simbrams/ri

Realistic Inpainting with ControlNET (M-LSD + SEG)

Input

Configure the inputs for the AI model.

Eta

0

100

eta

Mask *

Mask image

Seed

Leave blank to randomize

Debug

Enable

Debug mode

Image *

Input image

Steps

0

100

num_inference_steps

Prompt

Strength

0

1

strength/weight

Blur Mask

Enable

Blur the mask

Do Resize

Enable

Resize the image

Merge M S

Enable

scheduler

Choose a scheduler

Image Size

512

100

Image size

Keep Alive

Enable

Keep model alive

Blur Radius

0

50

Blur radius

Only Objects

Enable

Modify only the objects

Seg Strength

0

100

seg_strength

Mlsd Strength

0

100

mlsd_strength

Tile Strength

0

100

tile_strength

Canny Strength

0

100

canny_strength

Guidance Scale

0

30

guidance_scale

Upscale Factor

1

4

upscale_factor

Dilation Factor

0

20

Mask dilation factor (0 for no dilation)

Negative Prompt

Preserve Elements

Enable

preserve_elements

Output

The generated output will appear here.

No output yet

Click "Generate" to create an output.