Wan 3.0 brings the regular and Prime text, image and reference workflows together in one family. Generate 2–30-second clips at 480p, 720p or 1080p from a written scene, one or two frame images, or a combination of visual, motion, sound and information references. Assign each source a role, describe the action and camera, and choose audio for synchronized sound. Both variants expose the same documented input methods with separate rates; video-reference requests include source-video time in the complete estimate.
Wan 3.0 is developed by Alibaba. Vidgo provides access to the model. Model names and trademarks belong to their respective owners.Select regular Wan 3.0 or Prime, then choose Text to Video for a new written scene, Image to Video for a starting frame or two endpoints, or Reference to Video for combined source material. Explain which image establishes appearance, which video guides movement and which audio supplies a sound reference. Review the task’s current rate with the complete media and output duration.
Alibaba Wan 3.0 Prime video model with text-to-video, image-to-video, and reference-to-video workflows at 480p, 720p, or 1080p for 2 to 30 seconds with optional synchronized audio.
Alibaba Wan 3.0 Prime video model with text-to-video, image-to-video, and reference-to-video workflows at 480p, 720p, or 1080p for 2 to 30 seconds with optional synchronized audio.
Alibaba Wan 3.0 Prime video model with text-to-video, image-to-video, and reference-to-video workflows at 480p, 720p, or 1080p for 2 to 30 seconds with optional synchronized audio.
Alibaba Tongyi Lab's Wan 3.0 multimodal video model with separate text-to-video, first/last-frame image-to-video, and reference-to-video workflows at 480p, 720p, or 1080p for 2 to 30 seconds.
Alibaba Tongyi Lab's Wan 3.0 multimodal video model with separate text-to-video, first/last-frame image-to-video, and reference-to-video workflows at 480p, 720p, or 1080p for 2 to 30 seconds.
Alibaba Tongyi Lab's Wan 3.0 multimodal video model with separate text-to-video, first/last-frame image-to-video, and reference-to-video workflows at 480p, 720p, or 1080p for 2 to 30 seconds.
Image generation accepts one or two image_urls in frame order. Reference generation accepts up to ten images, five videos and five audio references, plus one file reference or one link reference for supplementary information. Supply at least one reference category and choose either the file or link method when using those information sources. The prompt connects each contribution to the intended scene, motion and sound.
| Model / task | Input and workflow |
|---|---|
| Wan 3.0 Prime Text-to-Video | Alibaba Wan 3.0 Prime video model with text-to-video, image-to-video, and reference-to-video workflows at 480p, 720p, or 1080p for 2 to 30 seconds with optional synchronized audio. |
| Wan 3.0 Prime Image-to-Video | Alibaba Wan 3.0 Prime video model with text-to-video, image-to-video, and reference-to-video workflows at 480p, 720p, or 1080p for 2 to 30 seconds with optional synchronized audio. |
| Wan 3.0 Prime Reference-to-Video | Alibaba Wan 3.0 Prime video model with text-to-video, image-to-video, and reference-to-video workflows at 480p, 720p, or 1080p for 2 to 30 seconds with optional synchronized audio. |
| Wan 3.0 Text-to-Video | Alibaba Tongyi Lab's Wan 3.0 multimodal video model with separate text-to-video, first/last-frame image-to-video, and reference-to-video workflows at 480p, 720p, or 1080p for 2 to 30 seconds. |
| Wan 3.0 Image-to-Video | Alibaba Tongyi Lab's Wan 3.0 multimodal video model with separate text-to-video, first/last-frame image-to-video, and reference-to-video workflows at 480p, 720p, or 1080p for 2 to 30 seconds. |
| Wan 3.0 Reference-to-Video | Alibaba Tongyi Lab's Wan 3.0 multimodal video model with separate text-to-video, first/last-frame image-to-video, and reference-to-video workflows at 480p, 720p, or 1080p for 2 to 30 seconds. |
Existing regular and Prime records show two raccoon scenes, a suited-cat transition, a garden-gnome transition and a fox request combining images, motion video and laboratory audio. These are independent requests with their own sources. Inspect the actual clips and complete inputs to understand the controls in use.
Write the subject, ordered gestures, weather and camera route. The regular text record asks a raincoat-wearing raccoon to direct paper boats in a puddle, with rain, chitters and a distant bicycle bell. Inspect movement, scene structure and requested sounds against the prompt.
Describe the object interaction and audible contacts. The Prime laundry record asks a raccoon to scratch a record on a vibrating washing machine, with lid rattle and wet-paw sounds. Inspect the actual action and camera movement as a separate creative example.
Use two ordered images and describe the action between them. The regular cat record moves from a serious seated pose to a keyboard impact while retaining face markings, suit and desk. Compare both frames with motion, contact and requested keyboard sounds in the output.
Provide the beginning and ending states and describe the path. The garden-gnome record asks for a lean, launch and arc toward a koi-pond landing, retaining the figure and afternoon light. Inspect the actual progression and requested impact sounds against the two inputs.
Supply the image, motion and sound sources and state their contributions. The Prime fox request assigns image 1 to face, fur and coat, the video to gait and tail sway, and audio to laboratory room tone. Inspect the resulting character, movement and requested sound beside all four supplied media.
The regular case supplies two cat frames and asks for a five-second move into the keyboard-ending state. The Prime case supplies two visual references, a motion video and an audio recording; the prompt uses the first image for the fox’s appearance, the video for gait and the audio for laboratory ambience before placing the fox beside a bubbling beaker. Read each complete prompt and inspect every source with its generated result.
