Seedance 2.0 Mini
Seedance 2.0 Mini is a video generation model from ByteDance that supports text-to-video and image-to-video creation.
ByteDance
WaveSpeedText and image to video generation from ByteDance
Seedance 2.0 Mini is a video generation model developed by ByteDance and made available through the Wavespeed provider. It supports both text-to-video and image-to-video generation modes, accepting inputs such as start images, end images, reference images, reference videos, and reference audio. The model also includes an optional audio generation toggle, allowing users to produce video with synthesized sound in a single workflow. It was released in June 2026 and operates with a context window of up to 50,000 tokens.
Seedance 2.0 Mini is positioned as a cost-accessible option within the Seedance model family, priced between $0.06 and $0.60 per second of generated video. It supports configurable aspect ratios, resolutions, and durations, giving developers control over output format. The model is suited for applications that require programmatic video creation from text prompts or image inputs, such as content automation, prototyping, and creative tooling. Its multi-modal input support — including arrays of reference images, videos, and audio — makes it adaptable to a range of production workflows.
What Seedance 2.0 Mini supports
Text to Video
Generates video clips from text prompts, with configurable duration, resolution, and aspect ratio settings.
Image to Video
Animates a provided start image (and optionally a last image) into a video clip, enabling frame-bounded generation.
Audio Generation
Optionally synthesizes audio alongside the video output via a toggleable generate_audio input, producing media with sound in one pass.
Reference-Guided Generation
Accepts arrays of reference images, videos, and audio clips as conditioning inputs to guide the style or content of generated video.
Low-Cost Pricing
Priced at $0.06–$0.60 per second of generated video, making it accessible for high-volume or budget-sensitive workflows.
Flexible Output Config
Supports selectable aspect ratios, resolutions, and a numeric duration input so developers can tailor video dimensions and length per request.
Ready to build with Seedance 2.0 Mini?
Get Started FreeCommon questions about Seedance 2.0 Mini
What generation modes does Seedance 2.0 Mini support?
Seedance 2.0 Mini supports both text-to-video and image-to-video modes. In image-to-video mode, you can supply a start image and optionally a last image to define the beginning and end frames of the generated clip.
How is Seedance 2.0 Mini priced?
The model is priced between $0.06 and $0.60 per second of generated video. The exact cost depends on the resolution and other output settings selected at generation time.
What is the context window for Seedance 2.0 Mini?
Seedance 2.0 Mini has a context window of 50,000 tokens, which governs the amount of input information the model can process per request.
Can Seedance 2.0 Mini generate audio along with video?
Yes. The model includes a generate_audio toggle input that, when enabled, synthesizes audio as part of the video generation output in a single request.
What reference inputs does the model accept?
In addition to a start image and last image, the model accepts arrays of reference images, reference videos, and reference audio clips. These can be used to condition the style or content of the generated video.
Parameters & options
Start image URL to guide the video generation.
Optional last frame image URL for video continuation.
URL of the input video to edit. Videos longer than 15 seconds are trimmed to 15 seconds.
Reference image URLs to guide visual style, characters, or scene composition.
Reference video URLs (total length must not exceed 15 seconds).
Reference audio URLs (total length must not exceed 15 seconds).
Duration of the generated video in seconds.
Whether to generate native audio synchronized with the output video. For Video Edit, if 'No', the input video's audio track is preserved.
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 Fast Turbo
Seedance 2.0 Fast Turbo is a video generation model from ByteDance that supports text-to-video and image-to-video workflows.
ByteDanceSeedance 2.0 Fast
Seedance 2.0 Fast is a video generation model from ByteDance that supports text-to-video and image-to-video creation.
MiniMaxMiniMax H3
MiniMax H3 is a video generation model from MiniMax that supports text-to-video, image-to-video, and reference-based video creation at up to 2K resolution.
WanWan 3.0
Wan 3.0 is a video generation model that converts text prompts and images into video clips with optional audio output.
KlingKling 3.0 Pro
Kling 3.0 Pro is a video generation model from Kling that supports both text-to-video and image-to-video creation.
Start building with Seedance 2.0 Mini
No API keys required. Create AI-powered workflows with Seedance 2.0 Mini in minutes — free.