> ## Documentation Index > Fetch the complete documentation index at: https://docs.magnific.com/llms.txt > Use this file to discover all available pages before exploring further. # Edit Image > Edit or recompose one or more input images from a text prompt using OpenAI's GPT Image 2 model. **Key Features:** - Accepts 1-16 input images, used together as the visual context - Restyle a single image, or compose a new one from several - Same output controls as text-to-image (resolution, aspect ratio, format, compression, quality) **Best for:** - Product and scene variations from an existing shot - Combining a subject, a background and a style reference in one call - Adding or correcting text on an existing image **Output:** one edited image per `num_images` (up to 10), delivered as CDN URLs in the task's `generated` array. The input images are never modified. **Credits:** editing sends your images to the model and their input tokens dominate the cost, so it is priced differently from generation: flat units per output image by `quality` (`low` x1, `medium` x4, `high` x6), with `resolution` not affecting the price. The request is processed asynchronously: the endpoint returns a task id immediately. Retrieve the result by polling the task endpoint or by providing an optional `webhook_url`. ## OpenAPI ````yaml POST /v1/ai/text-to-image/gpt-image-2-edit openapi: 3.0.0 info: description: >- The Magnific API is your gateway to a vast collection of high-quality digital resources for your applications and projects. As a leading platform, it offers a wide range of graphics, including vectors, photos, illustrations, icons, PSD templates, and more, all curated by talented designers from around the world. title: Magnific API version: 1.0.0 servers: - description: B2B API Production V1 url: https://api.magnific.com security: - magnificApiKey: [] paths: /v1/ai/text-to-image/gpt-image-2-edit: post: tags: - text-to-image summary: Edit images from text - GPT Image 2 description: > Edit or recompose one or more input images from a text prompt using OpenAI's GPT Image 2 model. **Key Features:** - Accepts 1-16 input images, used together as the visual context - Restyle a single image, or compose a new one from several - Same output controls as text-to-image (resolution, aspect ratio, format, compression, quality) **Best for:** - Product and scene variations from an existing shot - Combining a subject, a background and a style reference in one call - Adding or correcting text on an existing image **Output:** one edited image per `num_images` (up to 10), delivered as CDN URLs in the task's `generated` array. The input images are never modified. **Credits:** editing sends your images to the model and their input tokens dominate the cost, so it is priced differently from generation: flat units per output image by `quality` (`low` x1, `medium` x4, `high` x6), with `resolution` not affecting the price. The request is processed asynchronously: the endpoint returns a task id immediately. Retrieve the result by polling the task endpoint or by providing an optional `webhook_url`. operationId: edit_image_from_text_gpt_image_2 requestBody: content: application/json: examples: required-params: $ref: '#/components/examples/request-gpt-image-2-edit-required-params' all-params: $ref: '#/components/examples/request-gpt-image-2-edit-all-params' schema: $ref: '#/components/schemas/ttigi2-edit-request-content' required: true responses: '200': content: application/json: examples: success - in progress task: $ref: '#/components/examples/200-task-in-progress' schema: $ref: >- #/components/schemas/get_style_transfer_task_status_200_response description: >- OK - The request has succeeded and the GPT Image 2 Edit process has started. '400': $ref: '#/components/responses/400-bad-request' '401': $ref: '#/components/responses/401-unauthorized' '500': $ref: '#/components/responses/500-internal-server-error' '503': $ref: '#/components/responses/503-service-unavailable' components: examples: request-gpt-image-2-edit-required-params: description: A prompt and at least one reference image. summary: Minimum request value: prompt: Put the product on a marble surface, keep the label unchanged reference_images: - https://example.com/product.jpg request-gpt-image-2-edit-all-params: description: > Composes one image from three references. Editing is billed as flat units of the low tier by quality (low x1, medium x4, high x6) times num_images; resolution does not change the price of an edit. summary: Every parameter value: prompt: >- Place the subject from Image0 on the background of Image1, in the style of Image2 reference_images: - https://example.com/subject.jpg - https://example.com/background.jpg - upl_img_0123456789abcdef num_images: 2 resolution: 1k aspect_ratio: square_1_1 quality: high output_format: png background: auto moderation: auto webhook_url: https://www.example.com/webhook 200-task-in-progress: summary: Success - Task in progress value: data: generated: [] task_id: 046b6c7f-0b8a-43b9-b35d-6489e6daee91 status: IN_PROGRESS schemas: ttigi2-edit-request-content: properties: prompt: description: > Text instruction describing the edit to apply to the reference images. **Tips:** - Say what should change, not what the image already contains - Several references are used together as one visual context - Text inside the image can be corrected or replaced verbatim **Examples:** - Simple: "Put the product on a marble surface" - Detailed: "Replace the background with a sunlit studio, keep the product and its shadow, change the label text to ORGANIC" example: Put the product on a marble surface maxLength: 32000 minLength: 1 type: string reference_images: description: > The images to edit, in order. GPT Image 2 uses them together as the visual context for the prompt: it can restyle one image, or compose a new image from several. Each image may be up to 20 MiB, and one request may carry up to 64 MiB of images in total. items: description: > Image URL (must be publicly reachable over HTTPS), a base64-encoded image, or an upload id returned by the uploads API. Supported formats: jpg, jpeg, png, webp. example: https://example.com/product.jpg type: string maxItems: 16 minItems: 1 type: array webhook_url: description: > Optional callback URL that will receive asynchronous notifications whenever the task changes status. The payload sent to this URL is the same as the corresponding GET endpoint response, but without the data field. example: https://www.example.com/webhook format: uri type: string num_images: default: 1 description: | How many images to generate for this prompt. **Each image is billed separately.