02-Image-to-Video
Image-to-Video
Document Version: v1.0.0 | Last Updated: 2026-06-11 This platform fully supports the official Vidu video generation APIs. Requests and responses are transparently proxied with identical parameter semantics.
POST https://platform.dataeyes.ai/vidu/ent/v2/img2videoRequest Parameters
Request Headers
| Header | Required | Description |
|---|---|---|
Content-Type | Yes | application/json |
Authorization | Yes | Bearer {API_KEY} |
Request Body
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
model | String | Yes | Model name Options: viduq3-turbo, viduq3-pro, viduq3-pro-fast, viduq2-pro-fast, viduq2-pro, viduq2-turbo, viduq1, viduq1-classic, vidu2.0- viduq3-pro-fast: High-quality audio-video content, faster generation, cost-effective- viduq3-turbo: Faster generation speed compared to viduq3-pro- viduq3-pro: High-quality audio-video content with better results- viduq2-pro-fast: Lowest price, stable quality, 2–3x faster than viduq2-turbo- viduq2-pro: Best quality, rich details- viduq2-turbo: Good quality, fast generation- viduq1: Clear visuals, smooth transitions, stable camera movement- viduq1-classic: Clear visuals, richer transitions and camera movements- vidu2.0: Fast generation speed | |
images | Array[String] | Yes | First-frame image. The model uses this image as the first frame to generate the video. - Supports Base64-encoded images or image URLs (must be accessible) - Only 1 image is supported - Supported formats: png, jpeg, jpg, webp - Image aspect ratio must be less than 1:4 or 4:1 - Image size must not exceed 50 MB - POST body must not exceed 20MB; Base64 must include the content type prefix, e.g. data:image/png;base64,{base64_encode} | |
prompt | String | No | Text prompt. Maximum 5000 characters. Note: If the is_rec recommended prompt parameter is used, the model will ignore this prompt | |
audio | Bool | No | false | Whether to enable audio-video output (default is true for q3-pro, q3-turbo, q3-pro-fast)- true: Output video with dialogue and background audio- false: Output silent videoNote 1: When set to true, the voice_id parameter takes effectNote 2: When set to true, only q3 models support off-peak mode |
audio_type | String | No | all | Audio type, effective when audio is true- all: Sound effects + voice- speech_only: Voice only- sound_effect_only: Sound effects onlyNote: Audio splitting is currently only supported for q2, q1, and 2.0 series models |
voice_id | String | No | Voice ID. Ineffective for q3 series models. If empty, the system automatically recommends a voice. | |
is_rec | Bool | No | Whether to use recommended prompts - true: The system automatically recommends a prompt and uses it for generation- false: Generate based on the provided promptNote: Each task consumes an additional 10 credits when enabled | |
bgm | Bool | No | false | Whether to add background music Note: Ineffective for q2 model when duration is 9s or 10s; ineffective for q3 series |
duration | Int | No | Video duration (seconds). Default varies by model: - viduq3-pro, viduq3-turbo, viduq3-pro-fast: Default 5, range 1–16- viduq2-pro-fast, viduq2-pro, viduq2-turbo: Default 5, range 1–10- viduq1, viduq1-classic: Default 5, fixed at 5- vidu2.0: Default 4, options 4, 8 | |
seed | Int | No | Random seed. If omitted or set to 0, a random value is used. | |
resolution | String | No | Resolution. Default varies by model and duration: - viduq3-pro-fast (1–16s): Default 720p, options 720p, 1080p- viduq3-pro, viduq3-turbo (1–16s): Default 720p, options 540p, 720p, 1080p- viduq2-pro-fast (1–10s): Default 720p, options 720p, 1080p- viduq2-pro, viduq2-turbo (1–10s): Default 720p, options 540p, 720p, 1080p- viduq1, viduq1-classic (5s): Default 1080p, fixed at 1080p- vidu2.0 (4s): Default 360p, options 360p, 720p, 1080p- vidu2.0 (8s): Default 720p, fixed at 720p | |
movement_amplitude | String | No | auto | Movement amplitude. Options: auto, small, medium, largeNote: This parameter has no effect on q2 and q3 series models |
off_peak | Bool | No | false | Off-peak mode Note: Audio-video output for models other than q3 does not support off-peak mode |
watermark | Bool | No | false | Whether to add a watermark. Default is no watermark. |
wm_position | Int | No | 3 | Watermark position1: Top-left, 2: Top-right, 3: Bottom-right, 4: Bottom-left |
wm_url | String | No | Custom watermark image URL. If omitted, the default watermark is used. | |
payload | String | No | Pass-through parameter. Maximum 1048576 characters. | |
meta_data | String | No | Metadata identifier, JSON format string, pass-through field. | |
callback_url | String | No | Callback URL. Sends a POST callback request when the task state changes. |
Request Example
Response Parameters
| Field | Type | Description |
|---|---|---|
task_id | String | Task ID |
state | String | Processing state: created, queueing, processing, success, failed |
model | String | Model name used for this call |
prompt | String | Prompt used for this call |
images | Array[String] | Image parameter used for this call |
duration | Int | Video duration |
audio | Bool | Whether audio-video output is enabled |
audio_type | String | Audio type |
seed | Int | Random seed |
resolution | String | Resolution |
movement_amplitude | String | Movement amplitude |
payload | String | Pass-through parameter |
off_peak | Bool | Whether off-peak mode is used |
credits | Int | Number of credits consumed by this call |
watermark | Bool | Whether a watermark is used |
created_at | String | Task creation time |
Response Example
{
"task_id": "{task_id}",
"state": "created",
"model": "viduq3-pro",
"images": ["https://example.com/image.png"],
"prompt": "The astronaut waved and the camera moved up.",
"duration": 5,
"seed": 123456,
"resolution": "1080p",
"movement_amplitude": "auto",
"payload": "",
"off_peak": false,
"credits": 8,
"created_at": "2025-01-01T15:41:31.968916Z"
}