Create Task 1.0
POST
/ent/v2/one-click/mvOne-click Solutions
Authorizationstring*Replace {your api key} with your token
Token {your api key}imagesstring*Model images or style images used for MV generation.
Note 1: Supports Base64-encoded images or image URLs (must be accessible);
Note 2: Supports 1–7 images;
Note 3: Supported image formats: png, jpeg, jpg, webp;
Note 4: Image aspect ratio must be less than 1:4 or 4:1;
Note 5: Image size must not exceed 50 MB;
Note 6: Note that the byte length after base64 decoding must be less than 10M, and the encoding must include an appropriate content type string, e.g.:data:image/png;base64,{base64_encode}
["https://prod-ss-images.s3.cn-northwest-1.amazonaws.com.cn/vidu-maas/template/image2video.png"]Authorizationstring*Replace {your api key} with your token
Token {your api key}idstring*Task ID, returned upon successful creation by the create task API
{your_id}lip_ref_urls is required.⚠ lip_ref_urls is required, up to 2 images, order = who sings first in the song.
Authorizationstring*Replace {your api key} with your token
Token {your api key}premium_mv_modestring*Task type
sing (full lip-sync throughout)sing_perform (alternating lip-sync and performance)perform (performance) dance (dance)Authorizationstring*Replace {your api key} with your token
Token {your api key}idstring*Task ID, returned upon successful creation by the create task API
{your_id}audio_urlstring*Audio used to generate the MV.
Note 1: Supports Base64-encoded audio or an audio URL (must be accessible);
Note 2: Supports 1 audio file;
Note 3: Supported formats: mp3, wav, aac, m4a;
Note 4: Outputs the composited video plus a storyboard list in a single generation; uploaded audio must be at least 10 seconds and at most 300 seconds;
Note 6: The byte length after base64 decoding must be less than 20M, and the encoding must include an appropriate content type string, e.g.:data:image/png;base64,{base64_encode}
lip_syncbooleantrue: lip sync required
false: lip sync not required
Default: false
When enabled, adds 4 credits per second
Note 1: Not supported for non-real (non-human) subjects;
Note 2: Not supported for non-frontal segments in the video;
Note 3: Only supports medium shots, where the subject faces the camera at the start of the video
Note 4: Tasks longer than three minutes are not supported; no additional credits will be deducted
Note 5: When lip sync is enabled, 720p and 1080p are recommended; 540p is not supported
lip_ref_urlstringURL of the singer's face; must be front-facing to the camera, close-up shot.
Image file requirements: - Content: must include one clear frontal face of a person, and that person must appear in the video - File size: file ≤10MB - Image size: aspect ratio ≤2, maximum side length <4096 - Format: jpeg, jpg, png, bmp, webp
Using this parameter significantly increases the lip sync success rate
https://prod-ss-images.s3.cn-northwest-1.amazonaws.com.cn/vidu-maas/template/image2video.pngstylestringEnter the style text directly: diffuse style, anime style, etc.
qualitystringhigh/standardhigh → MIX pipeline.standard → Q2 reference-generation pipeline. (Default)
promptstringUser prompt.
Text description for generating the MV video.
Note 1: Character length must not exceed 3000 characters
aspect_ratiostringOutput aspect ratio, default 16:9
Optional values: 1:1, 16:9, 9:16, 4:3, 3:4
16:9resolutionstringResolution, default 720p
Optional values: 540p, 720p, 1080p
add_subtitlebooleanWhether subtitles are needed, default false
true: subtitles required
false: subtitles not required
subtitle_colorstringDefault #FFFFFF, white
Text color in HEX format
languagestringAudio language type, default auto
Optional: en, zh
srt_urlstringSubtitle file URL
callback_urlstringCallback protocol.
You need to actively set callback_url when creating a task. The request method is POST. When the video generation task status changes, Vidu will send a callback request containing the task's latest status to this address. The structure of the callback request content is consistent with the response body of the task query API.
The "status" values returned in the callback include:
lip_ref_urlsstringLip-sync reference character images
Required：Required when premium_mv_mode is sing / sing_performWhen premium_mv_mode is perform & dance, this parameter is not needed; passing it is considered invalid.
