Vidu Q3 - Generate Video (AI Model · By )

API Documentation

API Reference

Videos

Generate Video

Supported Model Code

Loading models...

Vidu Q3 (viduq3)

viduq30 models support this endpoint

Vidu Q3 is a next-generation AI video generation model featuring native synchronized audio-video output and up to 16-second 1080p video generation in a single pass. It supports frame-accurate camera control, multi-character dialogue, intelligent scene cutting, multilingual output, and high-quality image-to-video and text-to-video generation, making it ideal for anime, cinematic storytelling, short dramas, and commercial content creation.

Generate video

https://api.modelstream.ai

POST/v1/video/generations

Authentication

BearerAuth

AuthenticationBearer <token>

All API requests must be authenticated using a Bearer token in the Authorization header. Please ensure your API key is active.Authorization: Bearer sk-xxxxxx

Parameter Location: Header Param

Request Body

application/json

These parameters come from the selected model form_schema. Switching models updates this list and the request example.

Call Mode

Choose the call mode. Simple: upload 1-7 reference images + prompt (prompt ≤2000 chars), easiest. Subject: name reference subjects and reference them with @name in the prompt, supports multi-subject consistency (prompt ≤5000 chars). Only one mode can be used.

images*array

[Simple mode] Upload 1-7 reference images; the model generates a consistent video based on the subjects in them. Supports PNG, JPEG, JPG, WebP; pixels ≥128×128, aspect ratio between 1:4 and 4:1, each image ≤50MB.

RequiredExample Value: ["https://static.modelstream.ai/demo/vidu/viduq3.png"]Value Range: 0 ≤ value ≤ 7

prompt*string

Text description. Max 2000 characters in simple mode; max 5000 characters in subject mode, where you can use @name to reference subjects for consistency.

RequiredExample Value: The golden hour light slowly deepens to warm amber as sunset progresses. Shadow patterns from the mashrabiya screen stretch and elongate across the floor. The fountain's reflections grow warmer. The brass lantern becomes the dominant light source as natural light fades.Placeholder: Describe the video. In subject mode reference with @name, e.g. @girl running on the beach...

duration?number

Video duration in seconds; viduq3 range 3-16 seconds, default 5.

Example Value: 5Value Range: 3 ≤ value ≤ 16step: 1

aspect_ratio?string

Video aspect ratio; viduq3 supports 16:9, 9:16, 1:1 (4:3 and 3:4 are q2-only). Default 16:9.

Example Value: 16:9

Enum/Options:

16:99:161:1

resolution?string

Video output resolution; viduq3 supports 540p, 720p, 1080p, default 720p.

Example Value: 720p

Enum/Options:

540p720p1080p

audio?boolean

Enable audio-video direct output, producing video with dialogue and sound effects. Enabled by default for viduq3. Off-peak mode is unavailable when this is off.

Example Value: true

audio_type?string

Audio type; required when audio is true, default all.

Example Value: all

Enum/Options:

All (Vocals + Sound effects): allSpeech Only: speech_onlySound Effects Only: sound_effect_only

seed?number

Random seed. Enter a fixed integer for reproducible results; leave empty or set to 0 for a random seed.

Placeholder: Leave empty or 0 for random seed

off_peak?boolean

Off-peak generation mode consumes fewer credits; tasks complete within 48 hours. Supported for viduq3 only when audio is enabled. Disabled by default.

Example Value: false

watermark?boolean

Whether to add a watermark (fixed AI-generated content marker) to the video. Disabled by default.

Example Value: false

wm_position?string

Watermark position: 1=top-left, 2=top-right, 3=bottom-right, 4=bottom-left. Effective only when watermark is enabled.

Example Value: 3

Enum/Options:

Top-left: 1Top-right: 2Bottom-right: 3Bottom-left: 4

wm_url?string

URL of a custom watermark image. Leave empty to use the default watermark. Effective only when watermark is enabled.

