add an option for users to include their on-site generated images into the Civitai dataset.
the image
the prompts
the settings
you can then score for the best (or run your incredible detectors) and train 3 separate models in conjunction.
the inference,
the settings expert on a style prompt or new conjured up sliders that do correspond to the images style... outlines slider for instance
and a dedicated anatomy model (pony guy colab?)
and they grow together making the ULTIMATE SUPER WEAPON ....
th ... that's a thing you could do with your time ^^
Please authenticate to join the conversation.
Awaiting Dev Review
π‘ Feature Request
Almost 2 years ago

hellrunner
Get notified by email when there are changes.
Awaiting Dev Review
π‘ Feature Request
Almost 2 years ago

hellrunner
Get notified by email when there are changes.