This is an image generation model based on training from Illustrious-xl.
It utilizes the latest full Danbooru and e621 datasets for training, with native tags caption.
The stable test version can be downloaded from Civitai, with regular updates. The current release is the version that continues training for 55,000,000 steps.
https://civitai.com/models/833294This is an early test version intended for internal use. However, we are considering allowing limited external testing.
Our ultimate goal is to ensure that quality tags effectively track user preferences in recent years.
