alibaba/wan-3.0-prime/reference-to-videoFrom 46 credits for a 5-second clip· Reference to Video

Wan 3.0 Prime reference-to-video holds a face, wardrobe, location or voice across a clip using up to 10 images, 5 videos and 5 audio files. It returns 2 to 30 seconds at 480p to 1080p, with reference video and audio each capped at 15 seconds.

Call it with the model name alibaba/wan-3.0-prime/reference-to-video on POST /jobs/createTask, from 46 credits for a 5-second clip ($0.46). New accounts get 30 free credits to try it in the Playground first.

  • Create Video
  • Image to Video
  • Reference to Video
  • Extend Video
  • Up to 1080p
  • 2–30s clips
  • Sound included
  • Start and end frames
  • Up to 10 reference images
  • 5 aspect ratios

Introduction

Wan 3.0 Prime Reference to video builds a 2 to 30 second shot on the Prime render from up to ten image, five video and five audio references, with the same fields as Wan 3.0 Reference to video. At least one reference array, a reference file or a web link must be present and the prompt is optional; when you write one, it should say what each reference controls. Resolution is 480p, 720p or 1080p, default 720p, and aspect_ratio defaults to 16:9.

Choose a Wan 3.0 Prime mode by starting material

What you have at the startMode
a written scene or scriptWan 3.0 Prime Text to video
an approved opening imageWan 3.0 Prime Image to video
separate visual, motion, or sound referencesWan 3.0 Prime Reference to video

Key features

One identity plate, a whole scene from text

A single plate can carry the person while the prompt invents everything else. The dune example uses one identity image shot flat on a plain studio background; the moonlit dune field, the wind and a scarf several metres long streaming above her are all written. The scarf still has to be attached to the same arm at the end of the take, which makes it a good thing to check.

Camera behaviour borrowed from a clip

Reference video is for movement and camera style rather than faces. The motion-style example takes a slow handheld orbit from a reference clip and applies it to the woman from a reference image, standing in an empty studio, for 6 seconds at 720p. Reference clips must be MP4 or MOV, at least 16 fps, 1 to 15 seconds each and 15 seconds in total.

Voice continuity from audio references

Up to five WAV or MP3 audio references, 15 seconds in total, can hold a voice across takes. A presenter who looks continuous but sounds different between shots is still discontinuous, so when a person speaks in more than one shot, send the same audio reference every time.

Request parameters

ParameterRequiredDescription
aspect_ratioNoThe shape of the frame: wide, square or tall. 16:9 · 9:16 · 1:1 · 4:3 · 3:4 · adaptive · Default: 16:9
duration_secondsNoHow long the clip runs. You pay per second. -1–30 · Default: 5
enable_prompt_expansionNoLets the model add detail to a short prompt.
enable_thinkingNoLet the model reason about the brief and the reference material before generating. Helps with complex references; slower. Default: false
generate_audioNoAdds sound made to match the picture: voices, ambience and effects. Default: true
promptNoDescribe the subject, action, camera, light, pacing, and boundaries for the shot.
reference_audio_urlsNoAudio to match: a voice, music or a rhythm.
reference_file_urlNoOne reference document (PDF, DOCX, TXT, MD and similar) that the model reads for characters, wardrobe, setting and action.
reference_image_urlsNoPictures of the people, outfits or places the result should keep.
reference_link_urlNoOne public web page the model reads for reference. It must open without a login.
reference_video_urlsNoClips whose motion, camera or style the result should follow.
resolutionNoOutput size. Bigger sizes look sharper and cost more. 480p · 720p · 1080p · 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 480p9.18$0.092
resolution 720p18.9$0.19
resolution 1080p37.8$0.38

Each task is rounded up to whole credits, so one run at the lowest tier costs 46 credits for a 5-second clip ($0.46).

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

Use cases

A recurring presenter

Keep the same image plates for face and set, and the same audio reference for the voice, in every request of a series. The presenter example keeps "the same presenter, the same studio" and describes only the move — a push that ends on a specific framing — because identity is already carried by the references.

Style-matched inserts

When a new shot has to move the way an existing one does, supply that clip as a motion reference and an image for the subject. State in the prompt which is which, as the motion-style example does: "Take the camera behaviour from the reference clip — a slow handheld orbit — and apply it to the woman in the reference image."

Prompt guide & pro tips

Budget reference video against output length

A 6-second style clip therefore leaves room for up to 24 seconds of output. Reference limits are enforced during generation rather than on submission, so trim clips before you send them.

Keep the face on an image, not a video

A reference video sets motion style well but is a poor way to pin a face. Put identity on an image plate, name it in the prompt, and use video only for how the camera or the body moves.

Hold the reference set steady between takes

Change one reference or one line of the prompt per attempt and hold seed, so a difference can be traced to its cause. Settle the look at 5 seconds and 720p before extending, and check face, costume and voice against their references at the start and end of every render.

API quick start

Call the Wan 3.0 Prime 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 alibaba/wan-3.0-prime/reference-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": "alibaba/wan-3.0-prime/reference-to-video",
  "input": {
    "prompt": "A slow aerial shot drifting over a misty pine forest at sunrise",
    "reference_image_urls": [
      "https://media.popnow.ai/influencer/examples/ava.webp"
    ],
    "aspect_ratio": "16:9",
    "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.

Wan 3.0 Prime API questions

How much does the Wan 3.0 Prime API cost?

Wan 3.0 Prime starts at 46 credits ($0.46) for a 5-second clip with Reference to Video, its cheapest task. Prices by option: 480p 9.18 credits per second, 720p 18.9 credits per second, 1080p 37.8 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 Wan 3.0 Prime in the API?

Put alibaba/wan-3.0-prime/text-to-video for Create Video; alibaba/wan-3.0-prime/image-to-video for Image to Video; alibaba/wan-3.0-prime/reference-to-video for Reference to Video; alibaba/wan-3.0-prime/video-extend for Extend Video in the model field of POST /jobs/createTask.

Can I reuse my Wan 3.0 client code?

Yes. The request body, defaults and enums match field for field. Change the model name and nothing else.

How long can a clip be?

Two to thirty seconds, whole numbers, default five. Longer clips drift more, so lock the look at five seconds before extending.

Does it come with audio?

Yes, generated in the same pass and on by default. One file comes back with sound already aligned to picture; set generate_audio to false if you are scoring the shot yourself.

Which resolutions are available?

480p, 720p and 1080p, defaulting to 720p. For 2K and 4K use Wan 3.0 Pro Prime, which publishes a different resolution ladder.

How do I keep a character consistent?

Reference-to-video with the same image plates in every request, one fixed seed and one prompt skeleton. Text-to-video re-invents the face each run, so it cannot hold a cast.

What are the limits of the Wan 3.0 Prime API?

Clip length: 2–30 s; Resolutions: 480p · 720p · 1080p; Aspect ratios: 16:9 · 9:16 · 1:1 · 4:3 · 3:4 · adaptive; Reference audio: 5; Reference images: 10. Requests outside these limits are rejected before anything is charged.

Can I try Wan 3.0 Prime without writing code?

Yes. The Playground runs Wan 3.0 Prime on your PopNow credits, needs no API key, and shows the matching code for every run.

All Wan models

Plain Wan 3.0 makes the same clips for less when you can wait a little longer.

More about Wan 3.0 Prime