--- title: "Wan 3.0 Prime Edit Video" description: "Alibaba Wan 3.0 Prime video edit, the higher quality tier: rewrites a real clip from a prompt (replace a person, restyle, change the scene or the time of day) while following its motion. Name the clip Video 1 and any reference images Image 1, Image 2 in the prompt. Clips of 1 to 15 seconds; the clip length is billed on top of the output." updated: 2026-11-03 --- # Wan 3.0 Prime Edit Video **Node type:** `video:wan_v3_0_prime_edit` **Category:** `video` ## Description Alibaba Wan 3.0 Prime video edit, the higher quality tier: rewrites a real clip from a prompt (replace a person, restyle, change the scene or the time of day) while following its motion. Name the clip Video 1 and any reference images Image 1, Image 2 in the prompt. Clips of 1 to 15 seconds; the clip length is billed on top of the output. ## Pricing - **Cost:** ~17 credits per second - **Per-second rate:** The figure is the rate for a 5-second clip. Shorter clips can cost a bit more per second. You're always charged for the real length. ## Variant family - **Family:** `wan_v3_0_prime` - **Is primary:** no - **All variants:** `video:wan_v3_0_prime_t2v`, `video:wan_v3_0_prime_i2v`, `video:wan_v3_0_prime_r2v`, `video:wan_v3_0_prime_edit` ## Canvas ports These appear as port handles on the left side of the node. | ID | Label | Details | | ---------------------- | -------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `prompt` | **Prompt** | `TEXT` _(required)_ · multiline. Say what to change and name the clip as Video 1: "replace the man in Video 1 with the woman in Image 1", "restyle Video 1 as a clay animation", "make it night in Video 1, keep the camera move". Say what to keep, too: "keep the motion and framing of Video 1". | | `reference_video_urls` | **Source Video** | `VIDEO` _(required)_ · list. The clip to edit, called Video 1 in the prompt. 1 to 15 seconds at 16 fps or more (up to 5 clips, 15 seconds in total). Its length is billed on top of the output, measured before you are charged. | | `reference_image_urls` | **Reference Images** | `IMAGE` · list. Optional: who or what to put into the clip, called Image 1, Image 2 in the prompt (for example the person who replaces someone in Video 1). | | `reference_audio_urls` | **Reference Audio** | `AUDIO` · list | ## Sidebar config These render as form fields in the right-side config panel when the node is selected. | ID | Label | Details | | ------------------------- | ---------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `aspect_ratio` | **Aspect Ratio** | `TEXT` · options: `adaptive`, `16:9`, `9:16`, `1:1`, `4:3`, `3:4` · default: `"adaptive"`. Adaptive lets the model pick the shape, or follow the start frame when one is wired. | | `duration` | **Duration (seconds)** | `NUMBER` · `2…30` · default: `5` | | `resolution` | **Resolution** | `TEXT` · options: `480p`, `720p`, `1080p` · default: `"720p"` | | `audio` | **Generate Audio** | `BOOLEAN` · default: `true`. Sound is generated with the video. Same price either way. | | `enable_prompt_expansion` | **Prompt Expansion** | `BOOLEAN` · default: `true`. Rewrites the prompt before generating. Turning it off is 20 to 60 seconds faster but usually looks worse. | | `enable_thinking` | **Thinking** | `BOOLEAN` · default: `false`. Plans the shot before generating. Slower. | | `seed` | **Seed** | `NUMBER` · `0…2147483647` | ## Outputs | ID | Label | Type | | ------- | ------------------- | ------- | | `video` | **Generated Video** | `VIDEO` | ## Edit a real clip Wire the clip into **Source Video** and say in the prompt what to change, and what to keep. Name the clip **Video 1** and any pictures in **Reference Images** as **Image 1**, **Image 2**: - swap a person: "replace the man in Video 1 with the woman in Image 1, keep his movements and the camera" - restyle: "restyle Video 1 as a clay animation" - change the scene: "make it night in Video 1, keep the motion and framing" It runs on Wan 3.0's reference-to-video API, which is how Alibaba does video editing; there is no separate edit API. ## Limits - the clip is 1 to 15 seconds at 16 fps or more (up to 5 clips, 15 seconds in total) - the clip plus the output can be at most 30 seconds - **Duration** is the length you get back: an edit returns the Duration you set, not the clip's own length. To edit a whole 8 second clip, set 8 - at most 2 seconds of video, across the clips, may sit past what a clip plays. A trim saved without re-encoding keeps those hidden frames and they are billed too, so past that the run is refused and names the clip to re-export Each clip is measured before you are charged. A clip that cannot be read, or that breaks a limit, is refused with a message, and you are not charged. ## What a run costs Per second of the clip plus per second of your Duration, at your resolution's rate (Prime costs about 40% more). The card shows that price before you run when the board knows the clip's length; when it does not yet, the card prices 15 seconds of clip. Either way the run charges the clip's length measured from the file before it starts. A 5 second 720p edit of a 7.7 second clip is 146 credits on Wan 3.0 and 204 on Prime. The charge never goes up after the run; if less is billed, the difference is refunded. --- _Auto-generated from the Wireflow node registry._ Last updated: 2026-11-03 --- Documentation index: fetch https://www.wireflow.ai/llms.txt for the full list of Wireflow docs.