with a simple description of the output of high quality lovely beautiful girl!
I will continue to improve this model, any questions please comment!
Regarding the difference between FP16 and FP8 (after trimming), I have done a lot of tests, and there is no significant quality difference, but the drawing speed of FP8 may be slower (if you are a graphics card after RTX4060, there is no such problem).
This model does not incorporate any Lora in the training process, so it is very compatible with Lora!
Description
更稳定的画风输出!更强的文字识别能力!
I strongly recommend using this embedding;Async's Negative
FAQ
Details
Downloads
509
Platform
SeaArt
Platform Status
Available
Created
8/24/2024
Updated
8/26/2024
Deleted
-
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.



