Wan 2.6 is one of Rivya's heaviest Wan video projects because it covers text-to-video, image-to-video, and source-video editing from the same model family, with room for longer 15-second runs when a lighter option is not enough.
Triple mode: text-to-video + image-to-video + video-to-videoOne heavy Wan option that can start from a source video instead of only text or still images
One image or one source video keeps the edit path explicit
Input
Prompt, 1 image, or 1 video
Output
AI Video Generator
Credits
From 70 credits per generation
Best for
Video-to-video edits from an existing source clip
Example output
Preview for Wooded Hills Oil Painting Drive, 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 Wooded Hills Oil Painting Drive, focused on scene setup, camera path, motion continuity, editable details, and the final hero frame.
Best for
Video-to-video edits from an existing source clipLonger 15-second concept or promo runsAnimating stills with a flexible Wan projectIterative motion tests across text, image, and video inputs
Supports
Text to VideoImage to VideoVideo to Video
Online trial
Use Wan 2.6
Use Wan 2.6 when the job needs one Alibaba model that can cover text-to-video, image-to-video, and video-to-video in the same project. Open it for source-video edits or longer 15-second runs, and stay here when flexibility matters more than a narrower single-mode model.
Results
Wan 2.6
AlibabaText to Video
Wan 2.6 is one of Rivya's heaviest Wan video projects because it covers text-to-video, image-to-video, and source-video editing from the same model family, with room for longer 15-second runs when a lighter option is not enough.
Wan 2.6
No result yet. Submit a prompt to start a run.
Text to VideoImage to VideoVideo to Video
Prompt starters
Start Wan 2.6 with a proven prompt
Use a template already mapped to Wan 2.6 when you want a stronger first run than a blank prompt.
One heavy Wan option that can start from a source video instead of only text or still images
One image or one source video keeps the edit path explicit
Best-fit tasks
Best-fit tasks
Video-to-video edits from an existing source clipLonger 15-second concept or promo runsAnimating stills with a flexible Wan projectIterative motion tests across text, image, and video inputs
Model proof
Preview clip for an orbital megastructure sunset shot, focused on horizon setup, parallax reveal, readable scale, editable color temperature, and the final hero frame.
Orbital megastructure sunset video preview showing a calm horizon, curved structure reveal, soft pink-blue light, camera drift, and final wide hero frame.
Preview focused on elevated-road geometry, near-pass motion, traffic depth, vehicle scale, and a readable wide ending.
Sci-fi future city video preview showing an original speeder moving through layered elevated traffic.
Preview clip for a midnight fog forest wanderer brief, focused on fog depth, character motion, subtle light, and final reveal composition.
One heavy Wan option that can start from a source video instead of only text or still images
One image or one source video keeps the edit path explicit
720p and 1080p resolution, 5s/10s/15s duration
Longest clip duration at 15 seconds
Best-fit tasks
Use it when the task looks like this
Video-to-video edits from an existing source clipLonger 15-second concept or promo runsAnimating stills with a flexible Wan projectIterative motion tests across text, image, and video inputs
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 70 credits per generation
Input path
Prompt, 1 image, or 1 video
Prompt setup
Up to 5,000 chars
FAQ
Wan 2.6 FAQ
What kind of video work is Wan 2.6 actually the best fit for?
Wan 2.6 is the better fit when one project may need to start from text, a still image, or an existing source clip, and you want to keep those paths inside one heavier Wan project. It is especially relevant for source-video rework, 15-second concept or promo runs, and teams that would rather pay for a more flexible option than keep switching models as the job evolves.
What is Wan 2.6's real scope on Rivya right now?
On Rivya, Wan 2.6 currently supports text-to-video, image-to-video, and source-video editing. It takes either one image or one source video at a time, not a larger storyboard-style setup, and it currently exposes `720p` and `1080p` across `5s`, `10s`, and `15s` runs.
When is Wan 2.6's source-video path the real reason to choose it?
