One model for text-to-video, frame-guided generation, multimodal references, video editing and continuation. Choose 480p, 720p or 1080p and generate clips up to 30 seconds without switching tools.
Try It
Set your parameters and start generating AI videos with the workflows and inputs currently supported on this page, including text, images, video clips, or audio where supported.
Describe the video you want to generate...
Visual media on this page was generated with Wan 3.0 in Vofy Studio and illustrates the creative workflows described. It is not a benchmark or a guarantee of output.
What's New
Wan 3.0 replaces the task-specific pipelines of earlier Wan releases with a single unified generator. The capabilities below reflect what Vofy exposes in Studio today.
Wan 3.0 text-to-video
Earlier Wan releases split text-to-video, image-to-video and editing across separate endpoints. Wan 3.0 unifies them, so the same model handles a prompt-only concept, a guided first or last frame, a multimodal reference set, a targeted edit of existing footage, and a continuation of a clip that already exists.
Wan 3.0 product shot
Wan 3.0 is the first Wan generation on Vofy to reach a 30-second single-pass duration. Pick 480p for fast drafts, 720p for social delivery, or 1080p for presentation-ready footage. Duration and resolution are priced independently, so you can trade cost against length and fidelity shot by shot.
Wan 3.0 nature shot
Video editing and video extension are first-class tasks rather than add-ons. Bring in a clip to trim, replace or refine part of it, or extend it with a guided new ending so a shot keeps its subject, grade and camera language instead of restarting from scratch.
Wan 3.0 outputs generated in Vofy Studio, from cinematic text-to-video through to product and portrait work.
Cinematic Text-to-Video
Getting Started
Start from text when you only have a concept, add a first or last frame when composition matters, attach references to steer subjects and style, or upload existing footage to edit or extend it.
Write the action, camera movement, setting and pacing. Keeping shots short and specific gives Wan 3.0 less room to drift across a longer 30-second window.
Select 480p, 720p or 1080p and a duration between 2 and 30 seconds, then generate and iterate. Draft cheap at 480p before committing to a 1080p pass.
Specifications
Use Cases
From social content to professional workflows, see how creators and teams are using AI video generation across industries.
Generate a complete 20 to 30 second scene in a single pass for short films, explainers and narrative tests.
Keep a product's look consistent across shots with multimodal references while the model handles camera and light.
Trim, replace or refine part of a clip you already have instead of regenerating the whole shot.
Extend a finished clip with a guided new ending so vertical and square cutdowns share the same visual language.
Everything you need to know about Wan 3.0.
Visual media on this page was generated with Wan 3.0 in Vofy Studio and illustrates the creative workflows described. It is not a benchmark or a guarantee of output.