ByteDance's Volcano Engine has officially launched the Seedance 2.5 flash video generation model. The new model is designed to offer a more cost-effective solution for batch content production by doubling the generation speed compared to the standard version.
For text-to-video and image-to-video generation at 720P resolution, the service is priced at approximately ¥0.99 per second. This represents a price reduction of about 34% compared to the standard Seedance 2.5 model.
The model supports video generation up to 30 seconds in length. Users can input up to 10 images, 5 video segments, and 5 audio segments per request, with output options available in 480P and 720P resolutions.
Seedance 2.5 flash is being rolled out to platforms including Jimeng, LibTV, Updream, Creao AI, and TapNow. The API will be available on the Volcano Ark platform starting this Sunday, November 15.
The company positions the new model as superior to the previous flagship, Seedance 2.0, while maintaining performance levels close to the current flagship, Seedance 2.5. It features improved instruction following, physical motion, and audio synchronization.