The source-video path is the main reason to step up to Wan 2.6 when the existing clip already contains motion, timing, or blocking worth preserving. If the strongest asset you have is the clip itself, not just a written shot description, Wan 2.6 becomes much easier to justify because you are steering from footage instead of rebuilding the scene from scratch.
When is Wan 2.6 worth its current credit tier?
Wan 2.6 is currently priced as `720p 5s = 70`, `720p 10s = 140`, `720p 15s = 210`, `1080p 5s = 105`, `1080p 10s = 210`, and `1080p 15s = 315` credits. That tier makes sense when the flexibility itself is saving work, especially if the same model is covering first generation, still-led motion, and source-video rework in one option.
When should I choose Wan 2.6 over Wan 2.7 or a narrower option?
Choose Wan 2.6 when the job needs text, still-image, and source-video starts plus clips up to `15s` in one flexible Wan model. Wan 2.7 is a better fit for cheaper short promos, paired-frame motion, or lighter source-video edits. If you do not need that flexibility yet, begin with a narrower option.
What can I test first on this page?
Start here when the key question is which asset should drive the run: text, one still image, or one source video. A short initial test can show whether Wan 2.6's broader input support is worth its higher credit tier before you commit to a longer project.
What can I set up on this page?
This page supports text-to-video, image-to-video, and source-video editing. You can upload either one image or one source video, depending on the option, and the core run settings are `720p` or `1080p` across `5s`, `10s`, and `15s`.
Which checks are worth making before I hit run?
Decide the source path first. If you are bringing a video, make sure the existing motion is worth preserving; if you are bringing a still, make sure it is strong enough to carry the scene; if you are starting from text, decide whether the shot really needs Wan 2.6's heavier option. After that, the practical checks are duration and resolution, and `720p 5s` is often enough for the very first validation.
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. Pricing currently follows the visible ladder: `720p 5s = 70`, `720p 10s = 140`, `720p 15s = 210`, `1080p 5s = 105`, `1080p 10s = 210`, and `1080p 15s = 315` credits. You can choose the right source path, duration, and resolution first, then sign in when you are ready to run it.
When should I stay on this page, and when should I move into the full Studio?
Stay here while you are validating the first source path and the first cost tier on Wan 2.6. 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 or scene 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
Midnight fog forest video preview with a robed wanderer moving through moonlit haze.
Preview of a hand-drawn storybook pop-up shot focused on page-turn continuity, handmade animation, outdoor light, and final book composition.
Hand-drawn storybook pop-up video preview with animated paper animals rising from an open book.
Preview clip focused on path motion, rocket scale, boarding continuity, and vertical liftoff.
Forest action video preview with a runner entering a clearing and launching in a compact rocket.
Preview clip for an orbital megastructure sunset shot, focused on horizon setup, parallax reveal, readable scale, editable color temperature, and the final hero frame.
Orbital megastructure sunset video preview showing a calm horizon, curved structure reveal, soft pink-blue light, camera drift, and final wide hero frame.
Preview focused on elevated-road geometry, near-pass motion, traffic depth, vehicle scale, and a readable wide ending.
Sci-fi future city video preview showing an original speeder moving through layered elevated traffic.
Preview clip for a midnight fog forest wanderer brief, focused on fog depth, character motion, subtle light, and final reveal composition.
Midnight fog forest video preview with a robed wanderer moving through moonlit haze.
Preview of a hand-drawn storybook pop-up shot focused on page-turn continuity, handmade animation, outdoor light, and final book composition.
Hand-drawn storybook pop-up video preview with animated paper animals rising from an open book.
Preview clip focused on path motion, rocket scale, boarding continuity, and vertical liftoff.
Forest action video preview with a runner entering a clearing and launching in a compact rocket.
Teams that need one model for generation and source-video rework
Developer access
Partly available via API
Wan 2.6 has callable Public API modes, but reference-media modes still need Files API upload support. Check the model reference before submitting.