Wan 2.6 supports text-to-video with no media, image-to-video with exactly one image, and video editing with one to three videos; images and videos cannot be mixed. The default is 1080p, 5 seconds, shot mode Off, and content filter On. Both controls are sent explicitly, and no audio track is generated.
The final task cost is rounded up to whole credits.
Example output
Example; generating model unverified · Preview for Wooded Hills Oil Painting Drive, focused on scene setup, camera path, motion continuity, editable details, and the final hero frame.
Text to Video · Image to Video
Example output
Example; generating model unverified · Preview for Wooded Hills Oil Painting Drive, focused on scene setup, camera path, motion continuity, editable details, and the final hero frame.
Best for
Supports
Online trial
No results to display yet.
Prompt starters
Model examples
Browse template previews for ideas. Each caption indicates whether generation with this model has been verified.
Example; generating model unverified · Preview for Wooded Hills Oil Painting Drive, focused on scene setup, camera path, motion continuity, editable details, and the final hero frame.
Example; generating model unverified · Preview clip for an orbital megastructure sunset shot, focused on horizon setup, parallax reveal, readable scale, editable color temperature, and the final hero frame.
Example; generating model unverified · Preview focused on elevated-road geometry, near-pass motion, traffic depth, vehicle scale, and a readable wide ending.
Example; generating model unverified · Preview clip for a midnight fog forest wanderer brief, focused on fog depth, character motion, subtle light, and final reveal composition.
Example; generating model unverified · Preview of a hand-drawn storybook pop-up shot focused on page-turn continuity, handmade animation, outdoor light, and final book composition.
Example; generating model unverified · Preview clip focused on path motion, rocket scale, boarding continuity, and vertical liftoff.
Decision fit
Decision fit
Best-fit tasks
Use it when the task looks like this
Model details
Provider
Alibaba
Category
Video
Capabilities
Text to Video · Image to Video · Video to Video
Credit model
Credit rate: 70–315 / video
Input path
Up to 3 reference files
Prompt setup
Up to 5,000 chars
Developer access
Wan 2.6 has callable Public API modes, but reference-media modes still need Files API upload support. Check the model reference before submitting.
Wan 2.6 FAQ
Wan 2.6 supports text-to-video with no media, image-to-video with exactly one image, and video editing with one to three videos; images and videos cannot be mixed. Text and image inputs support 5, 10, or 15 seconds; video input supports 5 or 10 seconds only.
Wan 2.6 supports text-to-video with no media, image-to-video with exactly one image, and video editing with one to three videos; images and videos cannot be mixed. Use exactly 1 JPG/PNG/WebP image (at least 256×256, up to 10 MB) or 1–3 MP4/MOV videos (up to 10 MB per file). Text and image inputs support 5, 10, or 15 seconds; video input supports 5 or 10 seconds only. The default is 1080p, 5 seconds, shot mode Off, and content filter On. Both controls are sent explicitly, and no audio track is generated.
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.
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. Text and image inputs support 5, 10, or 15 seconds; video input supports 5 or 10 seconds only.
Wan 2.6 supports text-to-video with no media, image-to-video with exactly one image, and video editing with one to three videos; images and videos cannot be mixed. Text and image inputs support 5, 10, or 15 seconds; video input supports 5 or 10 seconds only.
Wan 2.6 supports text-to-video with no media, image-to-video with exactly one image, and video editing with one to three videos; images and videos cannot be mixed. Use exactly 1 JPG/PNG/WebP image (at least 256×256, up to 10 MB) or 1–3 MP4/MOV videos (up to 10 MB per file).
Wan 2.6 supports text-to-video with no media, image-to-video with exactly one image, and video editing with one to three videos; images and videos cannot be mixed. Text and image inputs support 5, 10, or 15 seconds; video input supports 5 or 10 seconds only. The default is 1080p, 5 seconds, shot mode Off, and content filter On. Both controls are sent explicitly, and no audio track is generated.
The default is 1080p, 5 seconds, shot mode Off, and content filter On. Both controls are sent explicitly, and no audio track is generated. Use exactly 1 JPG/PNG/WebP image (at least 256×256, up to 10 MB) or 1–3 MP4/MOV videos (up to 10 MB per file).
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. Text and image inputs support 5, 10, or 15 seconds; video input supports 5 or 10 seconds only.
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
Seedance 2.5 is Rivya's larger Seedance workflow for prompt-only video, first- and last-frame guidance, multimodal references, and video-guided transformation. It adds a 1080p tier, output up to 30 seconds, automatic duration, MP4 or MOV output, and substantially larger image, video, and audio reference capacity than Mini.
Why consider it
Consider it when your next task needs Up to 50 reference files.
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.
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.
