Hailuo โ
Endpoint: POST https://mps.intl.tencentcloudapi.comAction: CreateAigcVideoTask
Hailuo is a video generation model that supports text-to-video and first-frame / first-and-last-frame video generation. H3 supports multimodal reference generation that mixes images, video, and audio (up to 9 images / 3 videos / 3 audio clips, 12 in total); the 02 and 2.3 series are simple generation engines with fixed durations.
Basic Information โ
| Item | Value |
|---|---|
| ModelName | Hailuo |
| ModelVersion | H3 / 2.3 / 2.3-fast / 02 |
| Guardrail release support | Only H3 supported |
Supported Specifications by Version โ
| Version | Resolution | Aspect Ratio | Length |
|---|---|---|---|
H3 | Default output: 768PUpscale output: 1080P / 2K / 4K | 21:9 / 16:9 / 4:3 / 1:1 / 3:4 / 9:16 | 4โ15 seconds |
H3-Max | Default output: 480P / 768PUpscale output: 1080P / 2K / 4K | 16:9 / 9:16 / 4:3 / 3:4 / 1:1 / adaptive | 5โ15 seconds |
02 / 2.3 | Refer to the output options for each version | โ | 6 seconds10 seconds |
Input Conditions โ
| Version | Condition |
|---|---|
H3 | Input: reference image 9 images / video 3 / audio 3, total 12; separate from first/last frame mode |
H3-Max | Input: text or first/last frame |
02 / 2.3 | Input: H3 multimodal limits do not apply |
The 02 and 2.3 series are simple generation engines with a fixed length, while H3 is a multimodal engine that references image, video, and audio together.
Request Parameters โ
| Parameter | Required | Type | Description |
|---|---|---|---|
ModelName | Required | String | Fixed value Hailuo |
ModelVersion | Optional | String | H3 / 2.3 / 2.3-fast / 02 |
Prompt | Required | String | Generation prompt. See the version-specific limits below |
NegativePrompt | Optional | String | Elements to exclude from the result. Applied on supported models |
EnhancePrompt | Optional | Boolean | Automatic prompt correction. Default value false |
ImageUrl | Optional | String | First frame image URL. Must be externally accessible and 10MB or less |
LastImageUrl | Optional | String | Last frame image URL. Used together with ImageUrl |
ImageInfos.N | Optional | Array | Reference image array. Category / Url / ReferenceType, etc. |
Duration | Optional | Integer | Generation length (seconds). Only values allowed by each model are applied |
ExtraParameters | Optional | Object | Resolution / AspectRatio / EnableAudio |
AdditionalParameters | Optional | String | JSON string containing model-specific options. For the seed passing format, refer to Additional Configuration |
ExtraParameters.EnablelnputComplianceCheck | Optional | Boolean | If false is explicitly passed, input moderation is released. Contact your sales representative before use |
ExtraParameters.EnableOutputComplianceCheck | Optional | Boolean | If false is explicitly passed, output moderation is released. Contact your sales representative before use |
Request Example โ
text-to-video (H3) โ
H3 reflects the camera movement described in the prompt. The default output resolution is 2560x1440.
{
"ModelName": "Hailuo",
"ModelVersion": "H3",
"Prompt": "a girl running toward the camera on a playground holding a kite, orbit camera, cinematic quality",
"Operator": "wiki-example",
"StoreCosParam": {
"CosBucketName": "<bucket-appid>",
"CosBucketRegion": "<bucket-region>",
"CosBucketPath": "/aigc/"
},
"EnhancePrompt": false
}H3-Max / First/Last Frame โ
{
"ModelName": "Hailuo",
"ModelVersion": "H3-Max",
"Prompt": "The camera moves from the first frame toward the final composition.",
"NegativePrompt": "blur, distortion",
"EnhancePrompt": false,
"ImageUrl": "https://<host>/first.jpg",
"LastImageUrl": "https://<host>/last.jpg",
"Duration": 5,
"ExtraParameters": {
"Resolution": "768P",
"AspectRatio": "16:9"
},
"StoreCosParam": {
"CosBucketName": "<bucket-appid>",
"CosBucketRegion": "<bucket-region>",
"CosBucketPath": "/aigc/"
},
"Operator": "wiki-example"
}Response Example โ
{
"Response": {
"Status": "DONE",
"Message": "ok",
"Resolution": "1920x1080",
"VideoUrls": [
"https://aigc-output-video-<id>.cos.<region>.myqcloud.com/<file>.mp4?q-sign-algorithm=sha1&..."
