usamaehsan/flux-multi-controlnet

Fast FLUX DEV -> Flux Controlnet Canny, Controlnet Depth , Controlnet Line Art, Controlnet Upscaler - You can use just one controlnet or All - LORAs: HyperFlex LoRA , Add Details LoRA , Realism LoRA

Input
Configure the inputs for the AI model.

Random seed for reproducibility

Input image for inpainting

1
50

Number of denoising steps

The text prompt that guides image generation

0
5000

Output image width in pixels

0
5000

Output image height in pixels

0
10

Strength of inpainting (how much to repaint masked area)

Whether to use automatic masking

Mask image for inpainting (white pixels will be repainted)

Input image for Canny ControlNet

Input image for Depth ControlNet

Input image for Lineart ControlNet

0
2

Strength for Canny ControlNet

0
2

Strength for Depth ControlNet

0
50

Controls how closely the image follows the prompt

0
1

Weight of sparklers-visual-effect LoRA

Input image for Upscaler ControlNet

The negative text prompt that guides image generation

Text prompt for automatic object detection and masking

Reference image for IP Adapter

0
10

Scale of influence for IP Adapter

0
2

Strength for Lineart ControlNet

0
100

Size of padding when cropping the mask

0
2

Strength for Upscaler ControlNet

0
1

Weight of sparklers-visual-effect LoRA

Second reference image for IP Adapter

Third reference image for IP Adapter

0
10

Scale of influence for second IP Adapter image

0
10

Scale of influence for third IP Adapter image

Detector type to use with Canny ControlNet

Detector type to use with Depth ControlNet

0
1

Weight of the Realism LoRA adaptation

Whether to use background mask instead of object mask

0
1

Percentage of steps at which ControlNet stops applying

0
1

Weight of ppt-templates LoRA

0
1

Weight of couple-profile LoRA

0
1

Weight of the HyperFlex LoRA adaptation

Detector type to use with Lineart ControlNet

0
1

Percentage of steps at which ControlNet starts applying

0
1

Weight of home-decoration LoRA

0
1

Weight of the Add Details LoRA adaptation

0
1

Box threshold for automatic masking

Whether to use weighted text embeddings

0
1

Text threshold for automatic masking

0
1

Weight of sparklers-visual-effect LoRA

Negative reference image for IP Adapter

0
10

Scale of influence for negative IP Adapter image

0
1

Weight of portrait-photography LoRA

0
1

Weight of portrait-illustration LoRA

0
1

Weight of visual-identity-design LoRA

Output
The generated output will appear here.

No output yet

Click "Generate" to create an output.

flux-multi-controlnet - ikalos.ai