The i2v-ref version model supports generating videos with reference images, and it can support up to 4 reference images.
The Seedance 1.0 lite model is a small parameter version of the 1.0 model series. While achieving excellent video generation quality, it significantly improves the generation speed, making it a cost-effective choice that balances performance and efficiency. The i2v version of the model supports video generation from the first frame image and video generation from the first and last frame images. The supported video generation durations are 5s and 10s. Three resolution options are available: 480P, 720P, and 1080P.
The t2v version model is the text-to-video version of the 1.0 Lite version. It has stable generation quality and high cost performance, and generates videos according to text instructions.
Seedance 1.0 Pro Fast is a comprehensive model with the lowest price and the highest performance, achieving an excellent balance between video generation quality, speed, and price. It can generate videos based on images. Inheriting the core advantages of Seedance 1.0 Pro, it also features improved generation speed and more competitive pricing, bringing creators an experience optimized in both efficiency and cost.
Seedance 1.0 Pro Fast is a comprehensive model with the lowest price and the highest performance, achieving an excellent balance among video generation quality, speed, and price. It can generate videos based on text. Inheriting the core advantages of Seedance 1.0 Pro, it also features improved generation speed and more competitive pricing, bringing creators an experience optimized in both efficiency and cost.
Seedance 1.0 Pro creates coherent multi-shot image-to-video clips with smooth, stable motion and faithful prompt adherence.
Seedance 1.0 Pro Text to Video can generate coherent multi-shot text-to-video, with a resolution of 1080p, smooth and stable movement, and can accurately fit the prompt words.
