Wan 2.7 Video is Rivya's newer Wan AI video model for text-to-video and image-to-video drafts where you want current Wan motion quality, prompt control, and short-form scene exploration.
Resolution and duration pricing: 720p = 16 credits/sec, 1080p = 24 credits/secSupports text-to-video, image-to-video, and video editing in one model
Image-to-video can use one image or a first-and-last-frame pair
Input
Prompt, up to 2 images, or 1 video + 1 image
Output
AI Video Generator
Credits
From 80 credits per generation
Best for
Short-form product promos and social cutdowns
Example output
Preview for Steampunk Chef Feast Film, focused on scene setup, camera path, motion continuity, editable details, and the final hero frame.
Check the input, output, credits, and example result, then try this model directly on the page. Move into Studio when you need saved history, assets, or longer iteration.
Example output
Preview for Steampunk Chef Feast Film, focused on scene setup, camera path, motion continuity, editable details, and the final hero frame.
Best for
Short-form product promos and social cutdownsFirst-and-last-frame style motion tests from imagesQuick video edits from an existing source clip5 to 15 second Wan experiments plus short source-video edits
Supports
Text to VideoImage to VideoVideo to Video
Online trial
Try Wan 2.7 Video
Use Wan 2.7 Video for newer Wan text-to-video and image-to-video drafts with current motion quality.
Results
Wan 2.7 Video
AlibabaText to Video
Wan 2.7 Video is Rivya's newer Wan AI video model for text-to-video and image-to-video drafts where you want current Wan motion quality, prompt control, and short-form scene exploration.
Wan 2.7 Video
No result yet. Submit a prompt to start a run.
Text to VideoImage to VideoVideo to Video
Prompt starters
Start Wan 2.7 Video with a proven prompt
Use a template already mapped to Wan 2.7 Video when you want a stronger first run than a blank prompt.
Supports text-to-video, image-to-video, and video editing in one model
Image-to-video can use one image or a first-and-last-frame pair
Best-fit tasks
Best-fit tasks
Short-form product promos and social cutdownsFirst-and-last-frame style motion tests from imagesQuick video edits from an existing source clip5 to 15 second Wan experiments plus short source-video edits
Model proof
A fictional open-wheel car stops, the crew swaps tires in clear rhythm, and the shot ends as the car launches from pit lane.
Formula-style pit stop documentary video preview with tire-change close-ups and coordinated crew motion.
Preview for a dawn steel industrial motion poem, focused on steel surfaces, controlled haze, reflection continuity, camera glide, and the final wide frame.
Dawn steel industrial video preview showing light grazing metal structures during a slow cinematic reveal.
Preview clip for a neon rooftop rhythm performance, focused on neon stage blocking, confident movement, and beat-synced camera grammar.
Supports text-to-video, image-to-video, and video editing in one model
Image-to-video can use one image or a first-and-last-frame pair
Video editing can combine one source video with one optional image reference
A newer Wan video path beside Wan 2.6
Best-fit tasks
Use it when the task looks like this
Short-form product promos and social cutdownsFirst-and-last-frame style motion tests from imagesQuick video edits from an existing source clip5 to 15 second Wan experiments plus short source-video edits
Quiet facts
Inputs, output, and credits to confirm
Provider
Alibaba
Category
Video
Capabilities
Text to Video · Image to Video · Video to Video
Credit model
From 80 credits per generation
Input path
Prompt, up to 2 images, or 1 video + 1 image
Prompt setup
Up to 5,000 chars
FAQ
Wan 2.7 Video FAQ
What kind of video work is Wan 2.7 Video actually the best fit for?
Wan 2.7 Video is the better fit when you want a newer Wan option that stays flexible and still covers more than pure text-to-video. It is strong for short product promos, social cutdowns, first-and-last-frame image motion tests, and lightweight source-video touchups where pricing must reflect both resolution and duration.
What is Wan 2.7 Video's real scope on Rivya right now?
On Rivya, Wan 2.7 Video currently supports text-to-video, image-to-video, and a lightweight source-video edit path. It can take up to two assets in total: one image or a first-and-last-frame pair for image motion, or one source video plus one optional image for video editing. Text and image runs can go to `15s`, while the video-edit path currently tops out at `10s`.
When do Wan 2.7 Video's two-asset setups actually become useful?
The two-asset setup starts to matter when one image is not enough to describe the motion you want. A first-and-last-frame pair is useful when you need the clip to land between two specific visual states, and the video-edit path's optional reference image becomes useful when the source video should keep its motion but still borrow extra visual direction.
When is Wan 2.7 Video worth its current credit tier?
Wan 2.7 Video is currently easy to price: `720p` starts at 80 credits for 5s, while `1080p` reaches 360 credits for 15s. That simplicity is the value when you want something broader than a basic starter option, but still do not want the heavier cost curve of models like Wan 2.6. It is especially appealing when the job needs clear budgeting across multiple short clip tests.
When should I choose Wan 2.7 Video over Wan 2.5 or Wan 2.6?
