You're looking at a specific version of this model. Jump to the model overview.

kevin51jiang /ic-light:bd4985f1

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
string (enum)
None

Options:

None, Left Light, Right Light, Top Light, Bottom Light

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
string (enum)
webp

Options:

webp, jpg, png

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.

Schema
{'items': {'format': 'uri', 'type': 'string'},
 'title': 'Output',
 'type': 'array'}