Wan 3.0 Prime Video Edit

Wan 3.0 Prime Video Edit by Alibaba restyles or modifies an input video from a text instruction, optionally guided by reference images and audio, keeping the original length.
35% OFFalibaba/wan/3.0/prime/video-edit

Wan 3.0 Prime Video Edit by Alibaba restyles or modifies an input video from a text instruction, optionally guided by reference images and audio, keeping the original length.

Try the model

Playground

Open playground
Input
Text instruction describing the editing. Refer to the input video as Video 1 and to reference images or audio as Image 1, Audio 1, and so on.
URL of the input video (MP4 or MOV; 1-15 seconds, at least 16 fps, 240-4096px per side, under 100MB).
Additional Settings More

Customize your input with more control.

PNG, JPEG, WebP, or GIF · 20 MiB maximum each · up to 10

Up to 10 optional reference image URLs (JPEG, PNG, BMP, or WebP; up to 20MB each). Refer to them in the prompt as Image 1, Image 2, and so on.
Up to 5 optional reference audio URLs (WAV or MP3; 1-15s each, 15s total, under 15MB each).
Output video resolution tier. Allowed values: 480p, 720p, 1080p.
Generate a synchronized audio track. Pricing is the same either way.
Random seed (0-2147483647) for reproducible results. Omit for a random seed; the same seed may still produce slightly different results. Range: 0 to 2147483647.
35% OFF
Result
Idle

Your output will appear here

Complete the inputs, then click Run.

Displayed run estimate: $0.91. Final charges follow the model’s billing rules below.

Wan 3.0 Prime Video Edit

Change an existing clip with a sentence: restyle it, swap a subject or prop, or rework the setting. Optional reference images and audio guide the change. The result keeps the length and framing of the source.

Prime is the faster Wan 3.0 tier: the same inputs and output quality as standard Wan 3.0, with significantly shorter end-to-end generation time and a higher per-second rate. Use standard Wan 3.0 for batch or background jobs where turnaround does not matter.

Fields

FieldTypeDefaultNotes
promptstring, required—Up to 5,000 characters.
videovideo URL, required—Source clip, Video 1 in the prompt. MP4/MOV, 1–15s, ≥16fps, 240–4096px per side, ≤100MB.
imagesimage URL[] (≤10)—Referenced as Image 1, Image 2, …
audiosaudio URL[] (≤5)—WAV/MP3, 1–15s each, 15s total, ≤15MB. Referenced as Audio 1, …
resolution480p / 720p / 1080p720pSets the per-second rate.
generate_audiobooleantrueNative dialogue, music, and effects. Same price on or off.
seedinteger 0–2147483647randomFix it to compare prompt changes.

There is no duration field; the output is as long as the source.

Billing

Like the official Wan 3.0 rate, billing counts the source clip and the edited output, which are the same length, so each source second bills twice: $0.136 at 480p, $0.28 at 720p, $0.56 at 1080p. References are not metered.

Source clipBilled480p720p1080p
2s4s$0.272$0.56$1.12
5s10s$0.68$1.40$2.80
10s20s$1.36$2.80$5.60
15s30s$2.04$4.20$8.40

The quote shown before submission assumes a 5-second source ($1.40 at 720p); the final charge uses the measured length. Failed runs are not charged. Output files are copied to SandBase storage and the returned URL stays valid for 7 days; download anything you need to keep.

Prompting

  • Lead with the change and state what must stay: “turn the scene into clay animation; keep her face and the camera motion”.
  • Refer to the source as Video 1 and to references as Image 1 or Audio 1.
  • Draft at 480p; edits cost twice the source length.

Limits

  • The output aspect ratio follows the source video.
  • To add new footage after the clip, use video-extend.

Also on SandBase

Other Wan 3.0 Prime endpoints: alibaba/wan/3.0/prime/video (all modes in one schema), alibaba/wan/3.0/prime/text-to-video, alibaba/wan/3.0/prime/image-to-video, alibaba/wan/3.0/prime/reference-to-video, alibaba/wan/3.0/prime/video-extend. Standard tier: alibaba/wan/3.0/video-edit.