Flux 2 API Documentation

Overview

High-quality image generation using the Flux 2 Pro model. Delivers strong results for both creative and photorealistic use cases with fast inference.

Primary Endpoint

POST/api/v1/userFlux2/start

Generate high-quality images from text or edit existing images using Flux 2 Pro model. **Features:** - Text-to-Image generation with advanced prompt understanding - Image-to-Image editing (supports up to 8 reference images) - Character consistency across multiple images - Text rendering within images - High-quality output with professional-grade results **Processing Time:** - Usually 20-60 seconds **Output:** - Images are stored in R2 storage (3days-apac bucket) and expire 3 days after the task is created (createdAt + 3 days, same as `expirationDate`) - Download and persist the result to your own storage before it expires; `image_url` is a temporary CDN URL, not a permanent asset address - Expired tasks are omitted from the list endpoint; the detail endpoint still returns the record with `isExpired: true`, but its media URLs are no longer downloadable. ### Request - Send a valid bearer token. The server evaluates the operation in the authenticated caller's access context. - Send an `application/json` body. Required fields: `name`, `prompt`. - API-token callers may include `webhook_url` and `webhook_token` for best-effort terminal-state notifications; ordinary JWT/cookie calls ignore these fields. ### Behavior - This is an asynchronous operation: a successful submission creates a task and returns before processing finishes. - Persist the returned task identifier and use the corresponding detail or list operation to observe progress. - Treat the detail endpoint as the source of truth even when webhook delivery is enabled. ### Response - A `200` response confirms task acceptance; it does not by itself mean media generation has completed. - Retain the returned identifier and wait for a documented terminal status before using output URLs. - JSON object responses, including error responses, normally carry a top-level `trace_id` string for this request; include it when contacting support. It is not a task identifier. - Do not infer undocumented fields or statuses; clients should tolerate additional response properties. ### Errors - `400` — Invalid request parameters. - `401` — Unauthorized - Invalid or missing token. - `402` — Insufficient credits. - `500` — Internal server error. ### Related Operations - `GET /api/v1/userFlux2/list` — Get Flux 2 Pro task list. - `GET /api/v1/userFlux2/detail/{id}` — Get task details. - `DELETE /api/v1/userFlux2/{id}` — Delete Flux 2 Pro task. Authentication: set header Authorization: Bearer <token> (supports user JWT or sk_ API token).

Request Parameters

Name	Type	Required	Description
name	string	Yes	Name of the image generation task
prompt	string	Yes	Text prompt for image generation or editing instruction.
creation_mode	enum: text-to-image \| image-edit	No	Optional compatibility field for history and mode reporting; callers may omit it. The server ignores any supplied value and records `image-edit` when `input_images` contains a valid HTTP(S) image URL, otherwise `text-to-image`. It is not forwarded to the model provider.
input_images	array<string>	No	Array of input image URLs for image-to-image editing or multi-image composition (up to 8 images). When provided, automatically switches to image-to-image mode for character consistency.
aspect_ratio	enum: 1:1 \| 16:9 \| 9:16 \| 4:3 \| 3:4 \| 2:3 \| 3:2 \| custom \| match_input_image	No	Aspect ratio of the generated image. Options: 1:1, 16:9, 9:16, 4:3, 3:4, 2:3, 3:2, custom, match_input_image; default: "9:16"
resolution	enum: 1K \| 2K	No	Resolution of the generated image. - 1K: ~1 megapixel - 2K: ~2 megapixels ; default: "1K"
force_generate	boolean	No	Force generation even if NSFW content is detected. Defaults to true for API users, false for web users; default: true
minor_suspected_skip	boolean	No	Set to true when retrying after error code 1004 to confirm and bypass the suspected-minor soft block.; default: false
webhook_url	string	No	HTTPS URL to receive task.completed / task.failed notifications. Best-effort delivery, single attempt, no retries; clients should treat the detail API as the source of truth.; maxLength: 2048
webhook_token	string	No	Optional plaintext token returned in the X-A2e-Webhook-Token header so receivers can verify the request originated from a2e.; maxLength: 256

Request schema and conditional rules

{
  "allOf": [
    {
      "type": "object",
      "properties": {
        "name": {
          "type": "string",
          "description": "Name of the image generation task",
          "example": "Elon Musk and Mark Zuckerberg boxing"
        },
        "prompt": {
          "type": "string",
          "description": "Text prompt for image generation or editing instruction.\n",
          "example": "Elon Musk and Mark Zuckerberg boxing in a professional ring"
        },
        "creation_mode": {
          "type": "string",
          "enum": [
            "text-to-image",
            "image-edit"
          ],
          "description": "Optional compatibility field for history and mode reporting; callers may omit it. The server ignores any supplied value and records `image-edit` when `input_images` contains a valid HTTP(S) image URL, otherwise `text-to-image`. It is not forwarded to the model provider."
        },
        "input_images": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "Array of input image URLs for image-to-image editing or multi-image composition (up to 8 images).\nWhen provided, automatically switches to image-to-image mode for character consistency.\n",
          "example": [
            "https://example.com/reference1.jpg",
            "https://example.com/reference2.jpg"
          ]
        },
        "aspect_ratio": {
          "type": "string",
          "description": "Aspect ratio of the generated image. Options: 1:1, 16:9, 9:16, 4:3, 3:4, 2:3, 3:2, custom, match_input_image",
          "enum": [
            "1:1",
            "16:9",
            "9:16",
            "4:3",
            "3:4",
            "2:3",
            "3:2",
            "custom",
            "match_input_image"
          ],
          "default": "9:16",
          "example": "9:16"
        },
        "resolution": {
          "type": "string",
          "description": "Resolution of the generated image.\n- 1K: ~1 megapixel\n- 2K: ~2 megapixels\n",
          "enum": [
            "1K",
            "2K"
          ],
          "default": "1K",
          "example": "1K"
        },
        "force_generate": {
          "type": "boolean",
          "description": "Force generation even if NSFW content is detected. Defaults to true for API users, false for web users",
          "default": true
        },
        "minor_suspected_skip": {
          "type": "boolean",
          "default": false,
          "description": "Set to true when retrying after error code 1004 to confirm and bypass the suspected-minor soft block."
        }
      },
      "required": [
        "name",
        "prompt"
      ]
    },
    {
      "$ref": "#/components/schemas/WebhookInput"
    }
  ]
}

Response Fields

code: enum: 0
data: object
data._id: string: Task ID
data.name: string
data.prompt: string
data.input_images: array<string>
data.aspect_ratio: string
data.resolution: string
data.current_status: enum: initialized | processing
data.reference_id: string: Unique reference ID for tracking
data.coins: integer: Credits deducted for this task
data.createdAt: string
data.expirationDate: string: Date when the generated image expires (createdAt + 3 days)
data.expirationDays: integer: Retention period in days
data.remainingDays: integer: Days left before the result expires
data.isExpired: boolean: Whether the result has expired
trace_id: string: Trace ID of this HTTP request. Include it when contacting support about this request. It is generated per request and is not a task identifier; use the returned task `_id` to query results.
data.nsfw_detected: enum: true
data.message: string
data.severity: enum: low | medium | high
data.detected_categories: array<string>

Request Example

curl -X POST "https://www.a2e.com.cn/api/v1/userFlux2/start" \
  -H "Authorization: Bearer YOUR_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
  "name": "Elon Musk and Mark Zuckerberg boxing",
  "prompt": "Elon Musk and Mark Zuckerberg boxing in a professional ring"
}'