jacksonmann

Images

Whether to ignore the last layer of CLIP network or not

Enhance/diminish detail while keeping the overall style/character

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>

Strength of applying reference_depth_image. Used only when reference_depth_image is given.

Image that the output should be similar to

Strength of applying reference_image. Used only when reference_image is given.

Strength of applying reference_pose_image. Used only when reference_pose_image is given.

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