** example: 1 maximum: 10 minimum: 1 type: integer resolution: default: 1k description: > Resolution tier of the generated image. Combined with `aspect_ratio` it selects the exact pixel size. **Credits:** the tier multiplies the price set by `quality` — `1k` x1, `2k` x2, `4k` x3. On the edit endpoint it does not affect the price. enum: - 1k - 2k - 4k example: 1k type: string aspect_ratio: default: square_1_1 description: > Image size with the aspect ratio. The aspect ratio is the proportional relationship between an image's width and height, expressed as *_width_height (e.g., square_1_1, widescreen_16_9). It is calculated by dividing the width by the height. If not present, the default is `square_1_1`. enum: - square_1_1 - classic_4_3 - traditional_3_4 - widescreen_16_9 - social_story_9_16 - film_horizontal_21_9 - standard_3_2 - portrait_2_3 - horizontal_2_1 - banner_3_1 example: square_1_1 type: string quality: default: high description: > Render quality tier. Higher tiers spend more provider compute and cost more credits; lower tiers are faster and cheaper. - `low`: fastest and cheapest, for drafts and iteration - `medium`: balanced - `high`: maximum detail and prompt adherence (default) enum: - low - medium - high example: high type: string output_format: default: png description: > The file format of the generated image. - `png`: lossless, supports transparency. Best for logos, text and sharp edges - `jpeg`: compressed, no transparency. Smallest files for photographic content - `webp`: compressed, supports transparency `output_compression` only applies to `jpeg` and `webp`. enum: - png - jpeg - webp example: png type: string background: description: > How the image background is produced. - `opaque`: always render a filled background - `auto`: let the model decide, which may return a transparent background Transparency is only preserved by formats that support an alpha channel (`png`, `webp`). When omitted, the provider default applies. enum: - opaque - auto example: auto type: string output_compression: description: | Compression level for the generated image, where 100 is the least compressed. Only applies when `output_format` is `jpeg` or `webp`; ignored for `png`. example: 80 maximum: 100 minimum: 0 type: integer moderation: default: auto description: | Strictness of the model provider's own content filter. - `auto`: the provider's standard filtering (default) - `low`: less restrictive filtering This is the model provider's filter and is applied in addition to Freepik's platform moderation, which cannot be disabled. enum: - auto - low example: auto type: string required: - prompt - reference_images type: object get_style_transfer_task_status_200_response: example: data: generated: - https://openapi-generator.tech - https://openapi-generator.tech task_id: 046b6c7f-0b8a-43b9-b35d-6489e6daee91 status: CREATED properties: data: $ref: '#/components/schemas/task-detail' required: - data type: object task-detail: allOf: - $ref: '#/components/schemas/task' - properties: generated: items: description: URL of the generated image format: uri type: string type: array required: - generated type: object example: generated: - https://openapi-generator.tech - https://openapi-generator.tech task_id: 046b6c7f-0b8a-43b9-b35d-6489e6daee91 status: CREATED inline_object: example: message: message properties: message: type: string type: object inline_object_1: properties: problem: $ref: '#/components/schemas/inline_object_1_problem' type: object inline_object_2: example: message: Internal Server Error properties: message: example: Internal Server Error type: string type: object inline_object_3: example: message: Service Unavailable. Please try again later. properties: message: example: Service Unavailable. Please try again later. type: string type: object task: example: task_id: 046b6c7f-0b8a-43b9-b35d-6489e6daee91 status: CREATED properties: task_id: description: Task identifier format: uuid type: string status: description: Task status enum: - CREATED - IN_PROGRESS - COMPLETED - FAILED type: string required: - status - task_id type: object inline_object_1_problem: properties: message: example: Validation error type: string invalid_params: items: $ref: '#/components/schemas/inline_object_1_problem_invalid_params_inner' type: array required: - invalid_params - message type: object inline_object_1_problem_invalid_params_inner: properties: name: description: Name of the invalid parameter. example: page type: string field: description: Field of the invalid parameter. Mirrors `name`. example: page type: string reason: example: Parameter 'page' must be greater than 0 type: string required: - field - name - reason type: object responses: 400-bad-request: content: application/json: examples: invalid_page: summary: Parameter 'page' is not valid value: message: Parameter 'page' must be greater than 0 invalid_query: summary: Parameter 'query' is not valid value: message: Parameter 'query' must not be empty invalid_filter: summary: Parameter 'filter' is not valid value: message: Parameter 'filter' is not valid generic_bad_request: summary: Bad Request value: message: Parameter ':attribute' is not valid schema: $ref: '#/components/schemas/inline_object' application/problem+json: examples: invalid_page: summary: Parameter 'page' is not valid value: message: Validation error invalid_params: - field: page reason: Parameter 'page' must be greater than 0 - field: per_page reason: Parameter 'per_page' must be greater than 0 schema: $ref: '#/components/schemas/inline_object_1' description: >- Bad Request - The server could not understand the request due to invalid syntax. 401-unauthorized: content: application/json: examples: invalid_api_key: summary: API key is not valid value: message: Invalid API key missing_api_key: summary: API key is not provided value: message: Missing API key schema: $ref: '#/components/schemas/inline_object' description: >- Unauthorized - The client must authenticate itself to get the requested response. 500-internal-server-error: content: application/json: schema: $ref: '#/components/schemas/inline_object_2' description: >- Internal Server Error - The server has encountered a situation it doesn't know how to handle. 503-service-unavailable: content: application/json: schema: $ref: '#/components/schemas/inline_object_3' description: Service Unavailable securitySchemes: magnificApiKey: description: > Your Magnific API key. Required for authentication. [Learn how to obtain an API key](https://docs.magnific.com/quickstart) in: header name: x-magnific-api-key type: apiKey ````