Begin exactly from Image 1 and finish on Image 2. In one continuous five-second shot, the suited tabby cat leans forward with mock seriousness, then suddenly face-plants into the keyboard. Papers twitch. The coffee cup stays put. Camera: locked medium shot with a tiny downward tilt at the impact. No cuts. Preserve the cat's face markings, suit, tie, desk, and lighting. Synchronized audio: chair creak, rapid keyboard clacks, a muffled meow. No readable text, letters, numbers, captions, labels, logos, brands, watermarks, advertisements, posters, UI screens, or product packaging.
Use image 1 for the fox's face, fur, and oversized white lab coat. Use video 1 only for the walking gait and tail sway. Use audio 1 for the laboratory room-tone: HVAC hum and distant glass. New 5-second 16:9 scene: the same fox walks along a lab bench, pauses, and sniffs a bubbling beaker. Medium tracking shot, eye level. Native audio: the supplied lab room-tone plus paw steps. No logos, no readable text, no products, no packaging, no prices, no CTA, no advertising, no watermark, no brand marks.
Prepare a written scene, a pair of compatible frames or a set of references with clear roles. Describe the action, camera, materials and sound, then choose regular or Prime and the intended duration. Reviewed clips can support animated stories, character comedy, object-state transitions, motion studies and scenes with a specific acoustic setting.
Write the subject, setting, gesture sequence and audible events. Generate a clip and review the scene and timing for an animated story or storyboard proposal.
Describe a readable setup, a physical action and its ending, including the camera and contact sounds. Inspect the actual progression for a short character performance or scene concept.
Prepare compatible endpoint images and explain how the subject travels between them. Compare the clip with both states for an action, transition or material-motion proposal.
Provide images for appearance and videos for the intended motion, assigning each source a role. Inspect the combined character, proportions and movement for an animation or performance study.
Provide an audio reference and describe the corresponding space and audible actions, then enable audio. Review the generated clip and requested acoustic relationship for a laboratory, workshop or atmosphere concept.
Prepare a file or link reference for supplementary context, alongside any visual or sound references. Explain how that information relates to the intended scene and inspect the returned clip for a visual explanation or story-development draft.
Regular and Prime have separate rates for 480p, 720p and 1080p. Billing uses output duration plus the total duration of reference videos, multiplied by the selected variant and resolution rate. Requests with image, audio or information references use the output duration when they supply no reference video. The dynamic table shows current rates per billable second; let source-video durations load on the task page and review the full estimate for the intended 2–30-second output.
| Model | Provider | Workflow | Input material | Output specification | Starting rate |
|---|---|---|---|---|---|
| Wan 3.0 Prime Text-to-Video | Alibaba | Text to Video | Text prompt | 1080p | $0.068 / billable second |
| Wan 3.0 Prime Image-to-Video | Alibaba | Image to Video | 1–2 starting/ending frames | 1080p | $0.068 / billable second |
| Wan 3.0 Prime Reference-to-Video | Alibaba | Reference to Video | Images / videos / audio / information | 1080p | $0.068 / billable second |
| Wan 3.0 Text-to-Video | Alibaba | Text to Video | Text prompt | 1080p | $0.05 / billable second |
| Wan 3.0 Image-to-Video | Alibaba | Image to Video | 1–2 starting/ending frames | 1080p | $0.05 / billable second |
| Wan 3.0 Reference-to-Video | Alibaba | Reference to Video | Images / videos / audio / information | 1080p | $0.05 / billable second |
Test your creative brief online, then bring the verified request into your application.
Open the selected task from the model list above. Enter the scene or motion instructions and supply the matching frames or references. Choose duration, resolution, framing and audio and review the complete estimate. Inspect the output against all source appearances, endpoints, motion and sound before preparing another request.
Choose a task, inspect its settings and cost, and follow the result from an online test to an authenticated API request.
Select regular or Prime in the model list, then choose text, one/two-frame animation or a reference request. Prepare the required sources, choose an integer duration from 2 to 30 seconds and 480p/720p/1080p, then select framing and audio. For reference videos, include their complete durations when reviewing the estimate.
Open the selected task from the model list above. Enter the scene or motion instructions and supply the matching frames or references. Choose duration, resolution, framing and audio and review the complete estimate. Inspect the output against all source appearances, endpoints, motion and sound before preparing another request.
Compare the regular or Prime rate for your resolution and the sum of output and reference-video seconds. Wait for the input durations to load and use that complete estimate with the planned test count to budget the project.
Read the actual prompt and inspect every source image or video alongside its generated result. Use the recorded examples to understand how to describe input roles, action progression and the details to preserve in your own request.
Retain the task ID returned by the API to query status and retrieve completed file URLs. Use your online generation history to review earlier results and the creative direction you tested.
Use the documentation linked from each task for its exact model identifier, accepted inputs, authentication and response format. Integrate the same task you tested online so its media and settings match the request.
Wan 3.0 is an Alibaba video family with regular and Prime text, image and reference tasks on Vidgo. Both provide 2–30-second output at 480p/720p/1080p, one-to-two-frame input and multimodal reference fields. They use separate model identifiers and rates, with reference-video duration included in billing.
Explore model introductions, API guides and platform comparisons to understand input preparation, request integration and cost planning for your project.