Choose Wan 2.7 Video for text, paired-frame image motion, and lighter source-video edits with straightforward duration-based pricing. Choose Wan 2.5 when seed and negative-prompt control matter more. Step up to Wan 2.6 when source-video work is central or the project needs its broader input and duration range.
What can I test first on this page?
Start here when you want a current Wan option that can work from text, one or two images, or one source video. Use the initial run to see whether a short promo, paired-frame motion test, or lightweight edit fits Wan 2.7's simpler pricing range.
What can I set up on this page?
This page supports text-to-video, image-to-video, and a lightweight video-edit path. You can start from text, from one image, from a first-and-last-frame pair, or from one source video plus one optional image. It currently exposes `720p` and `1080p`, with `5s`, `10s`, and `15s` for text and image runs, while video editing tops out at `10s`.
Which checks are worth making before I hit run?
Choose the option first: text, one image, paired frames, or one source video. After that, pick `720p` or `1080p`, decide whether `5s`, `10s`, or `15s` is enough for the test, and remember that the video-edit path caps at `10s`. If you are editing from video, it is also worth deciding whether to keep audio on auto or ask the model to preserve the original track.
Do I need to sign in before I run here, and how do credits work?
The page is public, but the actual video run is still gated behind sign in. Wan 2.7 keeps pricing simple: `720p` starts at 80 credits for 5s, while `1080p` reaches 360 credits for 15s. You can set up the right option, asset mix, and duration first, then sign in when you are ready to generate.
When should I stay on this page, and when should I move into the full Studio?
Stay here while you are validating the first Wan 2.7 run: which option to use, whether one or two assets are needed, and whether `720p` already answers the question. Open the full Studio once the work needs saved versions, repeated clip iterations, multiple coordinated assets, or a longer managed project around the same footage set.
Compare alternatives
Other models to consider next
Video
Seedance 2.0
ByteDance's full Seedance 2.0 video model with explicit support for prompt-only generation, frame-driven animation, and multimodal reference generation. Rivya keeps the documented role split explicit so frame inputs and multimodal references stay mutually exclusive instead of collapsing into one ambiguous upload bucket.
Why consider it
Consider it when your next task needs Prompt, frames, or image/video/audio references.
InputPrompt, frames, or image/video/audio references
CreditsFrom 64 credits per run
Best forHigher-quality short videos from prompts, frames, or reference bundles
ByteDance's faster Seedance 2.0 video model with full scene routing for prompt-only generation, frame-driven image animation, and multimodal reference video generation. Rivya keeps the documented scene split explicit so first/last-frame inputs do not collide with reference image, video, and audio roles.
Why consider it
Consider it when your next task needs Prompt, frames, or image/video/audio references.
InputPrompt, frames, or image/video/audio references
CreditsFrom 52 credits per run
Best forFast ad previs from prompts or storyboard frames
Video
Seedance 1.5 Pro
A Seedance video model for text-to-video and image-to-video with native audio-visual sync. It supports 480p–1080p, 4–12s clips, 6 aspect ratios, dynamic or fixed lens control, optional audio generation, and lip-sync.
Why consider it
Consider it when your next task needs Prompt + optional images.
InputPrompt + optional images
CreditsFrom 28 credits per generation
Best forShort clips with synced dialogue and motion
Neon rooftop performance video preview with one adult performer, skyline lighting, mist, and rhythmic camera cuts.
Preview clip for a low-key silhouette dance video brief, focused on fixed-frame rhythm, side-backlit silhouette, and controlled modern dance motion.
Low-key indoor dance video preview with one adult dancer, side-backlight, fixed camera, and clean silhouette movement.
Preview clip for a neon paint canvas reveal, focused on paint motion, canvas transformation, and a safe playful pet beat.
Creative studio video preview with neon paint splashing on a canvas, forming a mountain landscape, and a calm cat reacting.
A fictional open-wheel car stops, the crew swaps tires in clear rhythm, and the shot ends as the car launches from pit lane.
Formula-style pit stop documentary video preview with tire-change close-ups and coordinated crew motion.
Preview for a dawn steel industrial motion poem, focused on steel surfaces, controlled haze, reflection continuity, camera glide, and the final wide frame.
Dawn steel industrial video preview showing light grazing metal structures during a slow cinematic reveal.
Preview clip for a neon rooftop rhythm performance, focused on neon stage blocking, confident movement, and beat-synced camera grammar.
Neon rooftop performance video preview with one adult performer, skyline lighting, mist, and rhythmic camera cuts.
Preview clip for a low-key silhouette dance video brief, focused on fixed-frame rhythm, side-backlit silhouette, and controlled modern dance motion.
Low-key indoor dance video preview with one adult dancer, side-backlight, fixed camera, and clean silhouette movement.
Preview clip for a neon paint canvas reveal, focused on paint motion, canvas transformation, and a safe playful pet beat.
Creative studio video preview with neon paint splashing on a canvas, forming a mountain landscape, and a calm cat reacting.
Teams that want one newer Wan slot for generation and light edits
Developer access
Partly available via API
Wan 2.7 Video has callable Public API modes, but reference-media modes still need Files API upload support. Check the model reference before submitting.