Describe a shot, animate a still image, or use media references with Standard Seedance 2.0. Choose the input mode that fits your material, and say what the scene and motion should look like.
The final cost is rounded up to whole credits.
Example output
Seedance 2.0
Text to Video · Image to Video
Example output
Seedance 2.0
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
Seedance 2.0 FAQ
For text-to-video, describe the clip without uploading media. In frame mode, upload a first frame and optionally a last frame. For reference mode, add images, video, or audio and explain how each should guide the clip. Choose one mode per request; frame images and reference media cannot be combined.
Reference mode accepts up to 9 images, 3 video clips, and 3 audio clips. Images may be JPEG, PNG, WebP, BMP, TIFF, or GIF, up to 30 MB each. Use MP4 or MOV video up to 50 MB each, or MP3 or WAV audio up to 15 MB each. Each video or audio clip must be between 2 and 15 seconds. Video clips together can total no more than 15 seconds, and audio clips have a separate 15-second total. Include at least one reference and explain what it should guide. Video references require 1080p or 4K output.
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
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.
Suggested uses
Tasks to consider
Model details
Provider
ByteDance
Category
Video
Capabilities
Text to Video · Image to Video · Reference to Video
Credit charges
Credit rate: 41–208 per second of total video duration (input + output)
Inputs
Prompt, first frame with optional last frame, or image/video/audio references
Prompt requirements
Up to 20,000 characters
Developer access
Seedance 2.0 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.
Rivya reserves credits before generation. Without a video reference, multiply the output duration by the rate for your resolution: 41 credits per second at 720p, 102 at 1080p, or 208 at 4K. With a video reference, the rates are 62 credits per second at 1080p or 128 at 4K, applied to the combined reference-video and output duration. Reservations are rounded up to whole credits. Final charges depend on reported usage when settlement completes; a ready video does not mean its credits have settled.
Frame and reference inputs need metadata from Rivya's upload flow. For Public API requests, keep the original Files POST response with its signed tokens and file details. A media URL or later Files GET response alone is not enough for these inputs. If the required metadata is missing or rejected, upload the original file again.
Add a prompt of up to 20,000 characters describing the scene and motion. Choose 720p, 1080p, or 4K output and a whole-number duration from 4 to 15 seconds. At 720p, use images or audio as references, not video. Turn Web search off for frame or reference mode; it is only available for text-to-video. Check the credit reservation before submitting.
This page keeps the generator on Standard Seedance 2.0. Studio lets you select other available video models, and generation history lets you check submitted tasks and saved results. You can browse this page and write a prompt while signed out. Sign in to upload media or generate, with enough credits for the displayed reservation.
Why consider it
Credit charges: Credit rate: 6.8–24.8 per second of total video duration (input + output)
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
