Seedance 2.5
Seedance 2.5 is a video generation model from ByteDance that supports text-to-video, image-to-video, video editing, and audio generation.
ByteDance
WaveSpeedText and image to video with audio generation
Seedance 2.5 is a video generation model developed by ByteDance and released in July 2026. It supports multiple generation modes including text-to-video, image-to-video, video editing, and video extension, and is served through the Wavespeed provider on MindStudio. The model accepts a range of inputs — text prompts, start and end images, reference images, reference videos, and reference audio — giving users fine-grained control over the output.
Seedance 2.5 is designed for workflows that require flexible video creation from different starting points, whether that means generating a clip from a written description, animating a still image, or extending an existing video. It includes a built-in audio generation toggle, allowing users to produce video with synthesized audio in a single pass. Pricing is usage-based at $0.11 to $1.10 per second of generated video, and the model supports configurable aspect ratios, resolutions, and durations.
What Seedance 2.5 supports
Text-to-Video
Generates video clips from a text prompt, allowing users to describe a scene and receive a rendered video output.
Image-to-Video
Animates a still image into a video clip using a provided start image, end image, or both as reference frames.
Video Editing
Accepts an input video and applies edits or transformations based on provided prompts or reference inputs.
Video Extension
Extends an existing video clip by generating additional frames that continue from the original footage.
Audio Generation
Synthesizes audio to accompany generated video in a single pass, toggled via a dedicated input control.
Reference-Guided Generation
Accepts arrays of reference images, videos, and audio clips to guide the style or content of the generated output.
Configurable Output Format
Supports selectable aspect ratios, resolutions, and a numeric duration input so users can tailor video dimensions and length.
Ready to build with Seedance 2.5?
Get Started FreeCommon questions about Seedance 2.5
What generation modes does Seedance 2.5 support?
Seedance 2.5 supports text-to-video, image-to-video, video editing, and video extension modes, selectable via the Mode input.
How is Seedance 2.5 priced?
Pricing is usage-based at $0.11 to $1.10 per second of generated video, depending on the selected resolution and settings.
What is the context window for Seedance 2.5?
Seedance 2.5 has a context window of 50,000 tokens.
Can Seedance 2.5 generate audio alongside video?
Yes. The model includes a Generate Audio toggle that enables synthesized audio to be produced in the same generation pass as the video.
What input types does Seedance 2.5 accept?
The model accepts text prompts, start and end image URLs, an input video URL, arrays of reference images, reference videos, and reference audio files, as well as settings for aspect ratio, resolution, and duration.
Who developed Seedance 2.5 and when was it released?
Seedance 2.5 was developed by ByteDance and released in July 2026. It is available on MindStudio through the Wavespeed provider.
Parameters & options
Start image URL to guide the video generation.
Optional last frame image URL for video continuation.
URL of the input video. For extend: continues from last 30s. For edit: trimmed to 30s if longer, padded to 4s if shorter.
Reference image URLs to guide visual style, characters, or scene composition.
Reference video URLs (total length must not exceed 30 seconds).
Reference audio URLs (total length must not exceed 30 seconds).
Duration of the generated video in seconds.
Whether to generate native audio synchronized with the output video.
Explore similar models
ByteDanceSeedance 2.5 Turbo
Seedance 2.5 Turbo is a video generation model from ByteDance that supports text-to-video, image-to-video, and video editing modes.
ByteDanceSeedance 2.0 Mini
Seedance 2.0 Mini is a video generation model from ByteDance that supports text-to-video and image-to-video creation.
ByteDanceSeedance 2.0 Fast Turbo
Seedance 2.0 Fast Turbo is a video generation model from ByteDance that supports text-to-video and image-to-video workflows.
Black Forest LabsFLUX 3 Video
FLUX 3 Video is a video generation model from Black Forest Labs that supports audio, keyframes, and video continuation.
WanWan 3.0
Wan 3.0 is a video generation model that converts text prompts and images into video clips with optional audio output.
GoogleGemini Omni Flash
Gemini Omni Flash is a video generation model from Google that supports image and video inputs with multimodal editing capabilities.
Start building with Seedance 2.5
No API keys required. Create AI-powered workflows with Seedance 2.5 in minutes — free.