Up to 2 images, ordered by who sings first in the song; frontal close-up face shots; jpeg/jpg/png/bmp/webpimagesstringReference images
Required：Optional when premium_mv_mode is sing / sing_performRequired when premium_mv_mode is perform & dance
Up to 6 images; URL or base64; png/jpeg/jpg/webp; aspect ratio 1:44:1; ≤50MBaudio_urlstring*Audio. The audio must contain lyrics; uploading pure instrumental music is not supported
URL or base64; mp3/wav/aac/m4a; 10-300 secondslanguagestringAudio language type, defaults to automatic detectionOptions: en, zh, ja, ko, vi, th, id, ms, tl, hi, ar, fr, de, es, pt, ru, it, nl, sv, da, fi, no, el, pl, cs, hu, ro, bg, hr, sk, arstylestringE.g. "diffuse style", "anime style"
Style textpromptstringPrompt
≤3000 charactersaspect_ratiostringOutput aspect ratio, default 16:9
1:1 / 16:9 / 9:16 / 4:3 / 3:4resolutionstringResolution, default 720p
720p /1080padd_subtitlebooleanWhether to burn in subtitles, default false
true / falsesubtitle_colorstringSubtitle color, default white
HEX, e.g. #FFFFFFcallback_urlstringStatus change callback
URLapplication/jsonResponse fields
idstringTask ID
statestringProcessing status
Optional values:
created: created successfully
queueing: task is queued
processing: task is processing
success: task succeeded
failed: task failed
err_codestringError code; see the error code table for details
creditsintegerNumber of credits consumed by this task, unit: credits
application/jsonResponse fields
idstringTask ID
statestringProcessing status
Possible values:
created - Created successfully
queueing - Task queued
processing - Task processing
success - Task succeeded
failed - Task failed
err_codestringError code, see the error code table for details
creditsintegerNumber of credits consumed by this task, unit: credits
application/jsonResponse fields
idstringThe task ID generated by Vidu for this task
application/jsonResponse fields
idstringThe task ID generated by Vidu for this task
payloadstringPassthrough parameter provided when this task was invoked
bgmbooleanWhether BGM was used in this task invocation
off_peakbooleanWhether off-peak mode was used in this task invocation
creationsarrayGeneration results
idstringCreation ID, used to identify different generated outputs
urlstringCreation URL, valid for 24 hours
cover_urlstringCreation cover image, valid for 24 hours
watermarked_urlstringpayloadstringPass-through parameter provided when this task was invoked
bgmbooleanWhether this task invocation used BGM
off_peakbooleanWhether this task invocation used off-peak mode
creationsarrayGenerated results
idstringCreation ID, used to identify different generated outputs
urlstringCreation URL, valid for 24 hours
cover_urlstringCreation cover image, valid for 24 hours
watermarked_urlstringWatermarked creation URL, valid for 24 hours
Watermarked creation URL, valid for 24 hours
curl --request POST \
--url 'https://api.vidu.com/ent/v2/one-click/mv' \
--header 'Authorization: Token {your api key}' \
--header 'Content-Type: application/json' \
--data '{
"images": [
"https://prod-ss-images.s3.cn-northwest-1.amazonaws.com.cn/vidu-maas/template/image2video.png"
],
"audio_url": "",
"lip_sync": true,
"lip_ref_url": "https://prod-ss-images.s3.cn-northwest-1.amazonaws.com.cn/vidu-maas/template/image2video.png",
"style": "string",
"quality": "string",
"prompt": "",
"aspect_ratio": "16:9",
"resolution": "string",
"add_subtitle": true,
"subtitle_color": "string",
"language": "string",
"srt_url": "string",
"callback_url": "string"
}'{
"id": "your_id_here"
}curl --request GET \
--url 'https://api.vidu.com/ent/v2/tasks/{your_id}/creations' \
--header 'Authorization: Token {your api key}'{
"id":"your_task_id",
"state": "success",
"err_code": "",
"credits": 4,
"payload": "",
"creations": [
{
"id": "your_creations_id",
"url": "your_generated_results_url",
"cover_url": "your_generated_results_cover_url",
"watermarked_url": "your_generated_results_watermarked_url"
}
]
}curl --request POST \
--url 'https://api.vidu.com/ent/v2/one-click/premium_mv' \
--header 'Authorization: Token {your api key}' \
--header 'Content-Type: application/json' \
--data '{
"premium_mv_mode": "sing (full lip-sync throughout)sing_perform (alternating lip-sync and performance)perform (performance) dance (dance)",
"lip_ref_urls": "Up to 2 images, ordered by who sings first in the song; frontal close-up face shots; jpeg/jpg/png/bmp/webp",
"images": "Up to 6 images; URL or base64; png/jpeg/jpg/webp; aspect ratio 1:44:1; ≤50MB",
"audio_url": "URL or base64; mp3/wav/aac/m4a; 10-300 seconds",
"language": "Audio language type, defaults to automatic detectionOptions: en, zh, ja, ko, vi, th, id, ms, tl, hi, ar, fr, de, es, pt, ru, it, nl, sv, da, fi, no, el, pl, cs, hu, ro, bg, hr, sk, ar",
"style": "Style text",
"prompt": "≤3000 characters",
"aspect_ratio": "1:1 / 16:9 / 9:16 / 4:3 / 3:4",
"resolution": "720p /1080p",
"add_subtitle": "true / false",
"subtitle_color": "HEX, e.g. #FFFFFF",
"callback_url": "URL"
}'{
"id": "your_id_here"
}curl --request GET \
--url 'https://api.vidu.com/ent/v2/tasks/{your_id}/creations' \
--header 'Authorization: Token {your api key}'{
"id":"your_task_id",
"state": "success",
"err_code": "",
"credits": 4,
"payload": "",
"creations": [
{
"id": "your_creations_id",
"url": "your_generated_results_url",
"cover_url": "your_generated_results_cover_url",
"watermarked_url": "your_generated_results_watermarked_url"
}
]
}