
- Image
- Allowed adult content
At a glance
- Made by
- PurpleSmartAI
- Family
- Stable Diffusion
- Licence
- Fair AI Public License 1.0-SD
- Graphics memory
- 8 GB minimum, 12 GB recommended
- Adult content
- AllowedAdult content is permitted within the published rules.
Technically a fine-tune, practically a base model: a great many checkpoints on Civitai are built on it rather than on SDXL directly. It uses its own prompt conventions — score tags and quality prefixes — which do not carry over from vanilla SDXL, and that trips up everyone at least once.
Unlike the Stability base models it was trained with adult material included, which is why it is the foundation so much of the community builds on.