Skip to main content
Kyeo AI
AI video model
Alibaba
Wan 2.7

Wan 2.7 Video

Wan 2.7 supports text-to-video, first-frame or first-and-last-frame image-to-video, and video editing. It currently offers 720p and 1080p, so compare media requirements, duration, framing, and estimated credits together.

Workflows
Text to video, image to video, and video editing
Resolution
720p or 1080p
Duration
2–15 seconds for text/image; 2–10 seconds or source duration for editing
Credits
16/second at 720p; 24/second at 1080p
One model covers text-to-video, image-to-video, and video-editing workflows.
Image-to-video accepts a first frame or first and last frames for clearer visual boundaries.
Clear per-second credit tiers for 720p and 1080p make small test runs easier to budget.
Prompt expansion, watermarking, negative prompts, random seed, and editing audio handling are exposed as workbench controls.
Use this modelView credit pricingBack to Model Hub
30-second overview
Wan 2.7
16 credits/second at 720p; 24 credits/second at 1080p
What it does best
Wan 2.7 suits workflows that need text ideation, reference-image animation, and adjustments to an existing video in one model family. Its range of workflows does not replace storyboarding or source-media checks.
Best for
Consider it for product motion, character clips, social video, concept previews, transitions with clear first and last frames, and changes based on an existing video.
Popular searches
Which video workflows does Wan 2.7 support?Can Wan 2.7 use first and last frames?How long can a Wan 2.7 video be?

At a glance

What is this model like?

Start from text when you have no media, upload one image for a first frame, use two images to constrain the opening and closing frames, or upload a video for editing. Duration and aspect-ratio rules differ by workflow, so review each field before submitting.

What it does best
Wan 2.7 suits workflows that need text ideation, reference-image animation, and adjustments to an existing video in one model family. Its range of workflows does not replace storyboarding or source-media checks.
Best for
Consider it for product motion, character clips, social video, concept previews, transitions with clear first and last frames, and changes based on an existing video.
Why use it on Kyeo AI
Kyeo AI presents the currently available workflows, uploads, duration, resolution, and estimated credits together so you can compare Wan 2.7 with other video models before submitting.

Key facts

Quickly assess whether this model fits your use case.

Category
AI video model
Developer
Alibaba
Family
Wan 2.7
Task type
Asynchronous generation
Text to video
Used when no media is uploaded
Image to video
Upload one first frame or two first-and-last-frame images
Video editing
Upload one video and optionally one reference image
Aspect ratios
16:9, 9:16, 1:1, 4:3, and 3:4

Also known as

The same model may appear under different names across documentation and community discussions; this list keeps them easy to search and compare.

Wan 2.7
Tongyi Wanxiang 2.7
Wan 2.7 Video

Common questions

These practical questions focus on the task, input conditions, and result requirements you should confirm before choosing.

Which video workflows does Wan 2.7 support?
Can Wan 2.7 use first and last frames?
How long can a Wan 2.7 video be?
Which image and video formats does Wan 2.7 accept?
How many credits do 720p and 1080p use?
Can Wan 2.7 edit an existing video?
What is different between Wan 2.7 and Wan 2.5?
Is Wan 2.7 better suited to product clips or character shots?

Selection guide

Use these decision points when choosing a model.

1
Choose from the media you already have

Use text-to-video with no source media, image-to-video with one or two key frames, and video editing when the source clip must remain part of the result.

2
Validate at 720p and a short duration

Test the subject, motion, camera, and composition first. Move to 1080p or a longer duration only after the direction is stable.

3
Check the form before assuming extra controls

The current workbench determines upload counts and adjustable fields. Do not infer that a feature offered in another product is available here.

Popular comparisons

Compare common alternatives on the same task to clarify differences in inputs, controls, and cost.

Wan 2.7 vs Wan 2.6: which should I use?
Wan 2.7 vs Wan 2.5: which video model fits?
Wan 2.7 vs Seedance 2: which should I use?
How does the cost of 720p compare with 1080p?

Model comparison

Compare the current model with alternatives at a glance.

Kyeo AI workflows
Wan 2.7 Video
Text to video, first-frame or first-and-last-frame image to video, and video editing
Wan 2.6
Check its current detail page
Wan 2.5
Check its current detail page
Text/image duration
Wan 2.7 Video
Whole seconds from 2–15
Wan 2.6
See its current detail page
Seedance 2
See its current detail page
Resolution
Wan 2.7 Video
720p or 1080p
Wan 2.5
See its current detail page
Seedance 2
See its current detail page
Reference media
Wan 2.7 Video
One or two images, or one video with an optional reference image
Wan 2.6
Follow its current upload fields
Seedance 2
Follow its current upload fields
Credits
Wan 2.7 Video
16/second at 720p; 24/second at 1080p
Wan 2.5
Charged by its current resolution and duration
Seedance 2
Charged by its current mode and output settings

Practical usage insights

Practical guidance based on public sources, current on-site limits, and representative tasks.

First and last frames help when a transition has a clear destination

They provide a visible start and finish, while the prompt still needs a concise action and camera direction for the movement between them. Split complicated changes into shorter shots.

Total cost depends on rework

1080p uses more credits per second. If subject and motion are not yet stable, a short 720p test usually controls total spend better before the final output is upgraded.