],
"RequestId": "<request-id>"
}
}Special Configuration โ
Guardrail Release โ
Hailuo supports guardrail release only in ModelVersion=H3. Do not apply the same setting to other versions.
To use the guardrail release parameters, you must first contact your sales representative to confirm usage permission. Guardrail release is applied only when the parameter is explicitly passed, even on supported engines. If the parameter is omitted, the guardrail is not released.
| Parameter | Release Value | Scope |
|---|---|---|
ExtraParameters.EnablelnputComplianceCheck | false | Input moderation release |
ExtraParameters.EnableOutputComplianceCheck | false | Output moderation release |
Merge the following settings into your existing generation request. To release both input and output moderation, pass both fields together.
{
"ExtraParameters": {
"EnablelnputComplianceCheck": false,
"EnableOutputComplianceCheck": false
}
}Supported Capabilities by Version โ
| Version | Generation Mode | Length | Remarks |
|---|---|---|---|
H3 | text / image / multimodal reference | 4~15 seconds | References image 9, video 3, audio 3. Native voice generation |
2.3 | text / image | 6 seconds, 10 seconds | 1080P is 6 seconds only |
2.3-fast | image only | 6 seconds, 10 seconds | First frame required |
02 | text / image, first + last frame | 6 seconds, 10 seconds | 16:9 only |
H3 Input Constraints โ
Image input (first frame, last frame, reference image)
| Item | Constraint |
|---|---|
| Format | JPG, JPEG, PNG, WEBP, HEIC, HEIF |
| File size | 30MB or less |
| Width and height range | 256~5760 px |
| Aspect ratio | 0.4~2.5 |
| Count | First frame 1 image, last frame 1 image, reference images 9 images or fewer |
Video input (reference generation)
| Item | Constraint |
|---|---|
| Container | MP4, MOV |
| Codec | Video H.264, H.265 / Audio AAC, MP3 |
| File size | 50MB or less |
| Count | 3 or fewer |
| Segment length | 2~15 seconds, total 15 seconds or less |
| Width and height range | 256~5760 px |
| Aspect ratio | 0.4~2.5 |
| Frame rate | 23.976~60 |
Audio input (reference generation)
| Item | Constraint |
|---|---|
| Format | WAV, MP3 |
| File size | 15MB or less |
| Count | 3 or fewer |
| Segment length | 2~15 seconds, total 15 seconds or less |
image-to-video (First / Last Frame) โ
Enter ImageUrl and LastImageUrl, 1 image each. First/last frame (i2va) and multimodal reference (r2va) are selected as separate generation modes.
{
"ModelName": "Hailuo",
"ModelVersion": "H3",
"Prompt": "camera slowly pushes in",
"ImageUrl": "https://<cdn>/first.jpg",
"LastImageUrl": "https://<cdn>/last.jpg",
"Duration": 6,
"ExtraParameters": {
"Resolution": "1080P",
"AspectRatio": "9:16"
},
"Operator": "admin",
"StoreCosParam": {
"CosBucketName": "<bucket-appid>",
"CosBucketRegion": "<bucket-region>",
"CosBucketPath": "/aigc/"
},
"EnhancePrompt": false
}Additional Options โ
i2va and r2va are mutually exclusive
Select the r2va mode for reference video / audio generation, and the i2va mode for first/last frame generation.