zsxkib/ic-light-background

🖼️✨Background images + prompts to auto-magically relights your images (+normal maps🗺️)

Capabilities

1:1 4:3 3:4 16:9 9:16 2:3 3:2 Negative Prompt Seed

Cost

Community model (estimated from hardware time)

Input Parameters

Name	Type	Description	Default	Constraints
`background_image` *	string (uri)	The background image that will be used to relight the main foreground image	`—`	—
`prompt` *	string	A text description guiding the relighting and generation process	`—`	—
`subject_image` *	string (uri)	The main foreground image to be relighted	`—`	—
`appended_prompt`	string	Additional text to be appended to the main prompt, enhancing image quality	`"best quality"`	—
`cfg`	number	Classifier-Free Guidance scale - higher values encourage adherence to prompt, lower values encourage more creative interpretation	`2`	min: 1, max: 32
`compute_normal`	boolean	Whether to compute the normal maps (slower but provides additional output images)	`false`	—
`height`	integer	The height of the generated images in pixels	`640`	256 320 384 448 512 576 640 704 768 832 896 960 1024
`highres_denoise`	number	Controls the amount of denoising applied when refining the high resolution output (higher = more adherence to the upscaled latent, lower = more creative details added)	`0.5`	min: 0.1, max: 1
`highres_scale`	number	The multiplier for the final output resolution relative to the initial latent resolution	`1.5`	min: 1, max: 3
`light_source`	string	The type and position of lighting to apply to the initial background latent	`"Use Background Image"`	Use Background Image Use Flipped Background Image Left Light Right Light Top Light Bottom Light Ambient
`negative_prompt`	string	A text description of attributes to avoid in the generated images	`"lowres, bad anatomy, bad hands, cropped, worst quality"`	—
`number_of_images`	integer	The number of unique images to generate from the given input and settings	`1`	min: 1, max: 12
`output_format`	string	The image file format of the generated output images	`"webp"`	webp jpg png
`output_quality`	integer	The image compression quality (for lossy formats like JPEG and WebP). 100 = best quality, 0 = lowest quality.	`80`	min: 0, max: 100
`seed`	integer	A fixed random seed for reproducible results (omit this parameter for a randomized seed)	`—`	—
`steps`	integer	The number of diffusion steps to perform during generation (more steps generally improves image quality but increases processing time)	`25`	min: 1, max: 100
`width`	integer	The width of the generated images in pixels	`512`	256 320 384 448 512 576 640 704 768 832 896 960 1024

background_image required string

The background image that will be used to relight the main foreground image

prompt required string

A text description guiding the relighting and generation process

subject_image required string

The main foreground image to be relighted

appended_prompt string

Additional text to be appended to the main prompt, enhancing image quality

Default: "best quality"

cfg number

Classifier-Free Guidance scale - higher values encourage adherence to prompt, lower values encourage more creative interpretation

Default: 2 min: 1, max: 32

compute_normal boolean

Whether to compute the normal maps (slower but provides additional output images)

Default: false

height integer

The height of the generated images in pixels

Default: 640

256 320 384 448 512 576 640 704 768 832 896 960 1024

highres_denoise number

Controls the amount of denoising applied when refining the high resolution output (higher = more adherence to the upscaled latent, lower = more creative details added)

Default: 0.5 min: 0.1, max: 1

highres_scale number

The multiplier for the final output resolution relative to the initial latent resolution

Default: 1.5 min: 1, max: 3

light_source string

The type and position of lighting to apply to the initial background latent

Default: "Use Background Image"

Use Background Image Use Flipped Background Image Left Light Right Light Top Light Bottom Light Ambient

negative_prompt string

A text description of attributes to avoid in the generated images

Default: "lowres, bad anatomy, bad hands, cropped, worst quality"

number_of_images integer

The number of unique images to generate from the given input and settings

Default: 1 min: 1, max: 12

output_format string

The image file format of the generated output images

Default: "webp"

webp jpg png

output_quality integer

The image compression quality (for lossy formats like JPEG and WebP). 100 = best quality, 0 = lowest quality.

Default: 80 min: 0, max: 100

seed integer

A fixed random seed for reproducible results (omit this parameter for a randomized seed)

steps integer

The number of diffusion steps to perform during generation (more steps generally improves image quality but increases processing time)

Default: 25 min: 1, max: 100

width integer

The width of the generated images in pixels

Default: 512

256 320 384 448 512 576 640 704 768 832 896 960 1024

Version: 60015df78a8a Updated: 6/8/2026 48.6K runs