Greetings!
This is a textual inversion based on SDXL 1.0 images with the refiner, tested and trained to enhance the effectiveness of the output of human figures. It is meant to correct mutation like symptoms of the face and hands, and it has an excellent improvement in the clothing and blurriness and realism of such features as the skin.
V1.1 Edit: The above images are done on a Pony model of mine, so this embedding will work quite good with all forms of SDXL, as you can see.
Simply place this in your "embeddings" folder and type "badX" into your negative prompt. In comfyUI, in the negative prompt, include "Embedding:BadX,".
I have a new account on buymeacoffee:: https://bmc.link/ricesilo11W
And if you enjoy Stable Diffusion art, check out my galleries: https://deviantart.com/ricesilo
Commissions Available, contact me on Discord username: RiceSilo
Description
FAQ
Comments (2)
Pain in the butt to use since it's not in .safetensors format and even v1.1 (from Oct. '24) is still recognized as an SD1.5 embedding (even though it functionally is an SDXL embedding).
Technically still able to use it with some significant fiddling but just not the easy mode A1111 SDXL users are used to.
I just made it as an embedding with my Computer Science, it was really the first from those days SDXL was just released before they did all that with their UI.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.