Pick Seedance 2.0, 1.5 Pro or Fast
Use Fast to see whether the motion reads. Use 1.5 Pro for the 1.x take you intend to keep. Use Seedance 2.0 when the shot needs more than a first frame.
AI Video
Seedance is a ByteDance Seed AI video generator for text to video, image to video, and first-and-last-frame clips. The versions here are Seedance 2.0, Seedance 1.5 Pro, Seedance 1.0 Pro and Seedance 1.0 Pro Fast. Describe a shot in words, or upload a first frame, product photo or character still, to generate a short video.
Use Fast to see whether the motion reads. Use 1.5 Pro for the 1.x take you intend to keep. Use Seedance 2.0 when the shot needs more than a first frame.
For text to video, name subject, camera and light. For image to video, upload the still and describe only what moves. Supply a last frame when the ending pose is fixed.
Those three are locked before you generate. Ask for one camera move per clip. For more events, generate more clips and cut them together.
A written prompt is enough: subject, camera move, light, and the one action in the clip. Use this when you do not yet have a still. Seedance 2.0 and Seedance 1.5 Pro both do text to video.
Upload a still as the first frame and describe only the motion. Add a last frame when the clip has to land on a specific pose. Product shots, character sheets and storyboard frames all work as inputs. This is the most reliable way to control how the shot looks.
Seedance 2.0 accepts more kinds of input than the 1.x line. Seedance 1.5 Pro is the 1.x take you keep. Seedance 1.0 Pro Fast is for checking framing and movement, then rerun the same prompt on a Pro name. A longer duration stretches the same action; it does not add plot.
Seedance is a ByteDance Seed AI video model. It turns text or pictures into a short clip. Typical jobs are text to video, image to video, first-frame to video, and first-and-last-frame.
Seedance 2.0 accepts more input types than the 1.x line. Seedance 1.5 Pro is the current 1.x Pro for the take you keep. Fast is for checking motion before a Pro run.
Yes. Upload a first frame (and a last frame when that mode is listed) and describe the motion only. A product photo or character still is enough to start.
Duration is chosen before you generate and cannot be changed afterwards. A longer setting stretches the same action. For more events, generate more clips.