IC-Light-v2 for Image Relighting

All image to image models

Image to Image

An endpoint for re-lighting photos and changing their backgrounds per a given description

Inference$ Commercial useFrom 8 credits per run

About IC-Light-v2 for Image Relighting

An endpoint for re-lighting photos and changing their backgrounds per a given description

relightingediting

Pricing

A run with the default settings costs 8 credits. The exact cost updates in the playground as you change settings, and you're only charged when you press Run. Failed runs are refunded automatically.

Inputs

prompttextarearequired

The prompt to generate an image from.

negative_prompttextareadefault: ""

Negative Prompt for the image

image_urlfilerequired

URL of image to be used for relighting

mask_image_urlfile

URL of mask to be used for ic-light conditioning image

background_thresholdnumberdefault: 0.67

Threshold for the background removal algorithm. A high threshold will produce sharper masks. Note: This parameter is currently deprecated and has no effect on the output.

image_sizeselect

The size of the generated image.

Options: square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9

num_inference_stepsintegerdefault: 28

The number of inference steps to perform.

seedinteger

The same seed and the same prompt given to the same version of the model will output the same image every time.

initial_latentselectdefault: "None"

Provide lighting conditions for the model

Options: None, Left, Right, Top, Bottom

enable_hr_fixbooleandefault: false

Use HR fix

sync_modebooleandefault: false

If `True`, the media will be returned as a data URI and the output data won't be available in the request history.

num_imagesintegerdefault: 1

The number of images to generate.

cfgnumberdefault: 1

The real classifier-free-guidance scale for the generation.

lowres_denoisenumberdefault: 0.98

Strength for low-resolution pass.

highres_denoisenumberdefault: 0.95

Strength for high-resolution pass. Only used if enable_hr_fix is True.

hr_downscalenumberdefault: 0.5

guidance_scalenumberdefault: 5

The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.

enable_safety_checkerbooleandefault: true

If set to true, the safety checker will be enabled. Disabling it requires account authorization; unauthorized requests are always checked.

output_formatselectdefault: "jpeg"

The format of the generated image.

Options: jpeg, png

Related image to image models

Nano Banana Pro

Nano Banana Pro is Google's new state-of-the-art image generation and editing model

realismtypography

image-to-image

Nano Banana 2

Nano Banana 2 is Google's new state-of-the-art image generation and editing model

image-to-image

Nano Banana 2.1 Edit

Nano Banana 2.1 Edit by Google transforms reference images using text instructions, with output resolutions up to 4K and optional video or PDF context.

image editingimage to image

image-to-image

GPT Image 2.5 Sunburst Edit

Editing built for the tightest control, edits scoped precisely to the instruction, with subject and composition preserved across many rounds of revision.

stylizedtransform

image-to-image

✦ new

GPT Image 2.6 Sunburst Edit

Editing built for the tightest control, edits scoped precisely to the instruction, with subject and composition preserved across many rounds of revision.

stylizedtransform

image-to-image

GPT Image 2 API

GPT Image 2, OpenAI's latest image model, is capable of making fine-grained, detailed edits to images.

gpt-image-2openai

image-to-image

Nano Banana

Google's famous original image generation and editing model

image-editing

image-to-image

GPT Image 2.5 Flare Edit

Precise image editing that changes only what's asked, keeping subject, composition, and background intact, with reference subjects staying recognizable across styles and successive edits.

stylizedtransform

image-to-image

✦ new

GPT Image 2.6 Flare Edit

Precise image editing that changes only what's asked, keeping subject, composition, and background intact, with reference subjects staying recognizable across styles and successive edits.

stylizedtransform

image-to-image

Seedream 5.0 Pro Image Editing

Seedream 5.0 Pro is grounded, region-precise image editing model that changes one element while keeping the rest of the frame intact with layer separation, sketch completion, and up to 10 reference images.

realismtypography

image-to-image

SeedVR2

Use SeedVR2 to upscale your images

upscale

image-to-image

FLUX.1 Kontext [pro]

FLUX.1 Kontext [pro] handles both text and reference images as inputs, seamlessly enabling targeted, local edits and complex transformations of entire scenes.

image-to-image