You're looking at a specific version of this model. Jump to the model overview.
kevin51jiang /ic-light:ae0b55ae
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 |
|---|---|---|---|
| subject_image |
string
|
The main foreground image to be relighted
|
|
| prompt |
string
|
A text description guiding the relighting and generation process
|
|
| appended_prompt |
string
|
best quality
|
Additional text to be appended to the main prompt, enhancing image quality
|
| negative_prompt |
string
|
lowres, bad anatomy, bad hands, cropped, worst quality
|
A text description of attributes to avoid in the generated images
|
| width |
integer
|
512
Min: 100 Max: 1280 |
The width of the generated images in pixels
|
| height |
integer
|
640
Min: 100 Max: 1280 |
The height of the generated images in pixels
|
| steps |
integer
|
25
Min: 1 Max: 100 |
The number of diffusion steps to perform during generation (more steps generally improves image quality but increases processing time)
|
| cfg |
number
|
2
Min: 1 Max: 32 |
Classifier-Free Guidance scale - higher values encourage adherence to prompt, lower values encourage more creative interpretation
|
| highres_scale |
number
|
1.5
Min: 1 Max: 3 |
The multiplier for the final output resolution relative to the initial latent resolution
|
| highres_denoise |
number
|
0.5
Min: 0.1 Max: 1 |
Controls the amount of denoising applied when refining the high resolution output (higher = more adherence to the upscaled latent, lower = more creative details added)
|
| lowres_denoise |
number
|
0.9
Min: 0.1 Max: 1 |
Controls the amount of denoising applied when generating the initial latent from the background image (higher = more adherence to the background, lower = more creative interpretation)
|
| light_source |
None
|
None
|
The type and position of lighting to apply to the initial background latent
|
| seed |
integer
|
A fixed random seed for reproducible results (omit this parameter for a randomized seed)
|
|
| number_of_images |
integer
|
1
Min: 1 Max: 12 |
The number of unique images to generate from the given input and settings
|
| output_format |
None
|
webp
|
The image file format of the generated output images
|
| output_quality |
integer
|
100
Max: 100 |
The image compression quality (for lossy formats like JPEG and WebP). 100 = best quality, 0 = lowest quality.
|
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'}