{ "id": "ep5gjz1zfe", "slug": "seedance", "title": "Seedance", "updated": "2026-10-15", "topic_path": [ { "id": "technology", "label": "Technology and the built world", "api_url": "https://www.edgepedia.org/api/v1/topics/technology" }, { "id": "technology.computing", "label": "Computing and digital systems", "api_url": "https://www.edgepedia.org/api/v1/topics/technology.computing" }, { "id": "technology.computing.modern_ai", "label": "Modern AI: foundation models, generative AI, and the AI industry", "api_url": "https://www.edgepedia.org/api/v1/topics/technology.computing.modern_ai" }, { "id": "technology.computing.modern_ai.models", "label": "Model families and named models", "api_url": "https://www.edgepedia.org/api/v1/topics/technology.computing.modern_ai.models" }, { "id": "technology.computing.modern_ai.models.video_generation_models", "label": "Video generation models", "api_url": "https://www.edgepedia.org/api/v1/topics/technology.computing.modern_ai.models.video_generation_models" } ], "geo": [ { "id": "geo.chn.t2021.technology.computing.modern_ai.models", "label": "China · 2021 and later: Model families and named models", "api_url": "https://www.edgepedia.org/api/v1/geo/geo.chn.t2021.technology.computing.modern_ai.models", "path": [ { "id": "geo.chn", "label": "China", "api_url": "https://www.edgepedia.org/api/v1/geo/geo.chn" }, { "id": "geo.chn.t2021", "label": "China · 2021 and later", "api_url": "https://www.edgepedia.org/api/v1/geo/geo.chn.t2021" }, { "id": "geo.chn.t2021.technology", "label": "Technology and the built world", "api_url": "https://www.edgepedia.org/api/v1/geo/geo.chn.t2021.technology" }, { "id": "geo.chn.t2021.technology.computing", "label": "Computing and digital systems", "api_url": "https://www.edgepedia.org/api/v1/geo/geo.chn.t2021.technology.computing" }, { "id": "geo.chn.t2021.technology.computing.modern_ai", "label": "Modern AI: foundation models, generative AI, and the AI industry", "api_url": "https://www.edgepedia.org/api/v1/geo/geo.chn.t2021.technology.computing.modern_ai" }, { "id": "geo.chn.t2021.technology.computing.modern_ai.models", "label": "Model families and named models", "api_url": "https://www.edgepedia.org/api/v1/geo/geo.chn.t2021.technology.computing.modern_ai.models" } ] } ], "excerpt": "Seedance is a family of text-to-video and multimodal audio-video generation models developed by ByteDance's Seed team, first released in 2025 and expanded through the 2.0 and 2.5 generations in 2026.", "snippet": "Seedance is a family of text-to-video and multimodal audio-video generation models developed by ByteDance's Seed team, first released in 2025 and expanded through the 2.0 and 2.5 generations in 2026.", "node": "technology.computing.modern_ai.models.video_generation_models", "markdown": "# Seedance\n\n**Seedance** is a family of text-to-video and multimodal audio-video generation models developed by ByteDance's Seed team, first released in 2025 and expanded through the 2.0 and 2.5 generations in 2026. The series began as a high-speed video foundation model and evolved into a unified system that generates picture and sound together, accepts text, image, audio, and video inputs as references, and supports multi-shot storytelling and timestamp-level editing.[1](https://seed.bytedance.com/en/public_papers/seedance-1-0-exploring-the-boundaries-of-video-generation-models) • [2](https://arxiv.org/abs/2604.14148)\n\n| Key fact | Detail |\n|---|---|\n| Developer | ByteDance Seed team (Beijing-based ByteDance, creator of TikTok)[3](https://apnews.com/article/7e445388401d172c6bf51d0d42aa4f24) |\n| First release | Seedance 1.0, a video foundation model integrated into Doubao and Jimeng in June 2025[1](https://seed.bytedance.com/en/public_papers/seedance-1-0-exploring-the-boundaries-of-video-generation-models) |\n| Speed | Seedance 1.0 generates a 5-second 1080p video in 41.4 seconds, aided by a 10x inference speedup from multi-stage distillation[1](https://seed.bytedance.com/en/public_papers/seedance-1-0-exploring-the-boundaries-of-video-generation-models) |\n| Audio-video