AI video models

Animates a reference image with an optional text prompt. Smoother motion, natural skin textures and improved close-up quality.

Animates a reference image with an optional text prompt. 720P/1080P output, 3–15s. Zero data retention.

Reference-to-video. Takes 1–9 reference images (characters and scenes) plus a prompt and choreographs them into a single video, keeping each subject's identity consistent.

Generates videos from a reference image with optional text prompts. Supports 720P and 1080P output, durations 2–15s.

Next-generation video model with synchronized audio. Generates from text, images, video clips and audio. Native audio generation, video editing and extension.

Faster variant of Seedance 2.0. Trades some quality for speed while sharing the same multimodal architecture.

Compact, cost-efficient video generation model from the Seedance family. Ideal for high-volume workloads where speed and cost matter.

Audio-video generation model for 30-second videos with reference control and editing capabilities.

Generates video from a text prompt (t2v), animates one or more reference images (i2v) or continues an existing clip (v2v). Synchronized audio, up to FHD, 5–20s.