Video · ByteDance

Seedance 2.0 and 1.5

ByteDance's 2026 multimodal model: image, references and audio in, a clip with synced sound out. Pick it for dialogue scenes up to 15 s.

Anonymized Moderate cost
Latest versionSeedance 2.0February 12, 2026
Artificial Analysis Image to Video Arena1,000 Elo#18 of 22 on Artificial Analysis Image to Video Arena
Price$0.0854 per second of video$0.427 a 5 s clip
Key specClips up to 15 s, with sound

What sets it apart

Seedance 2.0 turned ByteDance's line into a four-input model (text, image, audio, video) with sound generated jointly with the picture and automatic shot planning. The catalog also keeps cheaper Fast and Mini tiers and the earlier 1.5 Pro.

  • Joint audio and video generation
  • Fast and Mini tiers for drafts
  • Automatic shot decomposition

Recommended for: keep the same character or product across shots.

Strengths and limits

Where it shines

  • Lip-synced speech in several languages, generated with the picture
  • Reference mode takes several images and audio clips
  • 2.0 goes up to 4K; Mini and 1.5 keep costs low

Think twice when

  • These public versions refuse photos with a recognizable person
  • No reference clips here, only images and audio
  • 2.0: 4 to 15 s; 1.5 Pro: 4 to 12 s
  • Native sound on every version
  • 2.0 up to 4K, Fast and Mini up to 720p

Use cases

Dialogue scene

Two colleagues in an elevator. She says, in English, 'Big day tomorrow.' He answers, 'Don't remind me.' Soft elevator hum, 8 seconds.

Voice and picture are generated together, so lips match.

Cheap draft first

A red kite flying over a beach, camera tilting up to the sky. 5 seconds.

Mini and Fast let you test before the full tier.

Animate a storyboard frame

From this concept frame, create a 10 second shot where the astronaut turns, the visor reflects a distant planet, with a deep low hum.

Image input keeps the look of your concept art.

Against its rivals

  • Kling V3Kling V3 adds motion control and a 4K tier.#12 of 22 on Artificial Analysis Image to Video Arena (1,055 Elo)
  • Veo 3 and 3.1Veo is capped at 8 s but very polished.#7 of 22 on Artificial Analysis Image to Video Arena (1,082 Elo)
  • Wan 2.xWan 2.x is cheaper and has a video edit mode.#8 of 22 on Artificial Analysis Image to Video Arena (1,077 Elo)
Compare side by side ↗

Version history

Each version, dated, with what it changed over the one before.

  1. Seedance 1.0Earlier, not in Sub Rosa
    • First Seedance: 1080p text and image to video with multi-shot clips, no audio.
    Source : en.wikipedia.org
  2. Seedance 1.5 Pro
    • Generates audio and video together in one model, with multilingual lip-sync.
    • Adds sound effects, music and camera moves such as dolly zoom.
    Source : en.wikipedia.org
  3. Seedance 2.0Latest
    • Four input types in one prompt: text, image, audio and video.
    • Clips up to 15 s with multi-shot scene planning and synced audio.
    • Fast and Mini tiers trade quality for price.
    Source : en.wikipedia.org

Benchmarks

How to read these scores: what a benchmark tells you.

Artificial Analysis Image to Video Arena: #18 of 22 models measured in the catalog. The same blind duel, starting from one image: which clip brings it to life better. An Elo rating: higher is preferred more often. 100 points apart means the higher-rated model wins about 64% of duels.

Artificial Analysis Image to Video ArenaElo rating · Artificial Analysis, October 4, 2026
  1. 1. MiniMax H3 MaxMiniMax H3 (Hailuo)1,195
  2. 2. MiniMax H3MiniMax H3 (Hailuo)1,181
  3. 3. Wan 3.0Wan 3.01,164
  4. 4. HappyHorse 1.1HappyHorse1,104
  5. 5. Grok Imagine 1.5Grok Imagine video1,098
  6. 6. HappyHorse 1.0HappyHorse1,083
  7. 7. Veo 3.1 Full QualityVeo 3 and 3.11,082
  8. 8. Wan 2.7Wan 2.x1,077
  9. 9. Grok ImagineGrok Imagine video1,072
  10. 10. Veo 3.1 FastVeo 3 and 3.11,066
  11. 18. Seedance 1.5 ProSeedance 2.0 and 1.51,000
See the numbers
ModelElo
1. MiniMax H3 Max1,195
2. MiniMax H31,181
3. Wan 3.01,164
4. HappyHorse 1.11,104
5. Grok Imagine 1.51,098
6. HappyHorse 1.01,083
7. Veo 3.1 Full Quality1,082
8. Wan 2.71,077
9. Grok Imagine1,072
10. Veo 3.1 Fast1,066
18. Seedance 1.5 Pro1,000

