> ## Documentation Index > Fetch the complete documentation index at: https://docs.poyo.ai/llms.txt > Use this file to discover all available pages before exploring further. # Flux 3 Klein > Generate or edit images with reference images and output up to 4K. 1. After submission, a `task_id` will be returned. If you provided a `callback_url`, when the task status becomes `finished` or `failed`, a POST request will be sent to the `callback_url`. 2. Regardless of whether `callback_url` is provided, you can retrieve the response result through the unified [Query Task Status](/api-manual/task-management/status) endpoint. Flux 3 Klein creates images from text and edits or combines reference images. Use it for product photography, illustrations, and reference-based compositions. ## Models * **flux-3-klein** — Text-to-image generation * **flux-3-klein-edit** — Image editing with up to 10 references ## Features * Generate 1–4 images per request in PNG, JPEG, or WebP. * Choose 1K, 2K, or 4K output with an aspect ratio or exact pixel dimensions. * Edit or combine up to 10 reference images. ## Input modes | Mode | Model | Input | | - | - | - | | Text to image | `flux-3-klein` | Describe the target image in `prompt`. | | Image editing | `flux-3-klein-edit` | Supply `prompt` and 1–10 URLs in `image_urls`. | The generation model does not accept reference images. For editing, refer to images in their supplied order, such as “the first image”. ## Required parameters * `prompt` (string): Non-empty description of the complete target image, including the subject, framing, background, lighting, and desired edits. * `image_urls` (array of strings): Required for `flux-3-klein-edit` only. Supply 1–10 publicly accessible HTTP(S) reference image URLs. ## Optional parameters * `size` (string): `1:1`, `4:3`, `3:4`, `16:9`, `9:16`, `3:2`, `2:3`, or an exact `WIDTHxHEIGHT` value. Defaults to `1:1` in both modes. * `resolution` (string): `1K`, `2K`, or `4K`. Defaults to `1K`; custom pixel dimensions require an explicit matching value. * `n` (integer): Number of output images, from 1 through 4. Defaults to 1. * `output_format` (string): `png` (default), `jpeg`, or `webp`. * `enable_safety_checker` (boolean): Enable content safety checking. Defaults to `true`. ## Size For an aspect ratio, `resolution` sets the long edge to 1024, 2048, or 4096 pixels. The short edge follows the requested ratio and is rounded to the nearest multiple of 16. For custom `WIDTHxHEIGHT` dimensions, each side must be 256–4096 pixels and divisible by 16. Supply `resolution` explicitly using the tier determined by the longer side: | Longer side | Required resolution | | - | - | | 256–1024 pixels | `1K` | | Above 1024 through 2048 pixels | `2K` | | Above 2048 through 4096 pixels | `4K` | For example, `size: "1536x1024"` requires `resolution: "2K"`. ## Examples The OpenAPI examples include generation, reference editing, and custom dimensions. ## Notes Keep all generation parameters inside `input`; `callback_url` belongs at the request's top level. ## OpenAPI ````yaml api-manual/image-series/flux-3-klein.json POST /api/generate/submit openapi: 3.0.0 info: title: PoYo AI - Flux 3 Klein API description: >- Generate or edit images with up to ten reference images and 1K, 2K, or 4K output. version: 1.0.0 servers: - url: https://api.poyo.ai description: Production server security: - BearerAuth: [] paths: /api/generate/submit: post: tags: - Flux 3 Klein summary: Submit a Flux 3 Klein task operationId: submitFlux3KleinTask requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/SubmitRequest' examples: text-to-image: summary: Generate an image value: model: flux-3-klein input: prompt: A red fox in fresh snow at sunrise size: '3:2' resolution: 2K edit-image: summary: Edit a reference image value: model: flux-3-klein-edit input: prompt: >- Keep the product from the first image and place it in a sunlit studio image_urls: - https://example.com/product.png size: '4:3' resolution: 1K custom-size: summary: Use an exact pixel size value: model: flux-3-klein input: prompt: An editorial portrait with soft window light size: 1536x1024 resolution: 2K responses: '200': description: Task submitted successfully content: application/json: schema: $ref: '#/components/schemas/SubmitResponse' '400': description: Invalid request parameters content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' components: schemas: SubmitRequest: type: object required: - model - input additionalProperties: false properties: model: type: string enum: - flux-3-klein - flux-3-klein-edit description: Public model identifier. callback_url: type: string format: uri description: Webhook URL for finished or failed task notifications. input: type: object required: - prompt additionalProperties: false properties: prompt: type: string minLength: 1 pattern: \S description: >- Describe the complete target image, including the subject, framing, background, and lighting. image_urls: type: array minItems: 1 maxItems: 10 items: type: string format: uri pattern: ^https?://\S+$ description: >- Required for flux-3-klein-edit only. Supply 1-10 reference image URLs. Do not send this field for flux-3-klein. size: type: string default: '1:1' description: >- Output aspect ratio: 1:1, 4:3, 3:4, 16:9, 9:16, 3:2, or 2:3; or exact WIDTHxHEIGHT pixels. Custom dimensions must each be 256-4096, divisible by 16, and accompanied by an explicit matching resolution. resolution: type: string enum: - 1K - 2K - 4K default: 1K description: >- Output resolution tier. For an aspect ratio, the long edge is 1024, 2048, or 4096 pixels and the short edge is rounded to the nearest multiple of 16. For custom dimensions, the long edge selects the tier: at most 1024 = 1K, above 1024 through 2048 = 2K, above 2048 through 4096 = 4K. 'n': type: integer minimum: 1 maximum: 4 default: 1 description: Number of output images. output_format: type: string enum: - jpeg - png - webp default: png description: Output image format. enable_safety_checker: type: boolean default: true description: Enable content safety checking. description: >- Parameters for the selected model. Media fields are required only for their corresponding mode. description: >- Generate or edit images with up to ten reference images and 1K, 2K, or 4K output. x-poyo-model-requests: $ref: '#/components/schemas/ModelRequests' SubmitResponse: type: object required: - code - data properties: code: type: integer enum: - 200 example: 200 data: type: object required: - task_id - status - created_time properties: task_id: type: string example: task-unified-1792468800-example status: type: string enum: - not_started example: not_started created_time: type: string format: date-time example: '2026-10-20T12:00:00' ErrorResponse: type: object required: - error properties: error: type: object required: - message - type properties: message: type: string example: Invalid request parameters type: type: string example: invalid_request_error securitySchemes: BearerAuth: type: http scheme: bearer bearerFormat: API Key description: 'Use Authorization: Bearer PoYo_API_KEY.' ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.