AI video model
Wan 2.7 Video AI Video Generator
Choose Wan 2.7 Video when you need a Wan AI video generator whose written scene can be constrained by planned frames, a motion clip, driving audio, or a negative prompt.
Wan 2.7 Video task directions
These local references help turn the current Wan 2.7 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; optional compatible reference media: image (up to 2), video (up to 1), audio (up to 1)
- Current controls
- Prompt length: Up to 5,000 characters · Duration: 2–15 seconds · Output resolution: 720P / 1080P · Framing: Text-to-video: 5 aspect-ratio choices; image-to-video: follows the supplied image
- Selection boundary
- The reference media guide the direction but do not guarantee transferred motion, identity, or lip sync. Compare a text-led model when no source media should constrain the clip, and remember that a prompt is required with image or video references here.
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; optional compatible reference media: image (up to 2), video (up to 1), audio (up to 1)
- Duration
- 2–15 seconds
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 2.7 Video
Current page
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
Wan 2.6 Video
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
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 2.7 Video
Direct a clip with multiple constraints
Wan 2.7 Video currently supports start and end frames, one motion clip, one driving audio file, a required prompt for reference-guided work, and a negative prompt.
Add compatible media when it helps
Text prompt required; optional compatible reference media: image (up to 2), video (up to 1), audio (up to 1). Only upload media you are allowed to use for the current project.
Confirm the clip settings
Current clip settings include 2–15 seconds, 720P / 1080P, and Text-to-video: 5 aspect-ratio choices; image-to-video: follows the supplied image.
Current Wan 2.7 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; 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 |
| Output resolution | 720P / 1080P |
| Framing | Text-to-video: 5 aspect-ratio choices; image-to-video: follows the supplied image |
| Additional controls | Negative prompt, Start and end frames |
AI video model
When to choose Wan 2.7 Video
Prompt-led video direction with frames, motion clip, driving audio, and negative prompt.
Current workflow fit
Choose Wan 2.7 Video when you need a Wan AI video generator whose written scene can be constrained by planned frames, a motion clip, driving audio, or a negative prompt.
When to compare another model
The reference media guide the direction but do not guarantee transferred motion, identity, or lip sync. Compare a text-led model when no source media should constrain the clip, and remember that a prompt is required with image or video references here.
How to create a video with Wan 2.7 Video
Choose the source that controls the first state, end state, motion path, or audio cue, then write a prompt that explains how those inputs should work together.
- 1
Assign each source one role
Decide whether a source is the start frame, end frame, motion reference, or driving audio before adding it; avoid asking one asset to do every job.
- 2
Add reference media when needed
Add approved compatible media only when an existing frame, motion, or sound should guide the result.
- 3
Confirm duration and output controls
Confirm the current 2–15 seconds, 720P / 1080P, and Text-to-video: 5 aspect-ratio choices; image-to-video: follows the supplied image 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 2.7 Video FAQ
- Do image or video references replace the prompt in Wan 2.7 Video?
- No. The current reference-guided workflow still requires a written prompt. Use it to explain the intended action, camera behavior, and relationship between source media.
- Can I start Wan 2.7 Video from reference media?
- Text prompt required; optional compatible reference media: image (up to 2), video (up to 1), audio (up to 1). Check the current media type and quantity limits before generation, and upload only approved source material.
- How long can a Wan 2.7 Video video be?
- The current video-duration setup is 2–15 seconds.
- What output controls does Wan 2.7 Video currently offer?
- Current output options include 720P / 1080P and Text-to-video: 5 aspect-ratio choices; image-to-video: follows the supplied image. Other available controls include negative prompt, start and end frames.
- 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.