Models › Seedance 2.0

Seedance 2.0, reference-to-video

bytedance/seedance-2.0/reference-to-video

Works where 2.5 refused every attempt. Refuses photoreal human references outright as possible likenesses, including your own face. Accepts an audio reference and synthesises a sound-alike rather than using it.

Everything it rendered

8 inputs, 8 takes. Click any one for the full request and its measurements.

Character serial, block 1 $1.80 · 3:56 lines 4/4 · synth voice · motion 3.68

Character serial, block 2 $1.80 · 3:38 lines 3/3 · synth voice · motion 1.54

refused

One face, one line no charge · — The images or videos provided may contain likenesses of real people or other private information that cannot be processed."

refused

Two people, two lines no charge · — The images or videos provided may contain likenesses of real people or other private information that cannot be processed."

Legible text on a sign $0.90 · 3:06 motion 2.58

Product on a turntable $0.90 · 3:56 motion 0.82

Fast camera, fast subject $0.90 · 2:55 motion 15.24 · clips

Stylised animation $0.90 · 2:22 motion 1.00

Identity across calls

How every model compared →