A negative prompt embedding I created for RAP (RAP - v1.0 | Stable Diffusion Checkpoint | Civitai) checkpoint model. It seems to work well across a wide range of models. Use in your negative prompt to make the image look better. Do not use as a regular prompt. This is a merge of several negative embedding with additional custom training. It is 75 tokens in size.

All example images are using ADetailer for the face instead of the restore face options.

Please leave a like and post images if you feel this embedding helped you.