Text to Video
Describe the subject, action and setting to create storyboards, product concepts or short social clips.
Text & Image to VideoUp to 10 ReferencesOptional Audio1080P
Wan 3.0 is Alibaba Tongyi Lab's cinematic video model for 5 to 15 second scenes with natural lighting and smooth transitions. Guide it with text, first and last frames, or up to 10 images and 5 video clips, with optional generated audio at up to 1080P.
Create short scenes with Wan 3.0 using text, a first frame, two endpoints or image and video references. Choose 480P, 720P or 1080P, with optional audio.
Describe the subject, action and setting to create storyboards, product concepts or short social clips.
Animate a product photo, portrait or illustration, starting from the composition you already have.
Guide a new scene with up to ten images and five video references in mixed-reference mode.
Describe a push, pan or tracking move in your prompt. Keep the shot focused on one action.
Choose the resolution and clip duration for your edit, with generated audio available as an option.
Both share the listed modes and output formats. Compare their quotes using the same settings. Compare ↗
Choose your input, direct the movement, then generate and refine.
Start with text, frame endpoints or visual references that match your scene.
Describe the action and camera move. Choose the duration, resolution and audio setting.
Review the quote, generate your clip, then preview and download the result.
Generate AI images and videos with subscription credits or credit packs. They share one credit balance; image costs vary by model and resolution, while video costs vary by model and duration. New users get 10 free trial credits.
Cancel anytime
For individuals & casual creators
Ideal for personal projects & starters
For professional creators & teams
Most popular choice for professional creators
Designed for studios & enterprise scale
Enterprise solution for highest productivity
Both expose text, first-frame, endpoint and mixed-reference modes here. Their credit schedules differ.
Video reference guides a new generation; it does not append exact frames to an existing clip.
No. Wan 3.0 and Prime offer 480P, 720P and 1080P on this site.
Yes. Input-video duration changes the billing calculation. Review the live quote after adding your sources.