AI video model
Wan 2.6 Video AI Video Generator
Choose Wan 2.6 Video when an approved source video should establish the starting motion and composition, while a written direction explains the intended transformation.
Wan 2.6 Video task directions
These local references help turn the current Wan 2.6 Video input and control contract into a concrete task direction. They are not presented as output from this model.
Every card identifies whether it is a verified model-family example or a visual reference. Reference cards are not model benchmarks or before-and-after claims.
- Input contract
- Text prompt required; 1 to 5 source videos are required
- Current controls
- Prompt length: Up to 5,000 characters · Duration: 5s, 10s options · Output resolution: 720P / 1080P · Framing: Framing follows the supplied media
- Selection boundary
- This workflow requires both a source video and a written direction. The source guides the transformation, but it does not guarantee exact motion, identity, or scene preservation. Choose a text- or image-led video model when no source video should constrain the result.
Action beat
State one subject action and the moment the clip should begin from.
- Task direction
- State one subject action and the moment the clip should begin from.
Reference direction, not a model output
Local ImageStyle visual reference. It is not presented as a model-specific result.
Camera direction
Name the camera behavior and the visual change it should reveal over time.
- Task direction
- Name the camera behavior and the visual change it should reveal over time.
Reference direction, not a model output
Local ImageStyle visual reference. It is not presented as a model-specific result.
Ending state
Define the final visual state, without treating this reference as a result from the current model.
- Task direction
- Define the final visual state, without treating this reference as a result from the current model.
Reference direction, not a model output
Local ImageStyle visual reference. It is not presented as a model-specific result.
- Create
- AI video
- Input
- Text prompt required; 1 to 5 source videos are required
- Duration
- 5s, 10s options
Compare available settings with related models
Check whether the input, output, and framing controls fit the job before you open a workspace. This table does not treat the example media as a cross-model performance test.
Wan 2.6 Video
Current page
Prompt-guided transformations of supplied source videos with 5 or 10 second output, 720p or 1080p, and multi-shot control.
- Input
- Text prompt required; 1 to 5 source videos are required
- Prompt length
- Up to 5,000 characters
- Duration
- 5s, 10s options
Wan 2.7 Video
Prompt-led video direction with frames, motion clip, driving audio, and negative prompt.
- Input
- Text prompt required; optional compatible reference media: image (up to 2), video (up to 1), audio (up to 1)
- Prompt length
- Up to 5,000 characters
- Duration
- 2–15 seconds
Seedance 2 Mini
Short multimodal clips with text, media references, audio generation, and web search.
- Input
- Text prompt or compatible reference media: image (up to 3), video (up to 3), audio (up to 3)
- Prompt length
- Up to 20,000 characters
- Duration
- 4–15 seconds
Seedance 2 Fast
The Fast-labelled multimodal workflow with a 15-second default clip.
- Input
- Text prompt or compatible reference media: image (up to 5), video (up to 3), audio (up to 3)
- Prompt length
- Up to 20,000 characters
- Duration
- 4–15 seconds
What you can control with Wan 2.6 Video
Transform a supplied source video with direction
Wan 2.6 Video currently requires a written direction and one to five source videos, exposes 5 or 10 second output, 720p or 1080p, and a multi-shot control. Framing follows the supplied source media.
Upload the required media
Text prompt required; 1 to 5 source videos are required. Only upload media you are allowed to use for the current project.
Confirm the clip settings
Current clip settings include 5s, 10s options, 720P / 1080P, and Framing follows the supplied media.
Current Wan 2.6 Video settings
These settings come from the current ImageStyle model configuration and help you decide whether the workflow fits the job.
| Setting | Current availability |
|---|---|
| Input | Text prompt required; 1 to 5 source videos are required |
| Prompt length | Up to 5,000 characters |
| Duration | 5s, 10s options |
| Output resolution | 720P / 1080P |
| Framing | Framing follows the supplied media |
| Additional controls | Multi-shot |
AI video model
When to choose Wan 2.6 Video
Prompt-guided transformations of supplied source videos with 5 or 10 second output, 720p or 1080p, and multi-shot control.
Current workflow fit
Choose Wan 2.6 Video when an approved source video should establish the starting motion and composition, while a written direction explains the intended transformation.
When to compare another model
This workflow requires both a source video and a written direction. The source guides the transformation, but it does not guarantee exact motion, identity, or scene preservation. Choose a text- or image-led video model when no source video should constrain the result.
How to create a video with Wan 2.6 Video
Start with one approved source video, choose the five- or ten-second delivery and output resolution, then write the specific action, visual treatment, and camera change the transformation should follow.
- 1
Choose the source video before writing the change
Confirm that the source video is authorized and already contains the movement or composition you want to transform. Then describe one deliberate change instead of asking the prompt to replace every element at once.
- 2
Check the source video and transformation direction
Confirm that the source video has the right subject, framing, and action to start from, then use the written direction only to state what should change or remain.
- 3
Confirm duration and output controls
Confirm the current 5s, 10s options, 720P / 1080P, and Framing follows the supplied media in the workspace before generation.
- 4
Generate and review continuity
Before public use, inspect subject motion, camera changes, visible text, sound, and the final frame.
Checks before you create and publish
- Treat the workspace as current
- Model availability and settings can change. Use the options shown in the current workspace before you submit.
- Use approved source media
- When you upload images, video, or audio, confirm that you are allowed to use and publish it for the current project.
- Review the generated video
- Before publishing, manually check motion continuity, text, sound, people, product details, and marks.
Wan 2.6 Video FAQ
- Can I use Wan 2.6 Video without uploading a source video?
- No. Wan 2.6 Video is a source-video transformation workflow: the current configuration requires at least one source video and a written direction. Choose a text- or image-led model when no source video is available.
- Can I start Wan 2.6 Video from reference media?
- Text prompt required; 1 to 5 source videos are required. Check the current media type and quantity limits before generation, and upload only approved source material.
- How long can a Wan 2.6 Video video be?
- The current video-duration setup is 5s, 10s options.
- What output controls does Wan 2.6 Video currently offer?
- Current output options include 720P / 1080P and Framing follows the supplied media. Other available controls include multi-shot.
- Can I publish a generated result without review?
- No. Before public use, manually review motion continuity, text, sound, product details, and any other element that must be accurate.
Updated:
Capability source: Current ImageStyle video-model configuration.