For the Ink Model I would recommend using the "dream shaper 6" with the baked VAE as well as a detail LoRa for the best results.Not a pony model, but does have a lot of NSFW imeges in the data setCompatible to use in DiffusionBee, 3.5.3<div data-youtube-video><iframe width="640" height="480" allowfullscreen="true" autoplay="false" disablekbcontrols="false" enableiframeapi="false" endtime="0" ivloadpolicy="0" loop="false" modestbranding="false" origin playlist src="https://www.youtube.com/embed/KWf6aaWSTIY" start="0"></iframe></div>This models trained off of artwork by atomic comics, Greg Rakowski, and more in dream booth.This model uses table to fusion 1.5 as its base model.Making these models can be expensive and very time consuming. If you would consider helping out, it would be much appreciated as any little bit goes a long way<a target="_blank" rel="ugc" href="https://www.buymeacoffee.com/Theprotoart">https://www.buymeacoffee.com/Theprotoart</a>using the regular prompts sometimes results in unexpected outcomes… i’ve tried running it with common prompts, such as manga, comic or vector, anime, etc.Check out my other models: <a target="_blank" rel="ugc" href="https://civarchive.com/user/mrpbody">https://civarchive.com/user/mrpbody</a>

Atomic micro model

Converted safetensor model. Most of the same data set of images as the original larger model

Files with SHA256: 970fdfd39bbf30111f8d20d0bfdb632846e7432a065fdb2c54e1967476bfa2b9