You're looking at a specific version of this model. Jump to the model overview.
usamaehsan /flux-multi-controlnet:9d985dc9
Input schema
The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.
| Field | Type | Default value | Description |
|---|---|---|---|
| prompt |
string
|
A girl in city, 25 years old, cool, futuristic style
|
The text prompt that guides image generation
|
| canny_image |
string
|
Input image for Canny ControlNet
|
|
| depth_image |
string
|
Input image for Depth ControlNet
|
|
| lineart_image |
string
|
Input image for Lineart ControlNet
|
|
| upscaler_image |
string
|
Input image for Upscaler ControlNet
|
|
| canny_detector_type |
string
(enum)
|
canny
Options: canny, mlsd, hed, lineart |
Detector type to use with Canny ControlNet
|
| depth_detector_type |
string
(enum)
|
depth
Options: depth, canny, mlsd, hed, lineart |
Detector type to use with Depth ControlNet
|
| lineart_detector_type |
string
(enum)
|
lineart
Options: lineart, canny, mlsd, hed |
Detector type to use with Lineart ControlNet
|
| canny_strength |
number
|
0.6
Max: 2 |
Strength for Canny ControlNet
|
| depth_strength |
number
|
0.6
Max: 2 |
Strength for Depth ControlNet
|
| lineart_strength |
number
|
0.6
Max: 2 |
Strength for Lineart ControlNet
|
| upscaler_strength |
number
|
0.6
Max: 2 |
Strength for Upscaler ControlNet
|
| guidance_scale |
number
|
3.5
Max: 50 |
Controls how closely the image follows the prompt
|
| steps |
integer
|
28
Min: 1 Max: 50 |
Number of denoising steps
|
| seed |
integer
|
Random seed for reproducibility
|
|
| visual_identity_design_weight |
number
|
0
Max: 1 |
Weight of visual-identity-design LoRA
|
| couple_profile_weight |
number
|
0
Max: 1 |
Weight of couple-profile LoRA
|
| film_storyboard_weight |
number
|
0
Max: 1 |
Weight of film-storyboard LoRA
|
| font_design_weight |
number
|
0
Max: 1 |
Weight of font-design LoRA
|
| home_decoration_weight |
number
|
0
Max: 1 |
Weight of home-decoration LoRA
|
| portrait_illustration_weight |
number
|
0
Max: 1 |
Weight of portrait-illustration LoRA
|
| portrait_photography_weight |
number
|
0
Max: 1 |
Weight of portrait-photography LoRA
|
| ppt_templates_weight |
number
|
0
Max: 1 |
Weight of ppt-templates LoRA
|
| sandstorm_visual_effect_weight |
number
|
0
Max: 1 |
Weight of sandstorm-visual-effect LoRA
|
| sparklers_visual_effect_weight |
number
|
0
Max: 1 |
Weight of sparklers-visual-effect LoRA
|
| hyperflex_lora_weight |
number
|
0.125
Max: 1 |
Weight of the HyperFlex LoRA adaptation
|
| add_details_lora_weight |
number
|
0
Max: 1 |
Weight of the Add Details LoRA adaptation
|
| realism_lora_weight |
number
|
0
Max: 1 |
Weight of the Realism LoRA adaptation
|
| width |
integer
|
0
Max: 5000 |
Output image width in pixels
|
| height |
integer
|
0
Max: 5000 |
Output image height in pixels
|
| image |
string
|
Input image for inpainting
|
|
| mask_image |
string
|
Mask image for inpainting (white pixels will be repainted)
|
|
| strength |
number
|
0.7
Max: 1 |
Strength of inpainting (how much to repaint masked area)
|
| padding_mask_crop |
integer
|
Size of padding when cropping the mask
|
|
| control_guidance_start |
number
|
0.2
Max: 1 |
Percentage of steps at which ControlNet starts applying
|
| control_guidance_end |
number
|
0.8
Max: 1 |
Percentage of steps at which ControlNet stops applying
|
| use_weighted_embeddings |
boolean
|
False
|
Whether to use weighted text embeddings
|
| auto_mask |
boolean
|
False
|
Whether to use automatic masking
|
| auto_mask_prompt |
string
|
Text prompt for automatic object detection and masking
|
|
| auto_mask_box_threshold |
number
|
0.3
Max: 1 |
Box threshold for automatic masking
|
| auto_mask_text_threshold |
number
|
0.25
Max: 1 |
Text threshold for automatic masking
|
| use_background_mask |
boolean
|
False
|
Whether to use background mask instead of object mask
|
Output schema
The shape of the response you’ll get when you run this model with an API.
{'format': 'uri', 'title': 'Output', 'type': 'string'}