Get API key

by Vidu

Up to 4K clips with sound and spoken dialogue

vidu/q4-preview/image-to-videoFrom 34 creditsfor a 5-second clip · $0.34
  • Up to 4K
  • 3–16s clips
  • Sound included
  • Up to 15 reference images
  • 5 aspect ratios
  • Image to Video
  • Reference to Video
  • Extend Video
See examples

About Vidu Q4 Preview

Vidu Q4 Preview is the public preview of Vidu's Q4 video model. Its endpoints are image-to-video from an opening frame, reference-to-video from one to 15 reference images, with optional voice clips, and video-extend, which continues a clip you already have. Clips run 3 to 16 seconds at 540p to 4k, with dialogue, effects and ambience generated alongside the picture.

Call it with the model name vidu/q4-preview/image-to-video on POST /jobs/createTask, from 34 credits for a 5-second clip ($0.34). New accounts get 30 free credits to try it in the Playground first.

Introduction

Vidu Q4 Preview Image to video animates one opening frame into a 3 to 16 second clip at 540p, 720p, 1080p, 2k or 4k. Vidu Q4 Preview is Vidu's public preview of its Q4 video model.

Choose a mode by starting material

What you haveMode
a frame to animateVidu Q4 Preview Image to video
people, outfits, products or places as images, with optional voice clipsVidu Q4 Preview Reference to video

Key features

Your frame carries through

In our runs the people, wardrobe and light of the opening frame stayed in the clip.

Sound and spoken lines

Dialogue, effects and ambience are generated with the picture. A line in double quotes was spoken in our run; turn generate_audio off for a silent clip.

Up to 4k

Five resolution tiers from 540p to 4k. 2k and 4k come back as 10-bit HEVC, so plan to edit or transcode them in a desktop tool.

Request parameters

ParameterRequiredDescription
duration_secondsNoHow long the clip runs. You pay per second. ≥ 3 · ≤ 16 · Default: 5
enable_prompt_expansionNoLets the model add detail to a short prompt. Default: false
generate_audioNoAdds sound made to match the picture: voices, ambience and effects. Default: true
image_urlYesThe picture to start from.
promptYesDescribe what happens after the opening frame: the action, the dialogue in quotes, the camera and the sound.
resolutionNoOutput size. Bigger sizes look sharper and cost more. 540p · 720p · 1080p · 2k · 4k · Default: 720p
seedNoReuse the same number to get a repeatable result. ≥ 0 · ≤ 2147483647

Pricing

Prices are in credits, the same credits you use on the website (1 credit = $0.01). The hold is taken when the task is accepted and settled to the actual charge when it finishes; failed tasks are refunded.

OptionCredits per second≈ USD
resolution 540p6.75$0.068
resolution 720p14.25$0.14
resolution 1080p18$0.18
resolution 2K28.5$0.29
resolution 4K58.5$0.59

Each task is rounded up to whole credits, so one run at the lowest tier costs 34 credits for a 5-second clip ($0.34).

For an exact number before you run, send the same body to POST /jobs/quote.

Use cases

Speaking shots

A character turns to camera and says a line in the same pass as the picture.

Fashion and lifestyle stills

Add a turn, a walk or a camera move to a styled frame.

Prompt guide & pro tips

Describe what happens next

Write the movement, the camera and the sound, not what the frame already shows.

Quote the dialogue

Put spoken lines in double quotes so they are spoken, not described.

Draft small, finish at 1080p

Test at 540p with a fixed seed, then rerun the winner at 1080p. Choose 2k or 4k only if you can handle HEVC.

API quick start

Call the Vidu Q4 Preview API in three steps

  1. Create an API key. Sign in to PopNow and create a key in the API console. Keys start with sk-popnow- and use the same credits as the website.
  2. Send the request. POST /jobs/createTask with model vidu/q4-preview/image-to-video and an input object that follows the parameter table. The response returns a task ID straight away.
  3. Get the result. Poll GET /jobs/recordInfo with the task ID, or pass a callBackUrl and we post the result to it. Download the output links when the task succeeds.
# 1. Create the task. Keep the Idempotency-Key if you retry after a network error.
export IDEMPOTENCY_KEY="$(uuidgen)"
curl -X POST https://api.popnow.ai/api/v1/jobs/createTask \
  -H "Authorization: Bearer $POPNOW_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $IDEMPOTENCY_KEY" \
  -d '{
  "model": "vidu/q4-preview/image-to-video",
  "input": {
    "prompt": "A slow aerial shot drifting over a misty pine forest at sunrise",
    "image_url": "https://media.popnow.ai/influencer/examples/marco.webp",
    "resolution": "720p",
    "duration_seconds": 5
  }
}'

# 2. Copy data.taskId from the response, then poll until state is succeeded, failed, canceled or expired.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
  -H "Authorization: Bearer $POPNOW_API_KEY"

Replace the prompt and any links with your own. The API tab has the response, polling and callback reference.

Vidu Q4 Preview API questions

How much does the Vidu Q4 Preview API cost?

Vidu Q4 Preview starts at 34 credits ($0.34) for a 5-second clip with Image to Video, its cheapest task. Prices by option: 540p 6.75 credits per second, 720p 14.25 credits per second, 1080p 18 credits per second, 2K 28.5 credits per second. Credits are the same as on the website (1 credit = $0.01), new accounts get 30 free credits, and failed tasks are refunded.

What is the model name for Vidu Q4 Preview in the API?

Put vidu/q4-preview/image-to-video for Image to Video; vidu/q4-preview/reference-to-video for Reference to Video; vidu/q4-preview/video-extend for Extend Video in the model field of POST /jobs/createTask.

What is Vidu Q4 Preview?

The public preview of Vidu's Q4 video model, released on 7 October 2026 ahead of the full Q4 model. It offers image-to-video, reference-to-video and video-extend. There is no text-to-video.

How long are the clips and at what resolution?

3 to 16 whole seconds at 24 frames per second, at 540p, 720p (the default), 1080p, 2k or 4k. Image to video keeps the shape of your frame; reference to video takes 16:9, 9:16, 1:1, 3:4 or 4:3.

Does it make sound, and can it speak lines?

Yes. Dialogue, effects and ambience are generated with the picture, and a switch turns them off. Put spoken lines in double quotes in the prompt; in our runs the quoted line was spoken. With a reference voice clip, write the line in the prompt too.

How many references can I use?

Reference to video takes 1 to 15 reference images (people, outfits, products or places) and up to 3 audio clips; Vidu asks for MP3, 3 to 12 seconds each. In our runs three references came back as one scene, and two portraits kept both faces.

Why won't my 4k file play in the browser?

2k and 4k clips are 10-bit HEVC (H.265) files, which some browsers cannot play inline. Open them in a desktop player or editor, or transcode them. 540p, 720p and 1080p are H.264 and play almost anywhere.

What are the limits of the Vidu Q4 Preview API?

Clip length: 3–16 s; Resolutions: 540p · 720p · 1080p · 2K · 4K; Prompt length (characters): 20,000. Requests outside these limits are rejected before anything is charged.

Can I try Vidu Q4 Preview without writing code?

Yes. The Playground runs Vidu Q4 Preview on your PopNow credits, needs no API key, and shows the matching code for every run.

All Vidu models

Vidu Q3 is the established image-to-video model, capped at 1080p. Q4 Preview adds reference scenes, clip extension and output up to 4K, and starts at a lower price per second.

More about Vidu Q4 Preview