Seed Models

Explore our next generation AI models

Foundation Models

Seed1.8

A general-purpose agent model capable of efficiently and accurately completing tasks in complex workflows.

Seed1.6

Seed1.6 integrates multimodal capabilities, with "adaptive thinking" balancing model performance with reasoning capability.

Seed1.5（Doubao-1.5-pro）

Seed1.5 demonstrates superior performance in knowledge, code generation, and reasoning tasks.

Seed1.5-VL

A large vision-language multimodal model, achieving state-of-the-art performance on 38 out of 60 public benchmarks.

Seed Diffusion Preview

An experimental diffusion language model specialized for code generation achieves an inference speed of 2,146 token/s.

Seed1.8

A general-purpose agent model capable of efficiently and accurately completing tasks in complex workflows.

Seed1.6

Seed1.6 integrates multimodal capabilities, with "adaptive thinking" balancing model performance with reasoning capability.

Seed1.5（Doubao-1.5-pro）

Seed1.5 demonstrates superior performance in knowledge, code generation, and reasoning tasks.

Seed1.5-VL

A large vision-language multimodal model, achieving state-of-the-art performance on 38 out of 60 public benchmarks.

Seed Diffusion Preview

An experimental diffusion language model specialized for code generation achieves an inference speed of 2,146 token/s.

Seed1.8

A general-purpose agent model capable of efficiently and accurately completing tasks in complex workflows.

Seed1.6

Seed1.6 integrates multimodal capabilities, with "adaptive thinking" balancing model performance with reasoning capability.

Seed1.5（Doubao-1.5-pro）

Seed1.5 demonstrates superior performance in knowledge, code generation, and reasoning tasks.

Seed1.5-VL

A large vision-language multimodal model, achieving state-of-the-art performance on 38 out of 60 public benchmarks.

Seed Diffusion Preview

An experimental diffusion language model specialized for code generation achieves an inference speed of 2,146 token/s.

GenMedia

Seedance 1.5 pro

A joint audio-video model that accurately follows complex instructions.

Seedream 4.5

Seedream 4.5 has an all-round improvement to support professional visual creatives with high consistency and fidelity.

Seedance 1.0

A multi-tasking video generation model that excels at multi-shot narratives, semantic understanding, and prompt following.

Seedream 4.0

A new-generation image creation model can flexibly handle complex multimodal tasks, producing high-definition images at up to 4K resolution.

SeedEdit 3.0

Fast and high-quality generative image editing, particularly with real-world images.

Seed3D 1.0

A 3D foundation model achieving SOTA performance in texture and material generation, precisely capturing fine-grained object details.

BAGEL

An open-source foundational model that natively supports multimodal understanding and generation of texts, images, and videos.

UI-TARS-1.5

Next-generation native GUI agent model, capable of effectively performing diverse tasks within virtual environments.

Seed LiveInterpret 2.0

An end-to-end simultaneous interpretation model that delivers high-quality, low-latency speech-to-speech interpretation.

Seed Realtime Voice

A native approach integrates speech and text modes to truly implement an end-to-end model of understanding and generation.

Seed-Music

A suite of music generation systems capable of producing high-quality music with fine-grained style control.

Seedance 1.5 pro

A joint audio-video model that accurately follows complex instructions.

Seedream 4.5

Seedream 4.5 has an all-round improvement to support professional visual creatives with high consistency and fidelity.

Seedance 1.0

A multi-tasking video generation model that excels at multi-shot narratives, semantic understanding, and prompt following.

Seedream 4.0

A new-generation image creation model can flexibly handle complex multimodal tasks, producing high-definition images at up to 4K resolution.

SeedEdit 3.0

Fast and high-quality generative image editing, particularly with real-world images.

Seed3D 1.0

A 3D foundation model achieving SOTA performance in texture and material generation, precisely capturing fine-grained object details.

BAGEL

An open-source foundational model that natively supports multimodal understanding and generation of texts, images, and videos.

UI-TARS-1.5

Next-generation native GUI agent model, capable of effectively performing diverse tasks within virtual environments.

Seed LiveInterpret 2.0

An end-to-end simultaneous interpretation model that delivers high-quality, low-latency speech-to-speech interpretation.

Seed Realtime Voice

A native approach integrates speech and text modes to truly implement an end-to-end model of understanding and generation.

Seed-Music

A suite of music generation systems capable of producing high-quality music with fine-grained style control.

Seedance 1.5 pro

A joint audio-video model that accurately follows complex instructions.

Seedream 4.5

Seedream 4.5 has an all-round improvement to support professional visual creatives with high consistency and fidelity.

Seedance 1.0

A multi-tasking video generation model that excels at multi-shot narratives, semantic understanding, and prompt following.

Seedream 4.0

A new-generation image creation model can flexibly handle complex multimodal tasks, producing high-definition images at up to 4K resolution.

SeedEdit 3.0

Fast and high-quality generative image editing, particularly with real-world images.

Seed3D 1.0

A 3D foundation model achieving SOTA performance in texture and material generation, precisely capturing fine-grained object details.

BAGEL

An open-source foundational model that natively supports multimodal understanding and generation of texts, images, and videos.

UI-TARS-1.5

Next-generation native GUI agent model, capable of effectively performing diverse tasks within virtual environments.

Seed LiveInterpret 2.0

An end-to-end simultaneous interpretation model that delivers high-quality, low-latency speech-to-speech interpretation.

Seed Realtime Voice

A native approach integrates speech and text modes to truly implement an end-to-end model of understanding and generation.

Seed-Music

A suite of music generation systems capable of producing high-quality music with fine-grained style control.

AI for Science

Protenix

A biomolecular foundation model capable of high-fidelity complex structure prediction and de novo protein design with a high rate of success.

Protenix

A biomolecular foundation model capable of high-fidelity complex structure prediction and de novo protein design with a high rate of success.

Protenix

A biomolecular foundation model capable of high-fidelity complex structure prediction and de novo protein design with a high rate of success.

Robotics

Seed GR-3

A robust vision-language-action model designed to be generalizable and capable of executing long-horizon and dexterous tasks.

Seed GR-3

A robust vision-language-action model designed to be generalizable and capable of executing long-horizon and dexterous tasks.

Seed GR-3

A robust vision-language-action model designed to be generalizable and capable of executing long-horizon and dexterous tasks.