Use text to describe a scene, images to guide its first and last frames, or a source video to request an edit. You can add an image reference to a video edit.
The final cost is rounded up to whole credits.

Example output
Wan 2.7 Video
Text to Video · Image to Video

Example output
Wan 2.7 Video
Best for
Supports
Try this model
No results to display yet.
Model examples
Review examples to help decide whether the model fits your task.
Model strengths
Model strengths
Suggested uses
Tasks to consider
Model details
Provider
Alibaba
Category
Video
Capabilities
Text to Video · Image to Video · Video to Video
Credit charges
Credit rate: 16–24 per second of output
Inputs
Prompt, up to 2 images, or 1 video with an optional image
Prompt requirements
Up to 5,000 characters
Developer access
Wan 2.7 Video can be called through Public API v1. Modes that use reference media require uploads through the Files API. Check the model reference for supported inputs.
Wan 2.7 Video FAQ
Pick a scene and describe its subject, action, and camera movement. Start with text alone, add a first frame if you have one, or upload a source video when you want an edit. Review the output before using it in a finished piece.
Text-to-video, image-to-video from a first frame or a first-and-last-frame pair, and video editing are available. Reference-to-video (R2V), audio_url, driving_audio_url, and first_clip_url inputs are not supported. Rivya sends nsfw_checker=true for each request; you cannot turn it off.
For image-to-video, the first image sets the starting frame and the second sets the last frame. For video editing, you can add an image reference alongside the source video to guide the requested change. You cannot combine a frame pair with a source video.
The reservation uses 16 credits per second at 720p or 24 at 1080p, rounded up for the whole task. It uses the requested duration, or the verified source-video duration when duration is 0. Final charges use reported usage after settlement; a successful result can still be awaiting settlement.
Wan 2.7 Video offers first-and-last-frame input and video editing with an optional image reference. Wan 2.5 accepts a single first-frame image; Wan 2.6 accepts a single image or video references. Compare the input options and credit estimates for your task before choosing.
Choose 720p or 1080p output and a duration that fits your input mode. Text-to-video and video editing offer an aspect-ratio setting. For image-to-video, the first frame guides the aspect ratio.
Use JPEG, PNG, or WebP images up to 30 MB, or an MP4 or MOV source video up to 30 MB. Source videos must be 2–10 seconds long. You can use a first frame with an optional last frame, or a source video with an optional image reference. Audio uploads are not supported.
Add a prompt of up to 5,000 characters. A negative prompt is optional and can contain up to 500 characters. Check the duration guidance for your input mode, make sure your uploaded media meets the file requirements, and review the credit estimate. Content checks stay on.
You can read this page without signing in. Sign in to upload reference media or generate a video, and make sure your account has enough credits for the estimate. The estimate is reserved before the provider request; final charges depend on reported usage.
The generator here is fixed to Wan 2.7 Video. Open Studio when you want to work with other available video models. Submitted tasks appear in your generation history.
Compare alternatives
Create Seedance 2.5 videos from text, a start frame with an optional end frame, or image, video, and audio references. Choose 480p, 720p, or 1080p, a duration from 4 to 30 seconds or automatic duration, and an MP4 or MOV format request.
Why consider it
Input option: Up to 50 reference files
Generate video from text, a first frame, or media references.
Why consider it
Input option: Prompt, first frame with optional last frame, or image/video/audio references
ByteDance's Seedance 2.0 Fast video model for text prompts, a first frame with an optional last frame, or image, video and audio references. Choose 480p or 720p, set a 4–15-second duration, and request audio or a returned last frame.
Why consider it
Input option: Prompt, first frame with optional last frame, or image/video/audio references