MCP / Models / Reference video, editing and lip sync
Vidu Q4 Reference to Video MCP: keep characters and voices
Vidu Q4 makes a 3 to 16 second clip from a prompt, up to 12 reference pictures and 3 voice clips, up to 4K. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.

$ YOUR NEXT RUN
Use Vidu Q4 Reference to Video in your assistant
Paste this prompt into Claude Code, Codex, Cursor or any agent. It reads the guide and helps you connect.
Read https://flymy.ai/skill.md and https://flymy.ai/mcp/models/vidu-q4-reference-to-video.md. Help me connect the FlyMy.AI MCP to this assistant, then run Vidu Q4 Reference to Video (flymyai/vidu-q4-reference-to-video) for this task: Use Vidu Q4 Reference to Video to make a clip of the character in my reference images walking along a misty forest trail.
What Vidu Q4 Reference to Video does
Send prompt, required, up to 5,000 characters, and optionally up to 12 reference pictures in images (characters, products, objects, locations; PNG, JPEG or WebP) and up to 3 voice clips in reference_audio_urls (MP3, 3 to 12 seconds and up to 50 MB each). Name the references in the prompt by position, in the order you send them: [@reference_image_1], [@reference_image_2] and so on for the pictures and [reference_audio_1] and so on for the voices. duration is 3 to 16 seconds (5 by default), aspect_ratio is 16:9, 9:16, 4:3, 3:4 or 1:1, resolution is 540p, 720p (the default), 1080p, 2K or 4K, and audio, on by default, adds sound with dialogue and effects in the voices of the clips. Outputs: video, one MP4 clip, and seed.
It is billed per second of video, more at a higher resolution; the pictures, the voices and the sound do not change the price. It takes pictures and voice clips only, not reference videos, and does not edit or extend a video; to animate one picture as the first frame use Vidu Q4 Image to Video.
Use only pictures and voice clips you have the right to use: a real person's face or voice needs that person's consent.
Vidu Q4 Reference to Video inputs
Every input of flymyai/vidu-q4-reference-to-video as its live schema lists them. Returns video (array), seed (string).
| Input | Type, values and default |
|---|---|
# prompt | string required Describe the video and tag your references by position: [@reference_image_1], [@reference_image_2] ... for the pictures and [reference_audio_1], [reference_audio_2] ... for the voice clips |
# images | string optional Up to 12 reference pictures (characters, products, objects, locations): links or uploads, PNG, JPEG or WebP |
# reference_audio_urls | string optional Up to 3 voice clips that keep voices consistent: links or uploads, MP3, 3-12 seconds and up to 50 MB each. Use only voices you have the right to use |
# duration | integer optional Allowed: 3 to 16 Default: 5 Length of the clip in seconds, 3-16; the price is per second |
# resolution | string optional Allowed: 540p, 720p, 1080p, 2K, 4K Default: 720p 540p ($0.0315 a second), 720p ($0.0665), 1080p ($0.084), 2K ($0.133) or 4K ($0.273) |
# aspect_ratio | string optional Allowed: 16:9, 9:16, 4:3, 3:4, 1:1 Default: 16:9 Shape of the video: 16:9, 9:16, 4:3, 3:4 or 1:1 |
# audio | boolean optional Default: true Generate sound with the video (dialogue and sound effects, in the voices of the voice clips); off makes a silent clip. The price is the same either way |
# seed | integer optional Allowed: 0 to 2147483647 Seed for the generation; the same seed and prompt repeat a result |
Ask your agent
Requests to paste as they are, once the FlyMy.AI MCP is connected.
flymyai/vidu-q4-reference-to-videoflymyai/vidu-q4-reference-to-videoflymyai/vidu-q4-reference-to-videoVidu Q4 Reference to Video price
From $0.0315 per second of duration, depending on resolution. A run at the default settings costs about $0.333. A run costs $0.0945 to $4.37, depending on duration and resolution. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.
| Setting | Price |
|---|---|
| resolution 540p | $0.0315 per second |
| resolution 720p | $0.0665 per second |
| resolution 1080p | $0.084 per second |
| resolution 2K | $0.133 per second |
| resolution 4K | $0.273 per second |
Call Vidu Q4 Reference to Video from code
The same model, from an agent or from your own code. Keys stay in your FlyMy.AI account.
From an agent, through the MCP
The agent calls get_model_schema, then run_model with:
{
"endpoint_id": "flymyai/vidu-q4-reference-to-video",
"input": {
"prompt": "Keep the subject and its motion, set the scene on a beach at golden hour"
}
}From your code, over HTTP
Form fields, not JSON; files go as uploads or public URLs. The answer is a prediction_id; read the result at https://api.flymy.ai/api/v1/flymyai/vidu-q4-reference-to-video/predict/async/result/?request_id=<prediction_id>.
curl -X POST https://api.flymy.ai/api/v1/flymyai/vidu-q4-reference-to-video/predict/async/ \
-H "X-API-KEY: $FLYMYAI_API_KEY" \
-F 'prompt=Keep the subject and its motion, set the scene on a beach at golden hour'Questions about Vidu Q4 Reference to Video
Do I need a Shengshu API key for Vidu Q4 Reference to Video?
No. Vidu Q4 Reference to Video runs on FlyMy.AI's account, so you need no Shengshu key or plan: sign in to FlyMy.AI once and each run is billed to your FlyMy.AI balance.
How much does Vidu Q4 Reference to Video cost?
From $0.0315 per second of duration, depending on resolution. There is no subscription or minimum; the price comes from FlyMy.AI billing and was checked on 2026-11-18.
How do I use Vidu Q4 Reference to Video in Claude Code, Codex or Cursor?
Add the FlyMy.AI MCP with one command and sign in, then ask in plain words, for example: "Use Vidu Q4 Reference to Video to make a clip of the character in my reference images walking along a misty forest trail." Your agent reads the inputs with get_model_schema and runs flymyai/vidu-q4-reference-to-video with run_model.
What does Vidu Q4 Reference to Video need as input?
Vidu Q4 Reference to Video requires prompt; it also takes 7 optional inputs, each listed on this page with its allowed values and default.
Can I call Vidu Q4 Reference to Video from my own code?
Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/vidu-q4-reference-to-video/predict/async/ with your FlyMy.AI API key in the X-API-KEY header.
Go to the source
From the FlyMy.AI model catalog of 2026-11-18: inputs from the model's live schema, prices from FlyMy.AI billing. Requests are examples to paste, not recorded runs.



