Try a camera move around a product, a short scene described in text, or motion from a single still. Choose the duration and resolution, then set an optional seed or negative prompt. Prompt expansion is off by default.
The final cost is rounded up to whole credits.

Example output
Wan 2.5 Video
Text to Video · Image to Video

Example output
Wan 2.5 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
Credit charges
Credit rate: 60–200 per video
Inputs
Prompt + optional images
Prompt requirements
Up to 800 characters
Developer access
Wan 2.5 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 2.5 Video FAQ
A product reveal, a camera move through a scene, or a short teaser are useful briefs to try. Start with text or one still image and request 5 or 10 seconds. Describe one main action so you have a clear question to assess in the result.
Every request needs a written prompt of up to 800 characters after trimming leading and trailing spaces. Use no image for text-to-video, or one image for image-to-video; video and audio inputs are not supported. Both modes offer 720p or 1080p and 5 or 10 seconds. Aspect ratio is a text-to-video setting only: 16:9, 9:16, or 1:1.
Prompt expansion is off by default and can be turned on. A negative prompt is optional and allows up to 500 characters after trimming. You can also enter an integer seed from 0 to 2,147,483,647, but a seed does not guarantee identical results. Safety checking stays on and has no user switch.
The initial estimate, reserved when you submit, is 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, in either mode. When valid reported usage is within the reservation, it is rounded up to a whole credit for the final charge. If that charge is lower than the reservation, the difference is returned. Missing or invalid usage, or usage above the reservation, leaves billing under review. A finished video does not necessarily mean billing has settled.
Upload one JPEG, PNG, or WebP image after signing in. The upload limit is 10 MiB (10,485,760 bytes) per image. Add a written prompt to describe the motion; the image does not replace it. This model accepts one image, so there is no second end-frame image input.
Start with a short product shot or a scene with one clear camera move. Describe the scene in a prompt, adding one still image if you want to start from a picture. The default settings are 720p and 5 seconds, with prompt expansion off.
A prompt is required in both modes, with up to 800 characters after trimming. With no image, you can choose 16:9, 9:16, or 1:1. Adding one image switches to image-to-video, where the aspect ratio control is hidden. Both modes offer 5 or 10 seconds at 720p or 1080p; neither accepts video or audio.
Choose the duration and resolution, then decide whether to turn on prompt expansion. The negative prompt is optional, with a 500-character limit after trimming. If you use a seed, enter an integer from 0 to 2,147,483,647; identical results are not guaranteed. Safety checking is always on.
Sign in to upload an image or generate. The initial estimate is reserved on submission: 60 credits for 720p at 5 seconds, 120 for 720p at 10 seconds, 100 for 1080p at 5 seconds, or 200 for 1080p at 10 seconds, for either input mode. Valid reported usage within that reservation is rounded up to a whole credit to settle the final charge. If the final charge is lower, the difference is refunded. Missing or invalid usage, or usage above the reservation, keeps the charge under review, even if the video has finished.
Studio provides the generation form and links to your generation history. Use it to set up another attempt or revisit a previous run while working on the same shot.
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