Placeholder: Custom watermark image URL (optional)

Response Parameters

application/json

200apiDocs.responses.successCreateVideoGenTask

task_id?string

Parameter description for Task Id

status?string

Parameter description for Status

400apiDocs.responses.badRequestParams

error?object

Parameter description for Error

message?string

Error Message

type?string

Error Type

param?string

Related Parameters

code?string

Error Code

curl -X POST "https://api.modelstream.ai/v1/video/generations" \
  -H "Authorization: Bearer <token>" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "viduq3",
  "prompt": "The crystalline phoenix slowly opens its eyes, which glow with a soft golden warmth. It gently unfurls its wings, causing the iridescent glass feathers to shift and shimmer as liquid gold ripples across them. The floating embers and golden ash in the air drift upward in response to the wing movement, while the misty waterfall in the deep background continues to cascade down softly. 5-second video, high-fantasy, intricately detailed.",
  "images": [
    "https://static.modelstream.ai/demo/vidu/viduq3.png"
  ],
  "duration": 5,
  "aspect_ratio": "16:9",
  "resolution": "1080p",
  "audio": true,
  "audio_type": "all",
  "off_peak": false,
  "watermark": false,
  "wm_position": 3
}'

{
  "task_id": "abcd1234efgh",
  "status": "queued"
}

API Documentation

API Reference

Videos

Generate Video

Supported Model Code

Loading models...

Vidu Q3 (viduq3)

viduq30 models support this endpoint

Generate video

https://api.modelstream.ai

POST/v1/video/generations

Authentication

BearerAuth

AuthenticationBearer <token>

All API requests must be authenticated using a Bearer token in the Authorization header. Please ensure your API key is active.Authorization: Bearer sk-xxxxxx

Parameter Location: Header Param

Request Body

application/json

These parameters come from the selected model form_schema. Switching models updates this list and the request example.

Call Mode

images*array

RequiredExample Value: ["https://static.modelstream.ai/demo/vidu/viduq3.png"]Value Range: 0 ≤ value ≤ 7

prompt*string

Text description. Max 2000 characters in simple mode; max 5000 characters in subject mode, where you can use @name to reference subjects for consistency.

duration?number

Video duration in seconds; viduq3 range 3-16 seconds, default 5.

Example Value: 5Value Range: 3 ≤ value ≤ 16step: 1

aspect_ratio?string

Video aspect ratio; viduq3 supports 16:9, 9:16, 1:1 (4:3 and 3:4 are q2-only). Default 16:9.

Example Value: 16:9

Enum/Options:

16:99:161:1

resolution?string

Video output resolution; viduq3 supports 540p, 720p, 1080p, default 720p.

Example Value: 720p

Enum/Options:

540p720p1080p

audio?boolean

Enable audio-video direct output, producing video with dialogue and sound effects. Enabled by default for viduq3. Off-peak mode is unavailable when this is off.

Example Value: true

audio_type?string

Audio type; required when audio is true, default all.

Example Value: all

Enum/Options:

All (Vocals + Sound effects): allSpeech Only: speech_onlySound Effects Only: sound_effect_only

seed?number

Random seed. Enter a fixed integer for reproducible results; leave empty or set to 0 for a random seed.

Placeholder: Leave empty or 0 for random seed

off_peak?boolean

Off-peak generation mode consumes fewer credits; tasks complete within 48 hours. Supported for viduq3 only when audio is enabled. Disabled by default.

Example Value: false

watermark?boolean

Whether to add a watermark (fixed AI-generated content marker) to the video. Disabled by default.

Example Value: false

wm_position?string

Watermark position: 1=top-left, 2=top-right, 3=bottom-right, 4=bottom-left. Effective only when watermark is enabled.

Example Value: 3

Enum/Options:

Top-left: 1Top-right: 2Bottom-right: 3Bottom-left: 4

wm_url?string

URL of a custom watermark image. Leave empty to use the default watermark. Effective only when watermark is enabled.

Placeholder: Custom watermark image URL (optional)

Response Parameters

application/json

200apiDocs.responses.successCreateVideoGenTask

task_id?string

Parameter description for Task Id

status?string

Parameter description for Status

400apiDocs.responses.badRequestParams

error?object

Parameter description for Error

message?string

Error Message

type?string

Error Type

param?string

Related Parameters

code?string

Error Code

curl -X POST "https://api.modelstream.ai/v1/video/generations" \
  -H "Authorization: Bearer <token>" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "viduq3",
  "prompt": "The crystalline phoenix slowly opens its eyes, which glow with a soft golden warmth. It gently unfurls its wings, causing the iridescent glass feathers to shift and shimmer as liquid gold ripples across them. The floating embers and golden ash in the air drift upward in response to the wing movement, while the misty waterfall in the deep background continues to cascade down softly. 5-second video, high-fantasy, intricately detailed.",
  "images": [
    "https://static.modelstream.ai/demo/vidu/viduq3.png"
  ],
  "duration": 5,
  "aspect_ratio": "16:9",
  "resolution": "1080p",
  "audio": true,
  "audio_type": "all",
  "off_peak": false,
  "watermark": false,
  "wm_position": 3
}'

{
  "task_id": "abcd1234efgh",
  "status": "queued"
}