
ByteDance's most advanced reference-to-video model, fast tier. Lower latency and cost with up to 9 images, 3 videos, and 3 audio clips as inputs.
ByteDance's most advanced reference-to-video model, fast tier. Lower latency and cost with up to 9 images, 3 videos, and 3 audio clips as inputs.
Seedance 2.0 Fast Reference to Video ranks #1 of 79 in the Image-to-Video Arena with 1343 Elo, based on blind human-preference votes, and holds 1301 Elo on Design Arena across 9,162 battles.
Seedance 2.0 Fast Reference to Video runs as a hosted API endpoint on fal.ai (bytedance/seedance-2.0/fast/reference-to-video), offered under a commercial license. No infrastructure needed — call it per generation.