You're looking at a specific version of this model. Jump to the model overview.
zsxkib /flux-pulid:21049bde
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 |
|---|---|---|---|
| main_face_image |
string
|
ID image for face generation
|
|
| prompt |
string
|
portrait, color, cinematic
|
Text prompt for 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
|
Negative prompt to guide what to avoid in the image
|
| width |
integer
|
896
Min: 256 Max: 1536 |
Width of the generated image
|
| height |
integer
|
1152
Min: 256 Max: 1536 |
Height of the generated image
|
| num_steps |
integer
|
20
Min: 1 Max: 20 |
Number of denoising steps
|
| start_step |
integer
|
0
Max: 10 |
Timestep to start inserting ID (0-4 recommended, lower for higher fidelity, higher for more editability)
|
| guidance_scale |
number
|
4
Min: 1 Max: 10 |
Guidance scale for text prompt influence
|
| id_weight |
number
|
1
Max: 3 |
Weight of the ID image influence
|
| seed |
integer
|
Random seed for generation (leave blank or -1 for random)
|
|
| true_cfg |
number
|
1
Min: 1 Max: 10 |
True CFG scale (1.0 for fake CFG, >1.0 for true CFG)
|
| max_sequence_length |
integer
|
128
Min: 128 Max: 512 |
Max sequence length for prompt (T5), smaller is faster
|
| output_format |
string
(enum)
|
webp
Options: png, jpg, webp |
Format of the output image
|
| output_quality |
integer
|
80
Min: 1 Max: 100 |
Quality of the output image (for jpg and webp)
|
| num_outputs |
integer
|
1
Min: 1 Max: 4 |
Number of images to generate
|
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'}