You're looking at a specific version of this model. Jump to the model overview.
mattheum /flux-multi-pulid-controlnet:73a2c5ab
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 |
|---|---|---|---|
| id_one_image |
string
|
Upload an ID image for the left side of the generated image
|
|
| id_two_image |
string
|
Upload an ID image for the right side of the generated image
|
|
| id_three_image |
string
|
Upload an ID image for the left side of the generated image
|
|
| id_four_image |
string
|
Upload an ID image for the right side of the generated image
|
|
| mask_one_image |
string
|
Upload an mask image for the first person of the generated image
|
|
| mask_two_image |
string
|
Upload an mask image for the second person of the generated image
|
|
| mask_three_image |
string
|
Upload an mask image for the third person of the generated image
|
|
| mask_four_image |
string
|
Upload an mask image for the fourth person of the generated image
|
|
| img_to_img_image |
string
|
Upload an image to guide the generation
|
|
| image2image_strength |
number
|
0
Max: 1 |
Set the strength of the image to image guidance (0.0-1.0)
|
| prompt |
string
|
portrait, color, cinematic
|
Enter a text prompt to guide image generation
|
| negative_prompt |
string
|
bad quality, worst quality, text, signature, watermark, extra limbs, low resolution, partially rendered objects, deformed or partially rendered eyes, deformed, deformed eyeballs, cross-eyed, blurry
|
Enter a negative prompt to specify what to avoid in the image
|
| width |
integer
|
1024
Min: 256 Max: 1536 |
Set the width of the generated image (256-1536 pixels)
|
| height |
integer
|
1024
Min: 256 Max: 1536 |
Set the height of the generated image (256-1536 pixels)
|
| num_steps |
integer
|
25
Min: 1 Max: 25 |
Set the number of denoising steps (1-20)
|
| start_step |
integer
|
0
Max: 10 |
Set the timestep to start inserting ID (0-4 recommended, 0 for highest fidelity, 4 for more editability)
|
| guidance_scale |
number
|
4
Min: 1 Max: 10 |
Set the guidance scale for text prompt influence (1.0-10.0)
|
| id_weight |
number
|
1
Max: 3 |
Set the weight of the ID image influence (0.0-3.0)
|
| seed |
integer
|
Set a random seed for generation (leave blank or -1 for random)
|
|
| true_cfg |
number
|
1
Min: 1 Max: 10 |
Set the Classifier-Free Guidance (CFG) scale. 1.0 uses standard CFG, while values >1.0 enable True CFG for more precise control over generation. Higher values increase adherence to the prompt at the cost of image quality.
|
| max_sequence_length |
integer
|
128
Min: 128 Max: 512 |
Set the max sequence length for prompt (T5), smaller is faster (128-512)
|
| output_format |
string
(enum)
|
webp
Options: png, jpg, webp |
Choose the format of the output image
|
| output_quality |
integer
|
80
Min: 1 Max: 100 |
Set the quality of the output image for jpg and webp (1-100)
|
| num_outputs |
integer
|
1
Min: 1 Max: 4 |
Set the number of images to generate (1-4)
|
| use_canny_controlnet |
boolean
|
False
|
Use the Canny controlnet
|
| use_depth_controlnet |
boolean
|
False
|
Use the Depth controlnet
|
| control_net_image |
string
|
Upload an image to guide the generation
|
Output schema
The shape of the response you’ll get when you run this model with an API.
{'items': {'format': 'uri', 'type': 'string'},
'title': 'Output',
'type': 'array'}