Capabilities

Text to video

Generate a 2–15 second clip without uploading media. Set aspect ratio, resolution, negative prompt, prompt expansion, watermark, and random seed.

First-frame or first-and-last-frame image to video

Upload one image as the first frame or two images as opening and closing frames. Images can be JPG, PNG, or WebP up to 30 MB each.

Video editing

Upload one MP4 or MOV up to 30 MB and optionally one reference image. Audio handling can be automatic or preserve the source audio.

Use cases

Product and brand clips

Create light camera movement, material changes, or contextual scenes from a product image. Test packaging text at small scale when legibility matters.

Character shots

Use a first frame to anchor the opening appearance or first and last frames to plan how the action settles. Split large movements into shorter shots.

Reworking an existing video

Adjust a source clip that meets the upload limits and decide whether the delivered version should keep its original sound.

Prompt tips

Lead with the subject's action

State who does what, then add the environment, camera, and details that must remain. Avoid stacking incompatible actions.

Give the camera one primary movement

Start with one push, pull, pan, or orbit. Test complex camera work in separate rounds so failures can be diagnosed.

For image-to-video, describe what happens next

The reference already supplies appearance and composition. Focus the prompt on the action, camera change, and details that should not drift.

Why choose it

Covers text ideation, reference-image animation, and video editing in one model.
First-and-last-frame input gives transitions and transformations clearer visual boundaries.
Supports landscape, portrait, square, 4:3, and 3:4 outputs where the workflow exposes aspect ratio.
The relationship between resolution and per-second credits is straightforward to estimate.

What to know first

The current public workbench does not offer video continuation or a separate audio-reference upload.
Video editing is capped at 10 seconds and text/image workflows at 15 seconds; longer stories need multiple shots.
First and last frames constrain endpoints but do not guarantee every intermediate frame follows a precise path.
Outputs are probabilistic; people, text, brand details, and media rights still require manual review.

Adjustable parameters

Quickly assess whether this model fits your use case.

Output resolution
resolution
Optional
Parameter type: Select
Default: 720p
720p
1080p
Output duration
duration
Optional
Parameter type: Number
Default: 5 seconds
Whole seconds from 2–15 for text/image; 2–10 for editing, or 0 to keep source duration
Aspect ratio
aspect_ratio
Text/edit
Parameter type: Select
Default: 16:9
16:9
9:16
1:1
4:3
3:4
Negative prompt
negative_prompt
Optional
Parameter type: Text
Up to 500 characters
Prompt expansion
prompt_extend
Optional
Parameter type: Toggle
On by default
On
Off
AI-generated watermark
watermark
Optional
Parameter type: Toggle
Off by default
Off
On
Audio handling during editing
audio_setting
Video editing only
Parameter type: Select
Automatic by default
Automatic
Keep source audio
Random seed
seed
Optional
Parameter type: Number
0–2147483647

Credit usage

16 credits/second at 720p; 24 credits/second at 1080p

Credits are calculated from output duration and resolution: 16 credits per second at 720p and 24 credits per second at 1080p. Check the estimate shown in the workbench before submitting.

Budget tip

Before batch generation, run an A/B test with the same assets across the current model and alternatives to validate quality and avoid wasting credits.

FAQ

Related models

Compare these similar candidates before deciding.

Wan 2.6

No media selects text-to-video, exactly one image selects image-to-video, and one to three videos select video editing; images and videos cannot be mixed. The default is 1080p, 5 seconds, shot structure Off, and content filtering On.

AI video model
70–315 credits / request
View detailsUse now

Wan 2.5 Video

Review Wan 2.5 Video on Kyeo AI with text-to-video or one-image input, 5/10 seconds, 720p/1080p, prompt constraints, and 60–200-credit pricing. Kyeo charges by resolution and duration: 60 credits for 720p at 5 seconds, 120 for 720p at 10 seconds, 100 for 1080p at 5 seconds, and 200 for 1080p at 10 seconds. The 720p 5-second default costs 60 credits. How are Wan 2.5's 60/100/120/200 credits calculated? — Review Wan 2.5 Video on Kyeo AI with text-to-video or one-image input, 5/10 seconds, 720p/1080p, prompt constraints, and 60–200-credit pricing.

AI video model
60/100/120/200 credits per request
View detailsUse now

Seedance 2.0

Seedance 2.0 / Capabilities — Text accepts no media; frames requires a first frame and allows a last frame; reference requires a prompt and at least one image, video, or audio reference. Reference media cannot be sent with endpoint-frame fields. Seedance 2.0 supports three mutually exclusive text, frame, and multimodal-reference scenes. The current callable output set is 720p, 1080p, and 4K for 4–15 seconds; video-reference requests are available only at 1080p or 4K because those are the current priced combinations. 164–3,840 credits per request

AI video model
164–3,840 credits per request
View detailsUse now

Sources

Content is based on model documentation, feature references, and the settings available on Kyeo AI.

Source note

The workflows, media limits, visible controls, and credits on this page describe the version currently available on Kyeo AI. Use the page and workbench as the current source of truth; features from other products or related versions are not assumed here.

Last updated: 2026-08-29
Wan 2.7 current interface notes
Platform

Used to check the input modes, visible controls, media limits, and availability of the version currently connected to this site. The page and workbench show the actual options.