Image Generation

Magic Lighting API

Relight images with Magic Lighting, Nano Banana Pro/2, or Qwen Image Edit — multi-provider routing with per-model credit rates. Integrate this model via REST with endpoint docs, parameters, and code examples.

Compare image models Use cases

Img2Img

Credit Cost

1 credit

Type

Image

Get API Key

Create auth keys for apps and agents

See Usage

Track requests, credits, and logs

Buy Credits

Top up prepaid API capacity

API Endpoint

POST

/api/v1/models/image-relighting/run

Test This Model

Run a real request through the API pipeline and inspect the exact input and output your integration will handle. Uses your credits like any API call; failed runs are refunded automatically.

LLM.txt

AI-Ready

For AI assistants

Copy this model's documentation into Claude, GPT, or any AI for instant integration help.

/llm/image-relighting.txt

OpenAPI Spec

Swagger compatible

Import into Postman, Swagger UI, or generate client SDKs in any language.

/api/openapi

Parameters

Input parameters accepted by this model

Parameter	Type	Description	Default
`subject_image` required	url	URL of the image to relight.	-
`prompt`	string	Describe the desired lighting (e.g. "cinematic neon lighting", "golden hour").	-
`light_source`	string	Optional direction / type of the light source.	-
`model_type`	enum	Which underlying relighting model to use. `magic-lightingnano-banana-pronano-banana-2qwen-image-edit`	`magic-lighting`
`number_of_images`	integer	How many variations to generate (1-12). min: 1 \| max: 12	`1`
`aspectRatio`	enum	Output aspect ratio. `1:116:99:164:33:4`+2 more	`1:1`
`negative_prompt`	string	What to avoid in the output.	-
`appended_prompt`	string	Quality keywords appended to every prompt (Magic Lighting only).	`best quality`
`output_format`	enum	Image encoding format. `pngjpgwebp`	`png`
`width`	string	Output width in pixels (Magic Lighting only).	`1024`
`height`	string	Output height in pixels (Magic Lighting only).	`1024`
`steps`	integer	Diffusion steps (Magic Lighting only; higher = slower + sharper). min: 10 \| max: 50	`25`
`cfg`	number	Prompt adherence (Magic Lighting only).	`2`
`highres_scale`	number	Upscale factor for the highres pass (Magic Lighting only).	`1.5`
`highres_denoise`	number	Denoise strength for the highres pass (Magic Lighting only).	`0.5`
`lowres_denoise`	number	Denoise strength for the initial pass (Magic Lighting only).	`0.9`
`output_quality`	integer	Image quality 1-100. min: 1 \| max: 100	`100`
`seed`	integer	Random seed for reproducibility.	-

Use saved characters (@Name)

This model takes no reference images, so @Name of a saved character is refused (400) before anything is charged. A saved location, prop or style with a description is inserted as text. For saved characters, use a model that takes reference images, such as Nano Banana Pro or Seedream 5 for images, or Seedance 2.5 or WAN 3.0 for video.

Example Outputs

Real outputs generated by this model

View Details

cinematic golden hour lighting from the left

2 credits

15.3s

Code Examples

Magic lighting — copy and paste to get started

bash

curl -X POST "https://pixeldojo.ai/api/v1/models/image-relighting/run" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "subject_image": "https://...",
    "prompt": "cinematic neon lighting",
    "model_type": "magic-lighting"
  }'

Response Format

Submit Response (202 Accepted)

json

{
  "jobId": "job_abc123...",
  "status": "pending",
  "statusUrl": "https://pixeldojo.ai/api/v1/jobs/job_abc123...",
  "creditCost": 1,
  "creditsRemaining": 95,
  "expiresAt": "2026-10-10T02:49:30Z"
}

Completed Response

json

{
  "jobId": "job_abc123...",
  "status": "completed",
  "output": {
    "images": [
      "https://temp.pixeldojo.ai/pixeldojotemp/1705930123-456789.png"
    ]
  },
  "creditCost": 1,
  "expiresAt": "2026-10-10T02:49:30Z"
}

LLM Documentation Try in Web UI Get API Key Usage Dashboard Buy Credits