generation | Seedance 1.5 pro introduced native joint audio-video generation with multilingual and dialect lip-syncing[4](https://seed.bytedance.com/public_papers/seedance-1-5-pro-a-native-audio-visual-joint-generation-foundation-model) |\n| Seedance 2.0 | Released in China in early February 2026; 4 to 15 second audio-video outputs at 480p and 720p; up to 3 video clips, 9 images, and 3 audio clips as references[2](https://arxiv.org/abs/2604.14148) |\n| Seedance 2.5 | Launched July 31, 2026; 30-second single-pass generations, up to 30 images, 10 videos, and 10 audio references, and timestamp-level editing[5](https://seed.bytedance.com/en/blog/one-take-creation-flexible-referencing-introducing-seedance-2-5) |\n| Controversy | The Motion Picture Association sent ByteDance a cease-and-desist letter in February 2026, its first to a major AI firm, alleging infringement of member studios' works[6](https://www.axios.com/2026/02/20/hollywood-seedance-intellectual-property) |\n\n## Seedance 1.0\n\nSeedance 1.0 was introduced as a high-performance, inference-efficient video foundation generation model. Its technical report describes four core improvements: multi-source data curation with precision video captioning; an efficient pre-training paradigm enabling interleaved multimodal positional encoding, native multi-shot generation, and multi-task modeling; post-training with fine-grained supervised fine-tuning and video-specific RLHF using multi-dimensional reward mechanisms; and model acceleration achieving a 10x inference speedup through multi-stage distillation and system-level optimizations.[1](https://seed.bytedance.com/en/public_papers/seedance-1-0-exploring-the-boundaries-of-video-generation-models)\n\nThe model supports multi-shot video generation from both text and image, producing 1080p videos with consistent subjects, visual style, and atmosphere across shot transitions. On the third-party benchmarking platform [Artificial Analysis](https://www.edgepedia.org/artificial-analysis), Seedance 1.0 ranked first on both the text-to-video and image-to-video leaderboards as of June 2025.[7](https://seed.bytedance.com/en/blog/tech-report-of-seedance-1-0-is-now-publicly-available) It was integrated into ByteDance's Doubao and Jimeng platforms in June 2025.[1](https://seed.bytedance.com/en/public_papers/seedance-1-0-exploring-the-boundaries-of-video-generation-models)\n\n## Seedance 1.5 pro\n\nSeedance 1.5 pro, described in an arXiv report, was engineered specifically for native, joint audio-video generation. It uses a dual-branch Diffusion Transformer architecture with a cross-modal joint module and a multi-stage data pipeline, plus post-training with supervised fine-tuning and RLHF, and an acceleration framework that boosts inference speed by over 10x. ByteDance highlights precise multilingual and dialect lip-syncing, dynamic cinematic camera control, and enhanced narrative coherence; the model is accessible on Volcano Engine.[4](https://seed.bytedance.com/public_papers/seedance-1-5-pro-a-native-audio-visual-joint-generation-foundation-model) The 1.5 pro version added joint audio-video generation with lip-synced multilingual dialogue and sound effects, launching at 480p and 720p.[8](https://github.com/seedance-official/Seedance-2.0)\n\n## Seedance 2.0\n\nSeedance 2.0 was officially released in China in early February 2026, with the launch announced on February 12, 2026.[2](https://arxiv.org/abs/2604.14148) • [9](https://seed.bytedance.com/en/blog/seedance-2-0-official-launch) It adopts a unified multimodal audio-video joint generation architecture supporting four input modalities: text, image, audio, and video.[9](https://seed.bytedance.com/en/blog/seedance-2-0-official-launch) Users can simultaneously input up to 9 images, 3 video clips, and 3 audio clips plus natural-language instructions, and the model can reference composition, motion, camera movement, visual effects, and audio from those inputs, including text-based storyboards.