jacksonmann

The number of last layers of CLIP network to skip

Control how much respect the output image should pay to the original content. Setting it to 0 changes nothing. Setting to 1 you'll get an unrelated image.

Disable automatically adding suggested prompt modification. Built-in LoRAs and trigger words will remain.

Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)

LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>

Same seed with the same prompt generates the same image. Set as -1 to randomize output.

real-vision-inpaint