Overview
Animate a still image into a video using the Wan 2.5 / 2.6 open-source video diffusion model family. Part of the Wan series known for fluid motion and temporal consistency.
Primary Endpoint
POST
/api/v1/userWan25/startStart a Wan video generation task. This endpoint supports Wan 2.5 image-to-video, Wan 2.6 image-to-video and Wan 2.7 multi-mode video generation. For Wan 2.7, set `model` to `wan2.7-i2v` and select the generation mode with `task_type`: - `text_to_video`: text prompt only. Do not provide image/video material. - `first_frame`: image-to-video from one first-frame image. Requires `image_url`. - `first_last_frame`: image-to-video with first and last frame control. Requires `image_url` and `last_frame_url`. - `reference_image`: reference-to-video. Requires 1 to 5 ordered image/video entries in `reference_media`; legacy pure-image clients may continue using `reference_image_urls`. - `video_extend`: extend an existing video clip. Requires `first_clip_url`; optional `last_frame_url`. - `video_edit`: edit an existing video. Requires `edit_video_url`; optional `reference_image_urls` with up to 3 image URLs. `text_to_video`, `first_last_frame`, `reference_image`, `video_extend` and `video_edit` are only available when `model=wan2.7-i2v`. ### 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: `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` — Bad Request - Invalid parameters. - `401` — Unauthorized - Invalid or missing JWT token. Authentication: set header Authorization: Bearer <token> (supports user JWT or sk_ API token).
Request Parameters
| Name | Type | Required | Description |
|---|---|---|---|
| name | string | No | Optional display name for the task |
| image_url | string | No | Source image URL. Required for `first_frame` and `first_last_frame`. |
| prompt | string | Yes | Generation prompt |
| negative_prompt | string | No | Negative prompt to avoid unwanted features |
| duration | enum: 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 | 11 | 12 | 13 | 14 | 15 | No | Video duration in seconds. Wan 2.6 and Wan 2.7 accept any integer from 2 to 15, except: reference_image drops to 2-10 when a reference video is present, and video_edit uses 5-10. Wan 2.5 only supports 5/10.; default: "5" |
| resolution | enum: 480p | 720p | 1080p | No | Video resolution; default: "720p" |
| ratio | enum: 16:9 | 9:16 | 1:1 | 4:3 | 3:4 | No | Video aspect ratio. Only used by Wan 2.7 `text_to_video` and `reference_image`.; default: "16:9" |
| enable_prompt_expansion | boolean | No | Whether to enable prompt rewriting using LLM; default: false |
| multi_shots | boolean | No | Enable intelligent multi-shot segmentation (only active when enable_prompt_expansion is true); default: false |
| model | enum: wan2.5-i2v-preview | wan2.6-i2v | wan2.6-i2v-flash | wan2.7-i2v | No | AI model version (wan2.6-i2v and wan2.7-i2v require VIP/Max user, wan2.6-i2v-flash is available to all users); default: "wan2.5-i2v-preview" |
| task_type | enum: text_to_video | first_frame | first_last_frame | reference_image | video_extend | video_edit | No | Wan 2.7 generation mode. Only used when `model=wan2.7-i2v`.; default: "first_frame" |
| last_frame_url | string | No | Last-frame image URL. Required for `first_last_frame`; optional for `video_extend`. |
| first_clip_url | string | No | Existing video clip URL. Required for Wan 2.7 `video_extend`. |
| edit_video_url | string | No | Input video URL. Required for Wan 2.7 `video_edit`. |
| reference_image_urls | array<string> | No | Legacy pure-image reference URLs for Wan 2.7 `reference_image`; optional for `video_edit` (up to 3 images). |
| reference_media | array<object> | No | Ordered Wan2.7 reference-to-video media. Input videos are billed together with output duration according to the official 5-second input cap.; minItems: 1; maxItems: 5 |
| reference_media[].type | enum: reference_image | reference_video | Yes | - |
| reference_media[].url | string | Yes | - |
| reference_media[].duration | number | No | Reference video duration in seconds. The server probes metadata when omitted. |
| seed | number | No | Random seed for reproducibility. Value must be in the range [0, 2147483647]. If not specified, system generates a random seed.; minimum: 0; maximum: 2147483647 |
| audio | boolean | No | Whether to generate audio for the video; default: true |
| audio_url | string | No | URL of audio file to use for first-frame/first-last-frame video generation. Supports WAV/MP3, 3-30s duration, max 15MB. If longer than video duration, audio will be truncated. |
| 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": "Optional display name for the task",
"example": "My Wan Video"
},
"image_url": {
"type": "string",
"description": "Source image URL. Required for `first_frame` and `first_last_frame`.",
"example": "https://example.com/image.jpg"
},
"prompt": {
"type": "string",
"description": "Generation prompt",
"example": "Make the person in the image wave their hand"
},
"negative_prompt": {
"type": "string",
"description": "Negative prompt to avoid unwanted features",
"example": "blurry, distorted"
},
"duration": {
"type": "string",
"enum": [
"2",
"3",
"4",
"5",
"6",
"7",
"8",
"9",
"10",
"11",
"12",
"13",
"14",
"15"
],
"default": "5",
"description": "Video duration in seconds. Wan 2.6 and Wan 2.7 accept any integer from 2 to 15, except: reference_image drops to 2-10 when a reference video is present, and video_edit uses 5-10. Wan 2.5 only supports 5/10."
