Chrome ExtensionWan 3.0 Video Prompt Generator
Generate optimized video prompts for Alibaba's Wan 3.0. Plan clips up to 30 seconds at 1080p with audio in the same pass, timestamped multi-shot storyboards, and references from images, video, audio, documents or a web page.
Describe the main visual scene — subjects, environment, mood, and key visual details
Generated Prompt
Fill in the form and click "Generate" to create an optimized Wan 3.0 video prompt.
Tip: Describe the motion and temporal progression of your scene. Think in terms of "what happens over time" rather than a static description.
Wan 3.0 Tips
- • Wan 3.0 generates up to 30 seconds in one pass: plan a beginning, middle and end instead of a single action
- • For multi-shot clips, write a timestamped storyboard with about 4 to 6 seconds per shot
- • Audio comes out with the video: write dialogue in quotes and name the music and sound effects you want
- • Refer to uploaded references by type and order, e.g. "Image 1", "Video 1", "Audio 1" (each type is counted separately)
- • Alibaba says on-screen text is not fully reliable yet, so keep text in frame short or add it in editing
- • Editing an existing clip? Start with an edit keyword ("Edit video: replace...", "Remove...") and for extensions start with "Extend" or "Continue" and say forward, backward or both
- • Specify the visual style clearly: Wan handles photorealistic through anime and painterly looks
Wan 3.0 Prompt Templates
Copy-ready shot briefs built around what this model actually rewards. Swap the [BRACKETED] parts for your own scene, then paste straight into the tool.
Cinematic Shot
CinematicStraightforward subject-action-camera structure.
[SUBJECT — detailed appearance] [ACTION] in [ENVIRONMENT]. Camera: [MOVEMENT AND FRAMING]. Lighting: [SETUP AND DIRECTION]. Motion: [WHAT MOVES AND AT WHAT SPEED]. Style: [GRADE AND LOOK]. Duration: [SECONDS] seconds.
Image-to-Video
TechniqueAnimating a still with explicit motion scope.
Animate the supplied image. Moving elements: [LIST AND HOW MUCH]. Fixed elements: [LIST]. Camera: [MOVE OR STATIC]. Preserve the image's composition, palette, lighting and subject appearance. [SECONDS] seconds.
Character Performance
CharacterPerformance-led shot with a described emotional beat.
[CHARACTER — face, build, wardrobe] in [SETTING]. Expression moves from [FIRST] to [SECOND] across the clip. Micro-motion: [SPECIFIC DETAILS]. Camera: [FRAMING], [MOVE]. Lighting: [SETUP]. Background: [BACKGROUND] softly out of focus. [SECONDS] seconds.
Environmental Atmosphere
ScenesMood-led shot driven by light and small motion.
[ENVIRONMENT] in [CONDITIONS AND TIME OF DAY]. The only motion is [WHAT MOVES — e.g. mist drifting between the trees and light shifting through the canopy]. Camera: [NEARLY STATIC WITH A SLOW DRIFT]. Lighting: [DESCRIPTION]. Grade: [GRADE]. [SECONDS] seconds.
Product Turntable
CommercialClean commercial rotation with fixed lighting.
[PRODUCT] on [SURFACE] against [BACKDROP], rotating slowly and continuously. [MATERIAL DETAIL] catching the light through the rotation. Lighting fixed: [SETUP]. Product stays centred and sharp. Camera locked off. Constant speed. [SECONDS] seconds.
Stylised Animation
StylisedNon-photoreal work with a consistent style anchor.
[SCENE AND ACTION] in [STYLE]. [SUBJECT DESCRIPTION]. Palette: [COLOURS]. Motion quality: [QUALITY]. Camera: [FRAMING AND MOVE]. Lighting: [STYLISED LIGHTING]. Style consistent across every frame. [SECONDS] seconds.
Wan Update Log
Wan 3.0
● LatestAugust 24, 2026- Public beta on Alibaba Cloud Model Studio from August 6, 2026; formal release on August 24 (model IDs wan3.0-video and wan3.0-video-prime).
- Clips up to 30 seconds in one pass at 480p, 720p or 1080p and 30fps, up from 15 seconds in Wan 2.7.
- Dialogue, background music and sound effects are generated together with the video.
- Omni-reference input: up to 10 images, 5 videos and 5 audio clips, plus one document or one public web page per request.
- List pricing of $0.05, $0.10 and $0.20 per second for 480p, 720p and 1080p. Alibaba notes audio texture and on-screen text are still being improved.
Wan 2.7
Spring 2026- Text-to-video and image-to-video with clips up to 15 seconds.
- Introduced the video editing features that carry forward into Wan 3.0.
Frequently Asked Questions
What is Wan 3.0?
Wan 3.0 is Alibaba's latest video generation model (API model IDs wan3.0-video and wan3.0-video-prime). It generates clips of 2 to 30 seconds at 480p, 720p or 1080p and 30fps, with dialogue, music and sound effects generated in the same pass.
What's new in Wan 3.0?
Maximum length doubles from 15 seconds (Wan 2.7) to 30 seconds in a single pass, and audio is generated with the picture. It also adds "omni-reference" input: up to 20 materials per request, with up to 10 images, 5 video clips and 5 audio clips (video and audio capped at 15 seconds total each), plus one document (pdf, doc/docx, ppt/pptx, xls/xlsx, txt, md) or one public web page. Public beta opened on August 6, 2026 and the formal release followed on August 24. The same model also does first/last-frame image-to-video, video editing (add, remove or modify elements, restyle, relight, edit dialogue) and extension forward, backward or both ways, as long as input plus output stays within 30 seconds.
How do I reference my uploads in a Wan 3.0 prompt?
Alibaba's guide says to refer to materials by type and order, for example "Image 1", "Video 1" or "Audio 1". Each type is numbered separately. An audio reference such as music or a voice can drive beat-synced dance or lip-sync.
How much does Wan 3.0 cost?
Alibaba lists $0.05 per second at 480p, $0.10 per second at 720p and $0.20 per second at 1080p, so a 30-second 1080p clip costs about $6 at list price.
What aspect ratios does Wan 3.0 support?
16:9, 9:16, 1:1, 4:3 and 3:4. The default is adaptive, which follows the aspect ratio of your reference material.
Is this tool free?
Yes! You get 1 free prompt generation per day. For unlimited access, sign up for a Promptslove membership.
Want Unlimited AI Prompt Generation?
Get unlimited access to all AI tools, 29,000+ premium prompts, courses, and resources.