Artificial Analysis Text to Video Arena with audio: #6 of 18 models measured in the catalog. The duel for clips with sound: picture, voices, effects and how well they match. An Elo rating: higher is preferred more often. Only models that make their own sound take part.

Artificial Analysis Text to Video Arena with audioElo rating · Artificial Analysis, October 4, 2026
  1. 1. Wan 3.0Wan 3.01,156
  2. 2. Seedance 2.5Seedance 2.51,142
  3. 3. MiniMax H3MiniMax H3 (Hailuo)1,138
  4. 4. MiniMax H3 MaxMiniMax H3 (Hailuo)1,134
  5. 5. Flux 3FLUX 3 video1,127
  6. 6. Seedance 2.0Seedance 2.0 and 1.51,119
  7. 7. Gemini Omni Flash 1.1Gemini Omni Flash1,113
  8. 8. Grok Imagine 1.5Grok Imagine video1,044
  9. 9. HappyHorse 1.1HappyHorse1,043
  10. 10. Wan 2.7Wan 2.x1,029
See the numbers
ModelElo
1. Wan 3.01,156
2. Seedance 2.51,142
3. MiniMax H31,138
4. MiniMax H3 Max1,134
5. Flux 31,127
6. Seedance 2.01,119
7. Gemini Omni Flash 1.11,113
8. Grok Imagine 1.51,044
9. HappyHorse 1.11,043
10. Wan 2.71,029

All 11 models in this family

ModelUsePrivacyPrice
Seedance 2.0seedance-2-0-text-to-video-basicText to videoAnonymized$0.0854 per second of video$0.427 a 5 s clip
Seedance 2.0seedance-2-0-image-to-video-basicImage to videoAnonymized$0.0854 per second of video$0.427 a 5 s clip
Seedance 2.0 R2Vseedance-2-0-reference-to-video-basicReferences to videoAnonymized$0.0855 per second of video$0.428 a 5 s clip
Seedance 2.0 Fastseedance-2-0-fast-text-to-video-basicText to videoAnonymized$0.0683 per second of video$0.342 a 5 s clip
Seedance 2.0 Fastseedance-2-0-fast-image-to-video-basicImage to videoAnonymized$0.0683 per second of video$0.342 a 5 s clip
Seedance 2.0 Fast R2Vseedance-2-0-fast-reference-to-video-basicReferences to videoAnonymized$0.0684 per second of video$0.342 a 5 s clip
Seedance 2.0 Miniseedance-2-0-mini-text-to-video-basicText to videoAnonymized$0.0423 per second of video$0.212 a 5 s clip
Seedance 2.0 Miniseedance-2-0-mini-image-to-video-basicImage to videoAnonymized$0.0423 per second of video$0.212 a 5 s clip
Seedance 2.0 Mini R2Vseedance-2-0-mini-reference-to-video-basicReferences to videoAnonymized$0.0423 per second of video$0.212 a 5 s clip
Seedance 1.5 Proseedance-1-5-pro-text-to-video-basicText to videoAnonymized$0.0261 per second of video$0.131 a 5 s clip
Seedance 1.5 Proseedance-1-5-pro-image-to-video-basicImage to videoAnonymized$0.0342 per second of video$0.171 a 5 s clip

Specifications

SpecificationSeedance 2.0Seedance 1.5 Pro
ReleasedFebruary 12, 2026December 2025
WeightsClosedClosed
Acceptstext, images, audio, videotext, images
Producesvideo, audiovideo, audio
Clip length4 to 15 s, with sound4 to 12 s, with sound
Resolutions4k, 1080p, 720p, 480p1080p, 720p, 480p
Languages·Multilingual lip-sync
Price$0.0854 per second of video$0.0261 per second of video
PrivacyAnonymizedAnonymized

Prices, context and lengths from the live catalog on October 16, 2026; parameters and licenses from the maker.