Brand new model trained using synthetically-generated datasets from publicly-available and privately-trained models, combined with tagging using multimodal LLMs. I kinda love this thing. I hope you love it too.
This model has been tuned for excellent composition, aesthetics, and "soul." Characters come alive, scenery is dynamic, and there are a /ton/ of well-supported art styles. If ZBase can't make it, no one can ;-)
Please use LoRAs as low ratios (0.4-0.6) to accomplish softcore and hardcore NSFW, as the model has been made "flaccid" for general audience use. Erotica and nudes are fully doable (and quite good) with the base model however, so enjoy :)
Description
Slight improvement to brightness/contrast/exposure
Better, more varied fabric, fur, skin, and scale textures
Better hires behavior at odd aspect ratios
Small improvements to composition quality and variation.
FAQ
Comments (7)
Very confusing and non-user friendly (for someone coming from SD 1.5), as almost every image posted uses different methods of prompting.
Hol' up, you're complaining that it's too flexible?
Sounds like a skill issue...
lol welcome to SDXL. You get WAY more options than1.5. Prompting is actually fun again!
@dustydecapod guess it depends on how yu look at it lmao
@TheP3NGU1N lmao
@colinw2292823 I'm still learning SDXL .... better than SD3 anyway XD
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.