Turn a prompt, guide frames, or a reference bundle into a Seedance 2.5 video, with resolution, duration, format, and generated-audio controls.
The final cost is rounded up to whole credits.

Example output
Seedance 2.5
Text to Video · Image to Video

Example output
Seedance 2.5
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
ByteDance
Category
Video
Capabilities
Text to Video · Image to Video · Reference to Video · Video to Video
Credit charges
Credit rate: 17–158 per second of total video duration (input + output)
Inputs
Up to 50 reference files
Prompt requirements
Optional prompt
Developer access
Seedance 2.5 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.
Seedance 2.5 FAQ
Choose Seedance 2.5 for 1080p, durations up to 30 seconds, automatic duration, MP4 or MOV format requests, or more than nine images, three videos, or three audio files. Mini has lower rates at 480p and 720p and supports durations up to 15 seconds. The final-frame control requests a still from the provider; this page does not offer a separate still-frame handoff.
Text accepts no uploads. Frames accepts exactly one starting image or two images for a start-and-end pair and rejects video or audio. Reference requires at least one uploaded image, video, or audio and is the only scene for a mixed reference bundle.
The reference scene accepts up to 30 images, 10 MP4 or MOV videos, and 10 MP3 or WAV audio files, with no more than 50 files in total. Images are limited to 30 MB each. Each video is limited to 95 MB and 2 to 30 seconds, with 30 video seconds in total. Each audio file is limited to 15 MB and 2 to 30 seconds, with 30 audio seconds in total.
Images and reference videos must each have width and height from 300 to 6,000 pixels and an aspect ratio from 0.4 to 2.5. Reference videos must also contain 409,600 to 927,408 pixels per frame and run at 24 to 60 frames per second. The prompt field has a 20,480-character limit.
Rivya reserves the requested output seconds at 28 credits per second for 480p, 63 for 720p, or 158 for 1080p. Automatic duration reserves 30 output seconds. Image or audio references without a video use these same no-video rates.
A request with a reference video uses 17 credits per second at 480p, 38 at 720p, or 95 at 1080p. Rivya multiplies that rate by verified input-video seconds plus reserved output seconds, then rounds the combined total up once.
Automatic duration is the -1 choice. Rivya reserves 30 output seconds before submission and adds verified input-video seconds when a video is included. Valid actual usage at or below the reservation settles the cost, with unused credits refunded. Missing, invalid, or higher-than-reserved usage keeps the reservation in reconciliation without an automatic extra debit.
Choose text, frames, or reference input; set 480p, 720p, or 1080p; select a whole-number duration from 4 to 30 seconds or automatic duration; and request MP4 or MOV format. You can also set generated audio, the final-frame request, web search, and the content filter.
No. The frames scene accepts only one or two images. Use the reference scene for image, video, or audio bundles; the two input styles are mutually exclusive.
Images may be JPEG/PNG/WebP. Videos must be MP4 or MOV. Audio must be MP3 or WAV. Rivya checks file type, size, and count; videos and audio also need verified duration, while images and videos have geometry checks. Uploading a file does not by itself make it valid for a generation.
Yes. At 1080p, Rivya reserves 158 credits per output second without video input. A request containing video uses 95 credits per second across verified input-video seconds plus reserved output seconds.
Choose automatic duration when you want the model to determine the output length. Rivya reserves 30 output seconds in advance. If you know the length you need, a fixed whole-number choice from 4 to 30 seconds makes the output reservation easier to estimate.
Open Studio to use Seedance 2.5 in the video workspace and browse the other available video models. Adjust the prompt, controls, or references for a new generation, and use generation history to find earlier tasks.
Compare alternatives
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
Seedance 2.0 Mini creates 480p or 720p videos lasting 4–15 seconds. Start with text, guide the clip with a first frame or a first-and-last-frame pair, or combine image, video and audio references. Choose one input mode for each generation, with optional generated audio.
Why consider it
Input option: Up to 15 reference files