[9](https://seed.bytedance.com/en/blog/seedance-2-0-official-launch)\n\nThe model generates audio-video content of 4 to 15 seconds at native 480p and 720p resolutions, supports 15-second multi-shot output with dual-channel audio, and ships with an accelerated variant, Seedance 2.0 Fast, for low-latency scenarios.[2](https://arxiv.org/abs/2604.14148) • [9](https://seed.bytedance.com/en/blog/seedance-2-0-official-launch) ByteDance's own evaluation reports industry-leading performance in multimodal reference generation and video tasks, while acknowledging remaining weaknesses in detail stability, hyper-realism, occasional audio distortion, multi-subject consistency, and text rendering accuracy.[9](https://seed.bytedance.com/en/blog/seedance-2-0-official-launch)\n\nSeedance 2.0 rolled out on Jimeng AI, Doubao, and other platforms, with API access via BytePlus ModelArk and resale through third-party hosts such as fal.ai, [Replicate](https://www.edgepedia.org/replicate), WaveSpeed, and Kie.[10](https://seed.bytedance.com/zh/blog/official-launch-of-seedance-2-0?view_from=content_recommend) • [8](https://github.com/seedance-official/Seedance-2.0)\n\n## Seedance 2.5\n\n[Seedance 2.5](https://www.edgepedia.org/seedance-2-5) launched on July 31, 2026, building on the 2.0 architecture with emphasis on long-form storytelling, multimodal reference, and editing. It extends single-pass generation from 15 to 30 seconds with multi-round extensions, allowing multi-minute content with a consistent audiovisual language, and raises reference limits to 30 images, 10 video clips, and 10 audio clips in a single pass.[5](https://seed.bytedance.com/en/blog/one-take-creation-flexible-referencing-introducing-seedance-2-5) Editing gains include timestamp-level control for targeted changes to audio and video, plus green screen, camera perspective, and reference-based editing; the model also uses clay-render references to control camera movement, blocking, and physically consistent lighting. It rolled out on Jimeng AI and Doubao Pro, with API access via BytePlus ModelArk to follow.[5](https://seed.bytedance.com/en/blog/one-take-creation-flexible-referencing-introducing-seedance-2-5)\n\n## Hollywood copyright dispute\n\nShortly after launch, Seedance 2.0 drew condemnation from Hollywood organizations. A widely shared video posted by Irish director Ruairí Robinson showed AI versions of [Tom Cruise](https://www.edgepedia.org/tom-cruise) and [Brad Pitt](https://www.edgepedia.org/brad-pitt) fighting in a post-apocalyptic wasteland; screenwriter Rhett Reese, co-writer of the Deadpool movies, responded that the technology threatened film careers.[3](https://apnews.com/article/7e445388401d172c6bf51d0d42aa4f24) The Motion Picture Association said Seedance 2.0 had \"engaged in unauthorized use of U.S. copyrighted works on a massive scale,\" and the actors union [SAG-AFTRA](https://www.edgepedia.org/sag-aftra) condemned what it called unauthorized use of members' voices and likenesses.[3](https://apnews.com/article/7e445388401d172c6bf51d0d42aa4f24)\n\nOn February 20, 2026, the MPA sent [ByteDance](https://www.edgepedia.org/bytedance) a cease-and-desist letter, the first time the association, which represents all of the major Hollywood studios, had sent such a letter to a major AI firm. The letter, addressed to ByteDance global general counsel John Rogovin, accused the company of producing content that closely replicates distinctive characters and other copyright-protected elements of member studios' works, and demanded written confirmation of corrective steps by February 27. In the following days, Disney, Warner Bros. Discovery, [Paramount Skydance](https://www.edgepedia.org/paramount-skydance), Netflix, and [Sony Pictures](https://www.edgepedia.org/sony-pictures) each sent their own cease-and-desist letters.[6](https://www.axios.com/2026/02/20/hollywood-seedance-intellectual-property) ByteDance responded that it respects intellectual property rights and is taking steps to strengthen safeguards against unauthorized use of intellectual property and likeness by users.