Myeongjang Pyeon

Images

Output

1: completely redraw face or hands / 0: no effect on output images

Adetailer Denoising Strength

Brightness

Cfg Scale

The number of last layers of CLIP network to skip

Clip Skip

Contrast

Enhance/diminish detail while keeping the overall style/character

Detail

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

Disable Prompt Modification

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

Embedding 1

Embedding 2

Embedding 3

Enhance Face With Adetailer

Enhance Hands With Adetailer

Height

Base image that the output should be generated from. This is useful when you want to add some detail to input_image. For example, if prompt is "sunglasses" and input_image has a man, there is the man wearing sunglasses in the output.

Input Image

How differ the output is from input_image. Used only when input_image is given.

Input Image Redrawing Strength

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

Lora 1

Lora 2

Lora 3

Negative Prompt

Num Outputs

Prompt

Reference Depth Image

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

Reference Depth Strength

Image with which the output should share identity (e.g. face of a person or type of a dog)

Reference Image

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

Reference Image Strength

Reference Pose Image

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

Reference Pose Strength

Samping Steps

Sampler

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

Seed

Width

Input

stable-diffusion-xl

Image that the output should be similar to

Whether to ignore the last layer of CLIP network or not

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]>

Random seed. Set as -1 to randomize output.

Pixel dimensions of output image (width x height)

Image Dimensions

LoRA file. You can apply and adjust the magnitude by putting the following to the prompt: <lora:[FILE_NAME]:[MAGNITUDE]>

Lora

Random seed. Set as -1 to randomize the seed

SDXLInput

BaseSDInput

Text-to-image generation with better prompt understanding and enhanced image composition.