- 🏢 ByteDance's flagship Seedance video family, image-to-video variant
- 🆕 Released March 2026, the first entry in the 2.0 generation
- 🎯 Takes a starting image plus a text prompt describing motion
- 📚 Catalog description cites realistic motion, scene consistency, cinematic quality
- 🔧 Sibling endpoints cover text-to-video and reference-to-video inputs
- ⚡ Fast and Mini tiers exist for quicker, lighter generation
- 🌐 Superseded within the family by Seedance 2.5 image-to-video
- 🧠 No public parameter count, license, or technical report in this catalog
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 significant…
Explore 18 more models by ByteDance →Seedance 2.0 is the image-to-video entry point of ByteDance's flagship Seedance video family, dated March 2026 in this catalog. Rather than generating from text alone, it starts from a still image you supply and a prompt that describes how the scene should move, making it the natural choice when you already have a fixed frame, character or composition you want to keep. The catalog description for the family highlights realistic motion, scene consistency and cinematic quality.
The 2.0 release arrived as a set of matched endpoints. Seedance 2.0 handles prompt-only generation, while Seedance 2.0 R2V works from reference material. Lighter tiers followed shortly after: Seedance 2.0 Fast in April 2026 and Seedance 2.0 Mini in June 2026, both offered for the same input modes.
Its immediate same-family predecessor is Seedance 1.5 Pro, released only days earlier in March 2026; ByteDance has since shipped a newer generation, Seedance 2.5, in August 2026, so 2.0 now sits as the older stable option in the line. No parameter count, license or official technical documentation is recorded for this checkpoint here, so capability comparisons between the generations are best made by testing them side by side.
Creators who need a source frame first can generate one with an image model such as Seedream V5 Pro or Seedream V5 Lite, then animate it here.
This About section is AI-generated from public sources via VeniceStats + Venice inference, with no human editing. It may contain inaccuracies.
Daily usage · Seedance 2.0 Basic · Organic sellers
| Seller | Health | Rep↓ | Sales | Video | Routing | $ / s | $ / video |
|---|---|---|---|---|---|---|---|
| ▲ Apex Ant 0x73b4…e736 | — | 81.71 | $20.69 | 3.9 min | #2 | $0.0851 | — |
| Venice.ai Proxy 0x1f22…18c9 | failingupstream error · 3.7 h · stale | 86.84 | $8.78 | 1.9 min | #1 | $0.104 | — |
"Best price" and the seller table are live Antseed catalog data (advertised $/1M tokens — or $ per generated image for unit-billed image models — not settled amounts). Reputation = buyer trust score (0-100, the Antseed SDK's own formula). "Routing" = the SDK's default buyer routing (what the VPR desktop app ships with): a trust ≥ 60 gate on the effective reputation, then cheapest-first among routable sellers; live failover state (per-peer cooldowns) is buyer-side runtime and not included. Model knowledge (TLDR, provider, About) via the VeniceStats enrichment layer. Advertised catalog, not the model used in any specific purchase. "Usage on Antseed" counts only settlements whose buyers share the per-model split on-chain (metadata v2/v3, opt-in), so every usage figure is a lower bound.