Wan 3.0 is now in DayGen
Create up to 30 seconds of video from text, precise start and end frames, or a mixed reference set—with native sound in the same generation.
Choose the right starting mode
Start from a prompt for text-to-video, use Frames to anchor the opening and optional ending, or switch to References when the shot should follow existing images, clips, or audio. DayGen sends each workflow to the matching Wan 3.0 endpoint automatically.
- Use Text when the prompt should define the whole scene.
- Use Frames when the first or last composition must be exact.
- Use References for character, product, place, movement, or sound continuity.
Direct the result with richer references
Reference mode accepts up to 10 images, 5 videos, and 5 audio files, plus an optional public document URL and web page URL. Videos can total up to 15 seconds at 16 FPS or higher, while audio has its own 15-second combined limit. Pick from uploads, Gallery, folders, Me and Character avatars, Products, Logos, Places, Templates, Brand, or Team assets; DayGen preserves the selected media types and sends them through Wan’s native multimodal reference flow.
Balance duration, finish, and sound
Choose any duration from 2 to 30 seconds, output at 480p, 720p, or 1080p, and frame the shot with an adaptive or fixed aspect ratio. Native audio, prompt expansion, thinking, safety checks, and reproducible seeds stay part of the same recoverable DayGen job.