},
"resolution": {
"type": "string",
"enum": [
"480p",
"720p",
"1080p"
],
"default": "720p",
"description": "Video resolution"
},
"ratio": {
"type": "string",
"enum": [
"16:9",
"9:16",
"1:1",
"4:3",
"3:4"
],
"default": "16:9",
"description": "Video aspect ratio. Only used by Wan 2.7 `text_to_video` and `reference_image`."
},
"enable_prompt_expansion": {
"type": "boolean",
"default": false,
"description": "Whether to enable prompt rewriting using LLM"
},
"multi_shots": {
"type": "boolean",
"default": false,
"description": "Enable intelligent multi-shot segmentation (only active when enable_prompt_expansion is true)"
},
"model": {
"type": "string",
"enum": [
"wan2.5-i2v-preview",
"wan2.6-i2v",
"wan2.6-i2v-flash",
"wan2.7-i2v"
],
"default": "wan2.5-i2v-preview",
"description": "AI model version (wan2.6-i2v and wan2.7-i2v require VIP/Max user, wan2.6-i2v-flash is available to all users)"
},
"task_type": {
"type": "string",
"enum": [
"text_to_video",
"first_frame",
"first_last_frame",
"reference_image",
"video_extend",
"video_edit"
],
"default": "first_frame",
"description": "Wan 2.7 generation mode. Only used when `model=wan2.7-i2v`."
},
"last_frame_url": {
"type": "string",
"description": "Last-frame image URL. Required for `first_last_frame`; optional for `video_extend`.",
"example": "https://example.com/last-frame.jpg"
},
"first_clip_url": {
"type": "string",
"description": "Existing video clip URL. Required for Wan 2.7 `video_extend`.",
"example": "https://example.com/clip.mp4"
},
"edit_video_url": {
"type": "string",
"description": "Input video URL. Required for Wan 2.7 `video_edit`.",
"example": "https://example.com/input-video.mp4"
},
"reference_image_urls": {
"type": "array",
"items": {
"type": "string"
},
"description": "Legacy pure-image reference URLs for Wan 2.7 `reference_image`; optional for `video_edit` (up to 3 images).",
"example": [
"https://example.com/reference-1.jpg",
"https://example.com/reference-2.jpg"
]
},
"reference_media": {
"type": "array",
"minItems": 1,
"maxItems": 5,
"description": "Ordered Wan2.7 reference-to-video media. Input videos are billed together with output duration according to the official 5-second input cap.",
"items": {
"type": "object",
"required": [
"type",
"url"
],
"properties": {
"type": {
"type": "string",
"enum": [
"reference_image",
"reference_video"
]
},
"url": {
"type": "string"
},
"duration": {
"type": "number",
"description": "Reference video duration in seconds. The server probes metadata when omitted."
}
}
}
},
"seed": {
"type": "number",
"minimum": 0,
"maximum": 2147483647,
"description": "Random seed for reproducibility. Value must be in the range [0, 2147483647]. If not specified, system generates a random seed."
