Wan 3.0 creates directed 2-30 second video from coordinated image, motion, and audio references with adaptive framing and native sound.
Upload one or more reference assets, mention their roles in the prompt, then choose the output length, frame, and resolution.
Final usage is the selected resolution rate multiplied by output duration.
Similar Models
Create videos up to 30 seconds, combine as many as 50 multimodal references, and refine specific moments with frame-level control.
A multimodal video generation model for text prompts, first-frame animation, and reference-guided production clips.
Create 4 to 10-second videos from text, up to seven reference images, or one short reference video with synchronized sound.
Model overview
Wan 3.0 on sjolt provides a focused reference-to-video workflow for character continuity, product motion, visual development, campaign scenes, music-led sequences, and short-form storytelling. Coordinate images, MP4 clips, and audio tracks, then retrieve the completed MP4 through the shared asynchronous task API.
Combine up to 10 images, 5 MP4 clips, and 5 audio tracks in one request. Assign every asset a clear role with @ mentions so subjects, visual language, camera movement, timing, dialogue, ambience, or music remain easy to interpret.
Describe the opening state, subject action, camera path, environmental response, sound cues, and intended ending. Use concise temporal language to align visible events with dialogue, effects, ambience, or musical beats.
Use adaptive framing or choose 16:9, 9:16, 1:1, 4:3, 3:4, select 480p, 720p, or 1080p, and create a whole-number clip from 2 to 30 seconds. Submit once, then poll the task identifier or receive a webhook when the video is ready.
Model characteristics
Use images for identity and composition, videos for motion and camera rhythm, and audio for dialogue, effects, ambience, or music direction.
Generate from references alone or add a written production brief with explicit @ mentions for each uploaded asset.
Choose adaptive framing or 16:9, 9:16, 1:1, 4:3, 3:4, output from 480p through 1080p, and a whole-number duration from 2 to 30 seconds.
Use one provider-qualified create route, the shared task-status endpoint, and optional webhook delivery for repeatable production pipelines.
FAQ
The initial release exposes reference-to-video with image, video, and audio guidance. Dedicated text-to-video and image-to-video variants can be added under the same Wan 3.0 model namespace later.
Upload up to 10 PNG, JPG, JPEG, or WebP images, 5 MP4 clips, and 5 MP3, WAV, M4A, AAC, or OGG audio tracks. At least one reference asset is required.
Reference videos may total at most 15 seconds, reference audio may total at most 15 seconds, and reference-video length plus output length cannot exceed 30 seconds.
No. References can drive the request alone. When adding instructions, mention each asset as @Image, @Video, or @Audio and describe its intended role.
Choose adaptive framing or 16:9, 9:16, 1:1, 4:3, 3:4, 480p, 720p, or 1080p, and a whole-number duration from 2 to 30 seconds.
Submit the provider-qualified reference route, keep the returned task identifier, then poll the shared task endpoint or receive a webhook. Successful tasks return the generated MP4 URL.
