> ## Documentation Index > Fetch the complete documentation index at: https://docs.bfl.ml/llms.txt > Use this file to discover all available pages before exploring further. # Generate an image with FLUX 3 > Generate or edit images with FLUX 3 and retrieve the asynchronous result. ## OpenAPI ````yaml openapi/flux-3-image.json POST /v1/flux-3-image openapi: 3.1.0 info: title: FLUX 3 Image version: 1.0.0 servers: - url: https://api.bfl.ai security: [] paths: /v1/flux-3-image: post: summary: Generate an image with FLUX 3 description: >- Generate an image from a prompt. Add up to ten reference images to edit an image, restyle it, or combine references into a new composition; describe how to use them in `prompt`. There is no `mode` field. Unknown fields return `422`. operationId: generate_flux_3_image requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ImageInputs' examples: Text to image: summary: Text to image value: prompt: >- Ultra-wide cinematic shot of a fog-drenched coastal highway at dawn, cliffs on one side, turquoise sea on the other, a single vintage car with headlights on, soft golden rim light aspect_ratio: '21:9' Edit an image: summary: Edit an image value: prompt: 'change the color of only one bird in the middle to #e01075' images: - >- https://cdn.sanity.io/images/2gpum2i6/production/4792198dfeba9223bf3ecf020fed2942de7f0bd7-1800x1200.webp Multi reference: summary: Multi reference value: prompt: Turn Image 1 in the Style of Image 2 images: - >- https://cdn.sanity.io/images/2gpum2i6/production/ababcf5c9cf86074d71c92d6362ff63545d90661-1800x1201.webp - >- https://cdn.sanity.io/images/2gpum2i6/production/dc642f5b01040c4afc46c1b4f8c4945152932683-1350x1800.webp Layout with boxes: summary: Layout with boxes value: prompt: >- Minimalist graphic illustration featuring a black silhouette of a person centered against a solid, vibrant chartreuse background . The figure is captured in a dynamic, mid-stride running pose, facing toward the left side of the frame. The image relies entirely on the high-contrast relationship between the two colors, mimicking a digital recreation of a screen-printed or risograph aesthetic, with no discernible light source or shadow. [{"id":"background_1","bbox":[0,0,1000,1000],"desc":"A flat field of neon yellow-green possessing a subtle, tactile paper texture with fine, organic grain and slight variations in color saturation, giving the flat surface a sense of physical depth."},{"id":"silhouette_1","bbox":[150,150,850,850],"desc":"A black silhouette of a person in motion, composed of a dense, stippled texture that resembles physical ink on paper or a low-resolution digital dither. The leading edges, including the front of the head, chest, and forward leg, are relatively solid and opaque. The trailing edges, such as the back, outstretched rear arm, and lifted back leg, dissolve into a spray of coarse, square-shaped pixels and scattered dots. The black ink shows a slight textural irregularity, as if pressed onto a porous surface."}] aspect_ratio: '1:1' Edit with boxes: summary: Edit with boxes value: prompt: >- In , change the large tiger and the small glowing butterfly to be pink. Keep the massive fallen log , the falling snow , and the dark background trees exactly unchanged. [{"id":"animal_1","from":null,"src_bbox":null,"tgt_bbox":[250,50,850,650],"desc":"Make both pink."},{"id":"insect_1","from":null,"src_bbox":null,"tgt_bbox":[650,680,750,750],"desc":"Make both pink."},{"id":"log_1","from":"ref_image_0","src_bbox":[600,0,1000,1000],"tgt_bbox":[600,0,1000,1000],"desc":"A massive, fallen tree log stretching horizontally across the foreground. The surface features deep, rough-textured bark, weathered cracks, and small pockets of frost."},{"id":"snow_1","from":"ref_image_0","src_bbox":[0,0,1000,1000],"tgt_bbox":[0,0,1000,1000],"desc":"Numerous white snowflakes of varying sizes falling across the scene. Some flakes are sharp and distinct, while others closer to the lens appear as blurred white streaks."},{"id":"trees_1","from":"ref_image_0","src_bbox":[0,0,650,1000],"tgt_bbox":[0,0,650,1000],"desc":"A dense stand of tall, dark, vertical tree trunks receding into the distance. A cool, blue misty light permeates the spaces between the trees, glowing most intensely from the right edge."}] images: - >- https://cdn.sanity.io/images/2gpum2i6/production/b6476b163e11444d6d5490ac1fa1e610d4eab85e-1360x768.webp Move with boxes: summary: Move with boxes value: prompt: >- In , move the miniature grey amigurumi knight figure upwards and to the left along the yarn cliff . Leave the polished steel tapestry needle in its original position in the air. Keep the rest of the image completely unchanged, preserving the blurred yarn backdrop , the large knitted dragon , and the fiery orange thread suspended between them. [{"id":"knight_1","from":"ref_image_0","src_bbox":[500,150,850,350],"tgt_bbox":[194,55,544,255],"desc":"A miniature amigurumi knight figure crocheted from thick grey woolen yarn. It has visible, intricate stitches forming a rounded helmet shape and a cylindrical body, with tiny stubby arms reaching upwards against the cliff."},{"id":"backdrop_1","from":"ref_image_0","src_bbox":[0,0,1000,1000],"tgt_bbox":[0,0,1000,1000],"desc":"A soft, out-of-focus expanse of cream ivory and melange indigo knitted yarn, providing a blurred studio backdrop with tangible fiber fuzz catching the ambient light."