◆ AI VIDEO NEWS · BYTEDANCE
ByteDance Seedance 2.0: multimodal video from text, image, audio and video
Seedance 2.0 took the top of the text-to-video leaderboard on launch, with a multimodal input system and the best quality-per-dollar in its tier.
ByteDance's Seedance 2.0, part of the Doubao 2.0 release, made an immediate impact by topping the Artificial Analysis text-to-video leaderboard on launch. Its defining feature is multimodal input: it accepts text, image, audio and video as prompts, a preview of where the whole category is heading.
In practice Seedance is the volume workhorse and the safest default: top-tier benchmark quality, remarkably smooth motion, and fast generation, all at a price that makes high-volume B-roll and YouTube footage affordable. A 480p draft tier and a 720p publish tier create a natural draft-then-final pipeline inside one model.
It's the answer to 'what should my default model be' for anyone whose content isn't dialogue-driven — the best pure quality-per-dollar ratio on the market.
What it costs: Priced per second by resolution — roughly $0.065 (480p) to $0.14 (720p); very strong value. Price your own project in the cost-per-usable-second calculator, or see the full breakdown on the pricing page.
Where it fits
Every model on this list wins at something different, and the smart workflow mixes them: draft on a cheap tier, render heroes on a premium one, and match the model to the shot. See how ByteDance stacks up against the rest in our full model comparison, or browse all coverage on the AI video news hub.