You're looking at a specific version of this model. Jump to the model overview.
zsxkib /flux-dev-inpainting-controlnet:f9cb02cf
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
|
Upload an image for inpainting. This will be the base image that will be partially modified.
|
|
| mask |
string
|
Upload a mask image for inpainting. White areas (255) indicate regions to be inpainted, while black areas (0) will be preserved from the original image.
|
|
| prompt |
string
|
A colorful hot air balloon floating over a serene landscape.
|
Enter a text description to guide the image generation process.
|
| negative_prompt |
string
|
|
Negative text prompt. Used to reduce or avoid certain aspects in the generated image.
|
| controlnet_conditioning_scale |
number
|
0.9
Max: 2 |
ControlNet conditioning scale.
|
| num_inference_steps |
integer
|
28
Min: 1 Max: 100 |
Set the number of denoising steps. More steps generally result in higher quality but slower generation.
|
| 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
|
Set a seed for reproducible generation. Leave as None for random results.
|
|
| output_format |
None
|
webp
|
Choose the file format for the output images.
|
| output_quality |
integer
|
80
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'}