},{"id":"cliff_1","from":"ref_image_0","src_bbox":[300,0,1000,450],"tgt_bbox":[300,0,1000,450],"desc":"A steep, uneven cliff face constructed from stacked, thick yarn skeins in rich shades of mustard yellow, terracotta, and melange indigo, featuring visible woven wool textures and loose, stray fiber strands."},{"id":"needle_1","from":"ref_image_0","src_bbox":[420,250,550,450],"tgt_bbox":[420,250,550,450],"desc":"A real, oversized polished steel tapestry needle, gleaming under the studio lighting. It features a blunt tip and an elongated eye, grasped like a weapon in the knight's yarn-stub hand."},{"id":"dragon_1","from":"ref_image_0","src_bbox":[100,600,950,1000],"tgt_bbox":[100,600,950,1000],"desc":"A large, fluffy knitted dragon made of highly textured, fuzzy yarn in terracotta and mustard yellow. It has a rounded snout, large crocheted eyes, and a wide-open mouth, with visible loose fibers creating a soft, tactile surface."},{"id":"fire_1","from":"ref_image_0","src_bbox":[350,400,650,650],"tgt_bbox":[350,400,650,650],"desc":"Curled, sculptural puffs of fiery orange angora thread, suspended in mid-air. The thread is highly textured, fuzzy, and chaotic, bursting from the dragon's mouth and stretching horizontally across the center."}] images: - >- https://cdn.sanity.io/images/2gpum2i6/production/aa7b28af831835fcef86e770262c8c30fa308c2c-1360x768.webp responses: '200': description: >- Poll the returned regional `polling_url` with `x-key`. Keep polling while `status` is `Pending`, `Reasoning`, or `Generating`. When it is `Ready`, download the image from `result.sample`; this signed URL expires after **1 hour**. Stop on `Error`, `Request Moderated`, `Content Moderated`, or `Task not found`. Polling errors may use HTTP `503` with a regular JSON body; inspect `status`. content: application/json: schema: $ref: '#/components/schemas/AsyncResponse' '400': description: Rejected input, including a reference image above 16 megapixels. content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' '422': description: >- Validation error, including unknown fields, a blank prompt, invalid parameter values, or a reference image below 256 × 256 pixels. content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' security: - APIKeyHeader: [] components: schemas: ImageInputs: title: FLUX 3 Image request type: object additionalProperties: false required: - prompt properties: prompt: type: string minLength: 1 pattern: \S description: >- Non-blank text describing the image to generate or the edit to apply. To place elements, name each one as `` in the text, then end the prompt with a JSON list of rows, one per element. Each `bbox` is `[top, left, bottom, right]` on a 0 to 1000 grid, so `[0, 0, 500, 500]` is the top-left quarter of the output: ```text A black silhouette of a running person on a flat chartreuse background . [ {"id": "background_1", "bbox": [0, 0, 1000, 1000], "desc": "chartreuse field"}, {"id": "runner_1", "bbox": [150, 150, 850, 850], "desc": "running silhouette"} ] ``` In an edit, rows use `from`, `src_bbox`, and `tgt_bbox` instead of `bbox`. There is no separate box field, and an `entities` field returns `422`. For full requests, choose **Layout with boxes** or **Edit with boxes** in the request examples. [Layout and editing](/flux_3/flux3_image_layout) lists every row field. images: description: >- One reference image or a list of 1 to 10 images, each as an HTTP(S) URL or a base64 string. A data URI prefix is accepted. Each image must be at least 256 × 256 pixels and at most 16 megapixels; each base64 payload must be at most 20 MB. Inputs over 16 megapixels are rejected with `400`, inputs below 256 × 256 pixels with `422`. oneOf: - type: string minLength: 1 - type: array minItems: 1 maxItems: 10 items: type: string minLength: 1 aspect_ratio: type: string enum: - auto - '21:9' - '2:1' - '16:9' - '3:2' - '7:5' - '4:3' - '5:4' - '1:1' - '4:5' - '3:4' - '5:7' - '2:3' - '9:16' - '1:2' - '9:21' default: auto description: >- With `auto`, output follows the first reference image's aspect ratio, or uses `1:1` when there is no reference image. resolution: type: string enum: - 768sq - 1k - 2k - 4k default: 1k description: >- Choose the output size. Check `output_mp` in the submit response for the exact size in megapixels. Generating at `4k` can take several minutes. safety_tolerance: type: integer minimum: 0 maximum: 4 default: 2 description: Input and output moderation tolerance; `0` is strictest. grounding: type: boolean default: true description: >- When `true`, the model can research the prompt with web search and image search before it generates. Set `false` to turn both off. AsyncResponse: type: object required: - id - polling_url properties: id: type: string description: Task identifier. polling_url: type: string format: uri description: >- Regional polling URL. Poll this URL with the `x-key` header rather than constructing a URL. cost: description: Cost in credits for this request anyOf: - type: number - type: 'null' input_mp: description: Input megapixels (2 decimal places) anyOf: - type: number - type: 'null' output_mp: description: Output megapixels (2 decimal places) anyOf: - type: number - type: 'null' HTTPValidationError: type: object properties: detail: type: array items: $ref: '#/components/schemas/ValidationError' ValidationError: type: object required: - loc - msg - type properties: loc: type: array items: anyOf: - type: string - type: integer msg: type: string type: type: string securitySchemes: APIKeyHeader: type: apiKey in: header name: x-key ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.