About this model
Seedance 1.5 Pro is ByteDance's Seed-team flagship video generator, offered here as the text-to-video endpoint alongside its companion Seedance 1.5 Pro image-to-video variant. ByteDance describes it as a joint audio-video model that accurately follows complex instructions, generating diverse voices and spatial sound effects that coordinate with the visuals, plus complex camera movement ranging from close-ups with subtle facial expression to full shots with cinematic composition and atmosphere.
The generational shift within the Seedance line is that output is no longer silent footage requiring a separate sound pass: ByteDance presents 1.5 Pro as generating picture and audio together, and emphasises broad language and dialect coverage with lip-sync and motion alignment, extending the family beyond purely visual output.
Within this catalog it sits at the base of a fast-moving lineage: Seedance 2.0 and its Seedance 2.0 Fast and Seedance 2.0 Mini tiers arrived later, followed by Seedance 2.5, with reference-to-video modes such as Seedance 2.0 R2V adding identity-anchoring inputs. For stills, ByteDance's parallel image family includes Seedream V5 Pro.
Choose 1.5 Pro for ByteDance's joint audio-video output; newer 2.x entries offer later releases and lower-cost tiers.
This About section is AI-generated from public sources (Claude Opus 5), with no human editing. It may contain inaccuracies — verify critical details against the sources listed above.
Data sources: Venice API · HuggingFace · Wikipedia — enrichment updated 6d ago