Seedance 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.
ByteDance
WaveSpeedFast text and image to video generation
Seedance 2.0 Fast Turbo is a video generation model developed by ByteDance and made available through the WaveSpeed provider on MindStudio. It supports both text-to-video and image-to-video generation modes, and accepts a range of reference inputs including images, videos, and audio. The model is tagged as a flagship offering and was released in April 2026, with pricing ranging from $0.60 to $1.58 per generation depending on configuration.
The model is designed for workflows that require flexible video output, offering selectable aspect ratios, resolutions, and durations through its input interface. Users can supply a starting image, an ending image, and multiple reference images or videos to guide generation. This makes it well-suited for creative and production use cases where visual consistency across frames or adherence to a reference style is important.
What Seedance 2.0 Fast Turbo supports
Text to Video
Generates video clips from a text prompt, with selectable aspect ratio, resolution, and duration options available at inference time.
Image to Video
Animates a provided image into a video clip, using a starting image and optionally a last image to define the visual bookends of the output.
Reference Image Guidance
Accepts an array of reference images to influence the visual style or content of the generated video, supporting multi-image input.
Reference Video Input
Accepts reference video URLs as additional conditioning inputs, allowing motion or scene context from existing footage to inform generation.
Audio Reference Input
Accepts reference audio URLs as inputs, enabling audio context to be supplied alongside visual prompts during video generation.
Configurable Output Format
Supports selectable aspect ratio, resolution, and duration settings, giving users direct control over the dimensions and length of generated video.
Turbo Generation Speed
The Fast Turbo variant is optimized for faster inference compared to standard generation pipelines, reducing time-to-output for video tasks.
Ready to build with Seedance 2.0 Fast Turbo?
Get Started FreeCommon questions about Seedance 2.0 Fast Turbo
What is the pricing for Seedance 2.0 Fast Turbo?
Pricing ranges from $0.60 to $1.58 per generation. The exact cost depends on the selected configuration options such as resolution and duration.
What input types does Seedance 2.0 Fast Turbo support?
The model accepts text prompts, a starting image, an ending image, arrays of reference images, reference videos, and reference audio URLs. Output format is configured via aspect ratio, resolution, and duration selectors.
What is the context window for this model?
Seedance 2.0 Fast Turbo has a context window of 50,000 tokens and a maximum response size of 10,000 tokens.
Who developed Seedance 2.0 Fast Turbo?
The model was developed by ByteDance and is provided on MindStudio through the WaveSpeed provider.
When was Seedance 2.0 Fast Turbo released?
Seedance 2.0 Fast Turbo was released in April 2026 and became available on MindStudio on April 14, 2026.
Parameters & options
Start image to guide the video generation.
Last frame image for video continuation.
Reference image URLs to guide style, characters, or 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.
Explore similar models
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.
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.
WanWan 2.7
Wan 2.7 is a video generation model supporting text-to-video and image-to-video creation with audio and reference image inputs.
GoogleVeo 3.1
Veo 3.1 is a Google video generation model that creates videos from text prompts or images, with optional audio output.
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.
Start building with Seedance 2.0 Fast Turbo
No API keys required. Create AI-powered workflows with Seedance 2.0 Fast Turbo in minutes — free.