alibaba/wan-3.0-pro-prime/reference-to-videoFrom 176 credits for a 5-second clip· Reference to Video

Wan 3.0 Pro Prime reference-to-video locks a face, garment, set, movement or voice using up to 10 image, 5 video and 5 audio references. It renders 2 to 30 seconds at 1080p, 2K or 4K, enlarged from 1080p above that.

Call it with the model name alibaba/wan-3.0-pro-prime/reference-to-video on POST /jobs/createTask, from 176 credits for a 5-second clip ($1.76). 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 4K
  • 2–30s clips
  • Sound included
  • Start and end frames
  • Up to 10 reference images
  • 5 aspect ratios

Introduction

Wan 3.0 Pro Prime Reference to video locks a face, a garment, a set, a movement or a voice with image, video and audio references and renders the shot at 1080p, 2K or 4K for 2 to 30 seconds on the Prime render. At least one of reference_image_urls (1 to 10 ordered images), reference_video_urls, reference_audio_urls (up to 5 clips each), reference_file_url (one document) or reference_link_url (one web page) is required. Name each reference in the prompt, or the model averages them into a subject that matches none of them.

Choose a Wan 3.0 Pro Prime mode by starting material

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

Key features

Two characters in one shot

The two-character example sends two plates and labels them: "The first image is the woman, the second is the man — keep both faces and both haircuts." They stand on either side of a workbench in a dim garage under one hanging bulb, 6 seconds at 1080p with seed 220913 and room tone only. It is the pattern for keeping a couple consistent across an episode.

A set plate with no people

References do not have to be people. The set-continuity example sends one plate of a boxing gym — ropes, lockers, a single hanging light — and asks for an empty frame with dust drifting through the beam and the bulb swinging slowly, locked camera, 5 seconds at 4k with audio off. Every shot in a sequence can then share the same room.

Movement referenced instead of written

Image, video and audio references can go in together, so movement can come from a clip rather than a paragraph.

Request parameters

ParameterRequiredDescription
aspect_ratioNoThe shape of the frame: wide, square or tall. 16:9 · 4:3 · 1:1 · 3:4 · 9:16 · adaptive · Default: adaptive
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. Default: true
generate_audioNoAdds sound made to match the picture: voices, ambience and effects. Default: true
promptNoDescribe the subject, motion and camera.
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. 1080p · 2k · 4k · Default: 1080p
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 1080p35.1$0.35
resolution 2K37.8$0.38
resolution 4K41.85$0.42

Each task is rounded up to whole credits, so one run at the lowest tier costs 176 credits for a 5-second clip ($1.76).

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

Use cases

A costume across several stages

The dancer example carries one performer and one layered chiffon costume into a third stage, with the follow spot now behind her so the fabric goes translucent as she turns through it. The references carry the dancer and the garment, so the prompt describes only the new lighting set-up, and translucent fabric under backlight leaves almost nothing to hide behind at a large delivery size.

Master files that get recut

Render a reference-locked hero shot at 4K in 16:9, then crop a 9:16 cutdown and a square banner out of the same master. Reference plates plus a fixed seed keep the cast identical across every derivative in the set.

Prompt guide & pro tips

Label by position

reference_image_urls is an ordered list, so refer to "the first image" and "the second image" and supply them in that order. Say for each one whether it is a character, a garment or a set; use video for movement and camera style and audio for a voice, a line reading or room tone.

Hold everything except the change

For a sequence, keep the plates, the seed and the prompt skeleton identical and change only the action or lighting line. Turn enable_prompt_expansion off — it defaults to true on this family — so the labels you wrote are not rewritten.

Check reference lengths before you submit

Video and audio reference limits are enforced during generation rather than when the task is accepted, so a clip over the limit is caught later instead of at submission. Measure clips first, keep reference video plus duration_seconds at 30 seconds or less, and explore at 1080p before rendering at 4K.

API quick start

Call the Wan 3.0 Pro 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-pro-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-pro-prime/reference-to-video",
  "input": {
    "reference_image_urls": [
      "https://media.popnow.ai/influencer/examples/ava.webp"
    ],
    "resolution": "1080p",
    "aspect_ratio": "adaptive",
    "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 Pro Prime API questions

How much does the Wan 3.0 Pro Prime API cost?

Wan 3.0 Pro Prime starts at 176 credits ($1.76) for a 5-second clip with Reference to Video, its cheapest task. Prices by option: 1080p 35.1 credits per second, 2K 37.8 credits per second, 4K 41.85 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 Pro Prime in the API?

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

What resolutions does it support?

1080p, 2k and 4k, defaulting to 1080p. A native Wan 3.0 Prime render tops out at 1080p, so 2k and 4k are enlarged from that render rather than drawn at those sizes. There is no 480p or 720p tier on this family; for native renders at those sizes, use Wan 3.0 or Wan 3.0 Prime.

Does it generate audio?

Yes, in the same pass and on by default, so the returned file already has sound locked to picture. Set generate_audio to false when the clip will be scored separately.

Why does my prompt come back changed?

enable_prompt_expansion is true by default on this family. It helps a thin brief and rewrites a detailed one; set it to false for the final render.

How long can a clip be?

Two to thirty seconds, set as a whole number, default five. Thirty seconds at 4K is the slowest request this family takes, so settle the shot short and small first.

What are the limits of the Wan 3.0 Pro Prime API?

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

Can I try Wan 3.0 Pro Prime without writing code?

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

All Wan models

Wan 3.0 Pro offers the same sizes from the standard Wan 3.0 render, for less per second. Pro Prime is the faster of the two.

More about Wan 3.0 Pro Prime