ByteDanceByteDance·🎬 Video Generation·↑ Newer: Seedance 2.5

Seedance 2.0

anonymized
Try on Venice.ai ↗
Quick reference
Seedance 2.0 — TLDR
  • 🏢 ByteDance Seed's flagship video generation family, released March 2026.
  • 🆕 Unified multimodal architecture accepting text, image, audio and video inputs.
  • 💬 Native joint audio-video generation, so sound is produced with the picture.
  • 🎯 Director-level control over performance, lighting, shadow and camera movement.
  • 🔧 Emphasis on motion stability and scene consistency across a shot.
  • ⚡ Family also includes Fast and Mini variants, plus image- and reference-conditioned endpoints.
  • 🌐 This entry is the text-to-video endpoint of the 2.0 family.
💰 Pricing
$0.350 – $14.58
per generation
📅 On Venice since
Mar 31, 2026
139 days ago
Provider

ByteDance is a Chinese internet technology company headquartered in Beijing's Haidian district, with an associated variable-interest entity incorporated in the Cayman Islands. Best known as a consumer internet operator at enormous scale, it has also become a…

Read full profile →
24 models on Venice
18 video · 3 image · 3 inpaint
Since Nov 5, 2025

About this model

Seedance 2.0 is the text-to-video member of ByteDance Seed's flagship video family. According to Seed's own model page, it adopts a unified multimodal audio-video joint generation architecture that accepts text, image, audio and video inputs, and emphasizes motion stability plus creator control over performance, lighting, shadow and camera movement. In practice, a prompt can specify camera moves and staging, and the model generates video with synchronized audio rather than a silent clip.

Against its predecessor Seedance 1.5 Pro, the documented change is architectural rather than incremental: Seed positions 2.0 as a joint audio-video model with multimodal conditioning across text, image, audio and video, where earlier Seedance releases were framed as video generators driven by text or a starting image. Seed's stated priorities for this generation are motion stability and director-style control of performance and lighting.

The 2.0 release ships as a tier system in this catalog. Seedance 2.0 Fast and the later Seedance 2.0 Mini are smaller-tier variants, while Seedance 2.0 image-to-video and Seedance 2.0 R2V expose the same generation through image and multi-reference conditioning.

For newer work, Seedance 2.5 succeeds this checkpoint in the same family, alongside its Seedance 2.5 image-to-video counterpart. Seedream V5 Pro is the image model in the same provider family.

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