# Vidu Q4 Preview Reference-to-Video — Atlas Cloud API > Vidu's latest flagship video model keeps subjects consistent across a 3-16 second clip from up to 15 reference images and 3 reference audio clips, with native synchronized audio and output from 540p up to 4K. This is the machine-readable API reference for **Vidu Q4 Preview Reference-to-Video** on Atlas Cloud, a unified API platform for 400+ AI models across text, image, video, audio and 3D. - **Model ID**: `vidu/q4-preview/reference-to-video` - **Built by**: Vidu - **Modality**: Video - **Model page**: https://www.atlascloud.ai/models/vidu/q4-preview/reference-to-video - **API key**: https://www.atlascloud.ai/console/api-keys - **Docs**: https://www.atlascloud.ai/docs ## Pricing on Atlas Cloud - $0.032 per second of generated video - Pay-as-you-go. No minimum spend, no subscription required. > **These are the authoritative Atlas Cloud rates for this model.** Any price that > appears in the vendor description further down refers to a different platform or > a different model variant and does not apply here. ## Use this model from an AI agent Atlas Cloud ships three first-party integration surfaces. All three authenticate with the same API key via the `ATLASCLOUD_API_KEY` environment variable. ### MCP server The official MCP server (`atlascloud-mcp`) exposes this model to any MCP-compatible host — Claude Code, OpenAI Codex, Cursor, Gemini CLI, Goose, Claude Desktop. One-line install: ```bash # Claude Code claude mcp add atlascloud -- npx -y atlascloud-mcp # OpenAI Codex CLI codex mcp add atlascloud -- npx -y atlascloud-mcp # Gemini CLI gemini mcp add atlascloud -- npx -y atlascloud-mcp export ATLASCLOUD_API_KEY="your-api-key" ``` Then ask in plain English; the agent calls `atlas_generate_video` with `model: "vidu/q4-preview/reference-to-video"`. The server fetches each model's schema and validates parameters before submitting, so invalid requests fail fast without spending credits. MCP docs: https://www.atlascloud.ai/docs/mcp-server ### Agent Skills `atlas-cloud-skills` is a portable skill package (API reference, code templates in Python / Node.js / cURL, model IDs with pricing) for Claude Code, Cursor, Codex and 12+ other agents: ```bash npx skills add AtlasCloudAI/atlas-cloud-skills export ATLASCLOUD_API_KEY="your-api-key" ``` Skills docs: https://www.atlascloud.ai/docs/skills ### CLI The `atlas` binary runs Atlas Cloud from a terminal or CI script. Async media jobs are polled and downloaded automatically (use `--no-download` when a script only needs the output URLs): ```bash # Install (Homebrew, npm, or shell installer) brew install AtlasCloudAI/tap/atlascloud # npm install -g atlascloud-cli # curl -fsSL https://raw.githubusercontent.com/AtlasCloudAI/cli/main/install.sh | sh atlas auth login atlas generate video vidu/q4-preview/reference-to-video -p "Your prompt here" ``` CLI docs: https://www.atlascloud.ai/docs/cli ## HTTP API reference - **Submit endpoint (POST)**: `https://api.atlascloud.ai/api/v1/model/generateVideo` — start an async generation; returns a `prediction_id` - **Poll endpoint (GET)**: `https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}` — poll this until the prediction finishes - **Model ID**: `vidu/q4-preview/reference-to-video` ## API Information This model can be used via our HTTP API or more conveniently via our client libraries. See the input and output schema below, as well as the usage examples. ### Input Schema The API accepts the following input parameters: - **`model`** (`string`, _required_): Model name. - Default: `"vidu/q4-preview/reference-to-video"` - Options: "vidu/q4-preview/reference-to-video" - **`prompt`** (`string`, _required_): Text description of the video. Refer to subjects from the reference images. Up to 20,000 characters. - Default: `"The woman from the first image and the man from the second image hug by the lakeside at sunset."` - **`reference_images`** (`array[string]`, _required_): 1 to 15 reference images (URLs or Base64) whose subjects stay consistent in the video. Formats: PNG, JPEG, JPG, WebP. Max 50MB each. - Min items: 1 - Max items: 15 - **`reference_audios`** (`array[string]`, _optional_): Optional, up to 3 reference audio clip URLs. Format: MP3, 3 to 12 seconds each, max 50MB each. - Min items: 0 - Max items: 3 - **`duration`** (`integer`, _optional_): Length of the generated video in seconds, 3 to 16. - Default: `5` - Min: 3 - Max: 16 - **`aspect_ratio`** (`string`, _optional_): Aspect ratio of the output video. - Default: `"16:9"` - Options: "16:9", "9:16", "1:1", "4:3", "3:4" - **`resolution`** (`string`, _optional_): Output resolution. Billed per second at the selected tier. - Default: `"720p"` - Options: "540p", "720p", "1080p", "2k", "4k" - **`generate_audio`** (`boolean`, _optional_): Generate synchronized audio (dialogue, sound effects, ambience) together with the video. - Default: `true` - **`seed`** (`integer`, _optional_): Random seed for reproducible results. Set -1 for a random seed. - Default: `-1` **Required Parameters Example**: ```json { "model": "vidu/q4-preview/reference-to-video", "prompt": "The woman from the first image and the man from the second image hug by the lakeside at sunset.", "reference_images": [ "" ] } ``` **Full Example**: ```json { "model": "vidu/q4-preview/reference-to-video", "prompt": "The woman from the first image and the man from the second image hug by the lakeside at sunset.", "reference_images": [ "" ], "reference_audios": [ "" ], "duration": 5, "aspect_ratio": "16:9", "resolution": "720p", "generate_audio": true, "seed": -1 } ``` ### Output Schema The API returns the following output format: - **`id`** (`string`, _optional_): Unique identifier for the prediction, the ID of the prediction to get. - **`urls`** (`object`, _optional_): Object containing related API endpoints. - **`model`** (`string`, _optional_): Model ID used for the prediction. - **`status`** (`string`, _optional_): Status of the task: created, processing, completed, or failed. - **`outputs`** (`array[string]`, _optional_): Array of URLs to the generated content (empty when status is not completed). - **`created_at`** (`string`, _optional_): ISO timestamp of when the request was created. **Example Response**: ```json { "id": "", "urls": {}, "model": "", "status": "", "outputs": [ "" ], "created_at": "" } ``` ## Usage Examples ### cURL ```bash # Step 1: Start generation (async) curl -X POST "https://api.atlascloud.ai/api/v1/model/generateVideo" \ -H "Authorization: Bearer $ATLASCLOUD_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "vidu/q4-preview/reference-to-video", "prompt": "The woman from the first image and the man from the second image hug by the lakeside at sunset.", "reference_images": [ "" ], "reference_audios": [ "" ], "duration": 5, "aspect_ratio": "16:9", "resolution": "720p", "generate_audio": true, "seed": -1 }' # Response will contain: {"code": 200, "data": {"id": "prediction_id", "status": "processing"}} # Step 2: Poll for result (replace {prediction_id} with the id returned above) curl -X GET "https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}" \ -H "Authorization: Bearer $ATLASCLOUD_API_KEY" # Keep polling until status is "completed", "succeeded" or "failed" # When completed, outputs will contain the generated content URL(s) ``` ## Additional Resources ### Documentation - [Model Playground](https://www.atlascloud.ai/models/vidu/q4-preview/reference-to-video) ## About this model _Vendor-supplied description. Any pricing or endpoint mentioned below refers to_ _other platforms — use the Atlas Cloud values above._ ### Vidu Q4 Preview Reference-to-Video **Vidu Q4 Preview Reference-to-Video** is Vidu's latest flagship model for subject-consistent video. Give it up to 15 reference images and up to 3 reference audio clips, and it generates a 3–16 second clip that keeps those characters, objects, and scenes consistent, with synchronized audio and output from 540p up to 4K. #### Why Choose This? - **Multi-subject consistency.** Combine up to 15 reference images of characters, products, or locations in one shot. - **Audio references.** Add up to 3 MP3 clips to steer voice, music, or sound in the generated audio. - **Native audio.** Sound is generated together with the video. Audio is on by default. - **Up to 4K.** Five resolution tiers from 540p to 4K, in five aspect ratios. - **Long takes.** Any duration from 3 to 16 seconds. #### Parameters | Parameter | Required | Description | | --- | --- | --- | | model | Yes | `vidu/q4-preview/reference-to-video` | | prompt | Yes | Scene description that refers to the subjects in the reference images, up to 20,000 characters. | | reference_images | Yes | 1–15 reference images (URLs or Base64). PNG / JPEG / JPG / WebP, max 50MB each. | | reference_audios | No | 0–3 reference audio clip URLs. MP3, 3–12 seconds each, max 50MB each. | | duration | No | Video length in seconds, integer 3–16. Default `5`. | | aspect_ratio | No | `16:9` (default), `9:16`, `1:1`, `4:3`, `3:4`. | | resolution | No | `540p`, `720p` (default), `1080p`, `2k`, `4k`. | | generate_audio | No | Generate synchronized audio. Default `true`. | | seed | No | Random seed. `-1` (default) picks a random seed. | #### How to Use _(Description truncated. Full text on the model page.)_ --- Atlas Cloud — one API for 400+ AI models. Model page: https://www.atlascloud.ai/models/vidu/q4-preview/reference-to-video · Docs: https://www.atlascloud.ai/docs