Vidu Reference to Video 2.0 | Fast Image-to-Video API

Vidu Reference-to-Video 2.0 — vidu/reference-to-video-2.0

Vidu Reference-to-Video 2.0 generates a short video from a text prompt while using multiple reference images to guide subject identity, style, and scene consistency. Upload one or more reference images, describe the action and camera intent in the prompt, and the model synthesizes a coherent clip that follows your references. Movement intensity can be adjusted with movement_amplitude, and seed can be fixed for repeatable results.

Key capabilities

Prompt-driven video generation guided by reference images
Supports multiple reference images to keep identity/style consistent
Movement amplitude control: auto / small / medium / large
Seed control for reproducible generations
Good for “merge two references into one scene” style storytelling

Use cases

Character + scene blending (e.g., a person from one reference enters a room from another)
Style-consistent short clips based on an artwork reference
Multi-reference continuity across a mini story sequence
Product storytelling using a reference setup and a subject reference
Quick concept videos for ads, trailers, and social

Pricing

Duration	Price per video
5s	$0.20

Inputs

images (required): one or more reference images (add multiple items)
prompt (required): action + scene + camera direction

Parameters

aspect_ratio: output aspect ratio (e.g., 16:9)
movement_amplitude: motion intensity (auto, small, medium, large)
seed: random seed (set a number for reproducible results)

Prompting guide (multi-reference)

When you provide multiple references, explicitly assign what each reference is used for:

Template: Use reference image 1 for the room and lighting. Use reference image 2 for the character’s appearance and clothing. The character steps out of the painting into the room, walks to the table, and places the coffee cup down. Smooth motion, consistent style, fixed camera, no flicker.

Example prompts

Use reference 1 as the room scene and table setup. Use reference 2 for the girl’s identity and painting style. The girl steps out of the painting into the room, walks to the table, and gently places the coffee cup down. Warm morning light, cinematic, smooth transition.
Combine both references into one coherent scene. The character crosses the room, interacts with the cup, subtle cloth movement, soft shadows, realistic contact with the table surface.

Reference To Video 2.0 API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/vidu/reference-to-video-2.0 with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Reference To Video 2.0 below.

HTTP example

# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/vidu/reference-to-video-2.0" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d '{
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "aspect_ratio": "16:9",
    "movement_amplitude": "auto",
    "seed": 0
}'

# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY"

# When status is "completed", read the output from data.outputs[0].

Node.js example

// npm install wavespeed
const WaveSpeed = require('wavespeed');

const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env

const result = await client.run("vidu/reference-to-video-2.0", {
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "aspect_ratio": "16:9",
        "movement_amplitude": "auto",
        "seed": 0
});

console.log(result.outputs[0]); // → URL of the generated output

Python example

# pip install wavespeed
import wavespeed

output = wavespeed.run(
    "vidu/reference-to-video-2.0",
    {
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "aspect_ratio": "16:9",
    "movement_amplitude": "auto",
    "seed": 0
}
)

print(output["outputs"][0])  # → URL of the generated output

Reference To Video 2.0 API — Frequently asked questions

What is the Reference To Video 2.0 API?

Reference To Video 2.0 is a Vidu model for video generation from images, exposed as a REST API on WaveSpeedAI. Vidu Reference-to-Video 2.0 turns references into videos that preserve characters, objects, and environments with Multi-Entity Consistency. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Reference To Video 2.0 API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID; poll the prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/vidu/vidu-reference-to-video-2.0.

How much does Reference To Video 2.0 cost per run?

Reference To Video 2.0 starts at $0.20 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does Reference To Video 2.0 accept?

Key inputs: `prompt`, `images`, `aspect_ratio`, `seed`, `movement_amplitude`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/vidu/vidu-reference-to-video-2.0.

How long does Reference To Video 2.0 take to generate?

Average end-to-end generation time on WaveSpeedAI is around 121 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.

Can I use Reference To Video 2.0 outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (Vidu). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.

PrzykładyZobacz wszystkie

Powiązane modele

README