You're looking at a specific version of this model. Jump to the model overview.
zsxkib /flux-dev-inpainting-controlnet:45a3d38b
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 |
|---|---|---|---|
| image |
string
|
Input image for inpainting. Should be a valid image file.
|
|
| mask |
string
|
Mask image for inpainting. Areas to be inpainted should be white, and areas to be preserved should be black. Should be a valid image file.
|
|
| prompt |
string
|
A minion sitting on a park bench.
|
Text prompt for image generation.
|
| negative_prompt |
string
|
|
Negative text prompt. Used to reduce or avoid certain aspects in the generated image.
|
| controlnet_conditioning_scale |
number
|
0.5
|
ControlNet conditioning scale. A single float value for generation.
|
| num_inference_steps |
integer
|
30
Min: 1 Max: 100 |
Number of inference steps for the diffusion model.
|
| guidance_scale |
number
|
3.5
Max: 20 |
Guidance scale for classifier-free guidance. Higher values encourage the model to generate images that are closer to the text prompt.
|
| true_guidance_scale |
number
|
3.5
Max: 20 |
True guidance scale for the transformer model.
|
| num_outputs |
integer
|
1
Min: 1 Max: 10 |
Number of images to generate.
|
| seed |
integer
|
Random seed. Set for reproducible generation.
|
|
| output_format |
string
(enum)
|
webp
Options: webp, jpg, png |
Format of the output images.
|
| output_quality |
integer
|
90
Min: 1 Max: 100 |
Quality of the output images (applicable for 'jpg' and 'webp'). Value between 1 (lowest quality) and 100 (highest quality). Ignored for 'png'.
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'items': {'format': 'uri', 'type': 'string'},
'title': 'Output',
'type': 'array',
'x-cog-array-type': 'iterator'}