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

Wan 3.0 Pro Prime image-to-video animates an opening frame at 1080p, 2K or 4K for 2 to 30 seconds, with generated audio. An optional last frame fixes the ending, and 2K and 4K are enlarged from a native 1080p render.

Call it with the model name alibaba/wan-3.0-pro-prime/image-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 Image to video animates an opening frame on the Prime render and delivers it at 1080p, 2K or 4K for 2 to 30 seconds. image_url is required and becomes the exact first frame; the prompt is optional and should describe motion and camera; last_image_url optionally fixes the final frame. The fields match Wan 3.0 Pro Image to video exactly, so a request built for that endpoint runs here with only the model name changed.

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-frame instructions such as focus pulls

A focus pull is two frames by nature, which is what last_image_url is for. The bloom example opens sharp on a flower bud and closes on a supplied frame that is sharp on an unbuttoned shirt behind it, 6 seconds at 4k; the prompt only says when the transfer happens. Very shallow depth of field leaves the render little latitude to land on the right plane without a pinned ending.

The source sets the ceiling, not the tier

Resolution governs the render, not the input. The 2k and 4k tiers are enlarged from a native 1080p render, so feed the sharpest still you have: JPEG, PNG without transparency, BMP or WEBP, 240 to 8000 pixels per side, up to 20 MB and no wider than 8:1.

Holds for scored edits

The alley-light-hold example is a 4-second hold at 2k with audio and prompt expansion both off: "Nobody moves. Only the neon tube above her stutters and the rain keeps falling, dragging its reflection across the wet plastic. Locked camera." It is the request shape for a shot that will be scored in the edit instead of carrying its own sound.

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
image_urlYesThe picture to start from.
last_image_urlNoOptional final frame, so the clip ends exactly where you want.
promptNoDescribe the subject, motion and camera.
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

Environmental change around a still subject

The neon-alley example opens on a plate that already carries the alley, the rain and the transparent slicker, so the prompt says only what changes: the rain coming down harder, a neon tube stuttering once, steam surging from a vent, and the subject holding the lens through all of it. Its audio line names each source — rain on steel, a buzzing tube, a hissing vent.

Close detail with a fixed end

The shirt example reuses the same two frames as the bloom example at 1080p for 4 seconds: a hand draws an open shirt slowly aside under raking gold light and lets it fall back, while the bud between the folds opens a little. Pinning both ends keeps a very shallow depth of field landing on the intended plane.

Prompt guide & pro tips

Leave what is visible out of the prompt

Restating what is already in the frame invites the model to redraw it. Use the prompt for motion and camera only, and keep aspect_ratio on adaptive so the clip follows the frame's own shape; pin a ratio only when the delivery format demands it.

Approve at 1080p, deliver at 2K or 4K

Settle the motion at 5 seconds and 1080p with seed held, then re-send the body at 2k or 4k. Every rerun that changes both resolution and seed changes two things at once, so one of them has to stay fixed while you judge the other.

Turn off expansion for exact motion

enable_prompt_expansion is true by default on this family. It helps a two-word idea and rewrites a precise motion brief; the alley-light-hold example switches it off so its three short sentences run as written. Any whole duration from 2 to 30 seconds is accepted, and -1 hands the choice of length to the model.

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/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": "alibaba/wan-3.0-pro-prime/image-to-video",
  "input": {
    "image_url": "https://media.popnow.ai/influencer/examples/marco.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 Image 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; Prompt length (characters): 20,000. 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