[3](https://apnews.com/article/7e445388401d172c6bf51d0d42aa4f24) At the time of the backlash, Seedance 2.0 was available only in China.[3](https://apnews.com/article/7e445388401d172c6bf51d0d42aa4f24)\n\nThe dispute intersected with commercial concerns about cost. In testimony before the [United States Senate](https://www.edgepedia.org/united-states-senate), one content creator shared a comparison of a clip from the film *F1* with a near-exact copy generated by Seedance, claiming the model replicated the most expensive shot in the film for nine cents.[11](https://www.blackburn.senate.gov/services/files/5C1BC7D6-C8DC-4B9D-A5F1-C3DB28380B8D)\n\n## References\n\n1. [Seedance 1.0: Exploring the Boundaries of Video Generation Models, ByteDance Seed](https://seed.bytedance.com/en/public_papers/seedance-1-0-exploring-the-boundaries-of-video-generation-models)\n2. [Seedance 2.0: Advancing Video Generation for World Complexity, arXiv](https://arxiv.org/abs/2604.14148)\n3. [AI video generator from creator of TikTok sparks a Hollywood backlash, AP News](https://apnews.com/article/7e445388401d172c6bf51d0d42aa4f24)\n4. [Seedance 1.5 pro: A Native Audio-Visual Joint Generation Foundation Model, ByteDance Seed](https://seed.bytedance.com/public_papers/seedance-1-5-pro-a-native-audio-visual-joint-generation-foundation-model)\n5. [One-take Creation, Flexible Referencing: Introducing Seedance 2.5, ByteDance Seed](https://seed.bytedance.com/en/blog/one-take-creation-flexible-referencing-introducing-seedance-2-5)\n6. [Motion Picture Association sends cease-and-desist letter to ByteDance over Seedance 2.0, Axios](https://www.axios.com/2026/02/20/hollywood-seedance-intellectual-property)\n7. [Tech report of Seedance 1.0 is now publicly available, ByteDance Seed](https://seed.bytedance.com/en/blog/tech-report-of-seedance-1-0-is-now-publicly-available)\n8. [Seedance-2.0 repository, GitHub](https://github.com/seedance-official/Seedance-2.0)\n9. [Seedance 2.0 Official Launch, ByteDance Seed](https://seed.bytedance.com/en/blog/seedance-2-0-official-launch)\n10. [字节跳动Seed：Seedance 2.0 正式发布](https://seed.bytedance.com/zh/blog/official-launch-of-seedance-2-0?view_from=content_recommend)\n11. [United States Senate document on Seedance copyright concerns](https://www.blackburn.senate.gov/services/files/5C1BC7D6-C8DC-4B9D-A5F1-C3DB28380B8D)\n\n---\n*Topic: Encyclopedia › Technology and the built world › Computing and digital systems › Modern AI: foundation models, generative AI, and the AI industry › Model families and named models › Video generation models*\n\n*Initially written Sep 17, 2026 · Reviewed: Sep 18, 2026; Oct 15, 2026 · Edited: Sep 18, 2026; Oct 15, 2026 · Last review: Oct 15, 2026*\n\n*Copyright 2026 EdgeChat AI, a subsidiary of Biostate AI.*\n\nLicense: Edgepedia Community License 1.0, https://www.edgepedia.org/edgepedia/license\n", "same_as": [], "url": "https://www.edgepedia.org/seedance", "markdown_url": "https://www.edgepedia.org/seedance.md", "license": { "name": "Edgepedia Community License 1.0", "url": "https://www.edgepedia.org/edgepedia/license", "summary": "Free with credit, commercial use included. AI training is open to everyone. For other uses, organizations over USD 100M in revenue or 100M monthly users license separately.", "spdx": "LicenseRef-Edgepedia-Community-1.0" }, "credit": "\"Seedance\", Edgepedia (EdgeChat), https://www.edgepedia.org/seedance. Edgepedia Community License 1.0.", "credit_md": "\"[Seedance](https://www.edgepedia.org/seedance)\", Edgepedia (EdgeChat), [https://www.edgepedia.org/seedance](https://www.edgepedia.org/seedance). [Edgepedia Community License 1.0](https://www.edgepedia.org/edgepedia/license).", "credit_html": "\"Seedance\", Edgepedia (EdgeChat), https://www.edgepedia.org/seedance. Edgepedia Community License 1.0.", "speakable": "Seedance is a family of text-to-video and multimodal audio-video generation models developed by ByteDance's Seed team, first released in 2025 and expanded through the 2.0 and 2.5 generations in 2026." }