},
"audio": {
"type": "boolean",
"default": true,
"description": "Whether to generate audio for the video"
},
"audio_url": {
"type": "string",
"description": "URL of audio file to use for first-frame/first-last-frame video generation. Supports WAV/MP3, 3-30s duration, max 15MB. If longer than video duration, audio will be truncated.",
"example": "https://example.com/audio.mp3"
},
"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": [
"prompt"
],
"x-duration-options-by-task-type": {
"text_to_video": [
"2",
"3",
"4",
"5",
"6",
"7",
"8",
"9",
"10",
"11",
"12",
"13",
"14",
"15"
],
"first_frame": [
"2",
"3",
"4",
"5",
"6",
"7",
"8",
"9",
"10",
"11",
"12",
"13",
"14",
"15"
],
"first_last_frame": [
"2",
"3",
"4",
"5",
"6",
"7",
"8",
"9",
"10",
"11",
"12",
"13",
"14",
"15"
],
"reference_image": [
"2",
"3",
"4",
"5",
"6",
"7",
"8",
"9",
"10",
"11",
"12",
"13",
"14",
"15"
],
"video_extend": [
"2",
"3",
"4",
"5",
"6",
"7",
"8",
"9",
"10",
"11",
"12",
"13",
"14",
"15"
],
"video_edit": [
"5",
"6",
"7",
"8",
"9",
"10"
]
},
"anyOf": [
{
"title": "Wan 2.5 first frame",
"type": "object",
"properties": {
"model": {
"type": "string",
"enum": [
"wan2.5-i2v-preview"
]
},
"task_type": {
"type": "string",
"enum": [
"first_frame"
],
"default": "first_frame"
},
"duration": {
"type": "string",
"enum": [
"5",
"10"
],
"default": "5"
}
}
},
{
"title": "Wan 2.6 first frame",
"type": "object",
"properties": {
"model": {
"type": "string",
"enum": [
"wan2.6-i2v",
"wan2.6-i2v-flash"
]
},
"task_type": {
"type": "string",
"enum": [
"first_frame"
]
},
"duration": {
"type": "string",
"enum": [
"2",
"3",
"4",
"5",
"6",
"7",
"8",
"9",
"10",
"11",
"12",
"13",
"14",
"15"
],
"default": "5"
}
}
},
{
"title": "Wan 2.7 text to video",
"type": "object",
"properties": {
"model": {
"type": "string",
"enum": [
"wan2.7-i2v"
]
},
"task_type": {
"type": "string",
"enum": [
"text_to_video"
]
},
"duration": {
"type": "string",
"enum": [
"2",
"3",
"4",
"5",
"6",
"7",
"8",
"9",
"10",
"11",
"12",
"13",
"14",
"15"
],
"default": "5"
}
}
},
{
"title": "Wan 2.7 first frame",
"type": "object",
"properties": {
"model": {
"type": "string",
"enum": [
"wan2.7-i2v"
]
},
"task_type": {
"type": "string",
"enum": [
"first_frame"
]
},
"duration": {
"type": "string",
"enum": [
"2",
"3",
"4",
"5",
"6",
"7",
"8",
"9",
"10",
"11",
"12",
"13",
"14",
"15"
],
"default": "5"
}
}
},
{
"title": "Wan 2.7 first and last frame",
"type": "object",
"properties": {
"model": {
"type": "string",
"enum": [
"wan2.7-i2v"
]
},
"task_type": {
"type": "string",
"enum": [
"first_last_frame"
]
},
"duration": {
"type": "string",
"enum": [
"2",
"3",
"4",
"5",
"6",
"7",
"8",
"9",
"10",
"11",
"12",
"13",
"14",
"15"
],
"default": "5"
}
}
},
{
"title": "Wan 2.7 reference image",
"type": "object",
"properties": {
"model": {
"type": "string",
"enum": [
"wan2.7-i2v"
]
},
"task_type": {
"type": "string",
"enum": [
"reference_image"
]
},
"duration": {
"type": "string",
"enum": [
"2",
"3",
"4",
"5",
"6",
"7",
"8",
"9",
"10",
"11",
"12",
"13",
"14",
"15"
],
"default": "5"
}
}
},
{
"title": "Wan 2.7 video extension",
"type": "object",
"properties": {
"model": {
"type": "string",
"enum": [
"wan2.7-i2v"
]
},
"task_type": {
"type": "string",
"enum": [
"video_extend"
]
},
"duration": {
"type": "string",
"enum": [
"2",
"3",
"4",
"5",
"6",
"7",
"8",
"9",
"10",
"11",
"12",
"13",
"14",
"15"
],
"default": "5"
}
}
},
{
"title": "Wan 2.7 video edit",
"type": "object",
"properties": {
"model": {
"type": "string",
"enum": [
"wan2.7-i2v"
]
},
"task_type": {
"type": "string",
"enum": [
"video_edit"
]
},
"duration": {
"type": "string",
"enum": [
"5",
"6",
"7",
"8",
"9",
"10"
],
"default": "5"
}
}
}
]
},
{
"$ref": "#/components/schemas/WebhookInput"
}
]
}Response Fields
- code: integer
- data: object
- data._id: string
- data.name: string
- data.image_url: string
- data.current_status: string
- data.coins: number
- 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.
Request Example
curl -X POST "https://www.a2e.com.cn/api/v1/userWan25/start" \
-H "Authorization: Bearer YOUR_API_TOKEN" \
-H "Content-Type: application/json" \
-d '{
"name": "My Wan 2.7 Reference Video",
"model": "wan2.7-i2v",
"task_type": "reference_image",
"reference_image_urls": [
"https://example.com/reference-1.jpg",
"https://example.com/reference-2.jpg"
],
"prompt": "Create a cinematic video matching the subject and visual style of the reference images",
"negative_prompt": "blurry, distorted",
"duration": "5",
"resolution": "720p",
"ratio": "16:9",
"enable_prompt_expansion": false
}'Related Endpoints
Responses
200
Wan video task started successfully
400
Bad Request - Invalid parameters
401
Unauthorized - Invalid or missing bearer token