Loading...

You don't need another chatbot. You need proof you can build something no one's built before. Every model, every agent, every experiment. Your table. You set it.

Platform

Knowledge
Visual Workflows
Collaboration Engine
Model Catalog

Resources

Research
Datasets

Legal

Terms of Service
Privacy Policy

© 2026 Hermosa Labs, LLC. All rights reserved.

Built in California 🌊🌊🌊

ByteDance Seed

[Beijing, China][founded 2023][backed by ByteDance Ltd.]seed.bytedance.com

ByteDance Seed is the foundation-model research team of ByteDance, founded in 2023, reporting to ByteDance CEO Liang Rubo and spread across offices in Beijing, Shanghai, Shenzhen and Hangzhou. It develops the Seed language models (marketed as Doubao Seed) behind the Doubao assistant, the Seedream image models, the Seedance video models and the OmniHuman human-animation models. The Doubao models power more than 50 application scenarios across ByteDance products.

sources:baike.baidu.com en.wikipedia.org seed.bytedance.com

· verified 2026-09-13

13

models

4

families

2023–2026

shipping

■ video 7■ image 4■ text 1■ multimodal 1

13 models · 4 families · 2023–2026

Seed (language)

newest: Seed 2.0 Mini · 2026-02-01

[api]

Seedream (image)

newest: Seedream 5.0 Lite · 2026-02

[image][api]

Seedance (video)

newest: Seedance 2.5 · 2026-08

[video][api]

OmniHuman (human animation)

newest: OmniHuman · 2025-02

[api]

Families (4)

Seed (language)

[api]

1 in catalog · 1 earlier

before the catalog2023-08 Doubao, Doubao assistant launched on the first Seed language models→

Seed 2.0 Mini

Doubao Seed 2.0 generation, video input, 262K context

[text]262k ctxnewest

sources:en.wikipedia.org

Seedream (image)

[image][api]

4 in catalog · 1 earlier

before the catalog2025-09 Seedream 4.0, unified generation and editing with reasoning→

Seedream V1

first Seedream text-to-image model

Seedream V2

second generation

Seedream 5.0 Lite

deeper instruction understanding, real-time search

[image][2 endpoints]newest

sources:seed.bytedance.com/…/seedream-4-0-officially-seed.bytedance.com/…/deeper-thinking-more-acc

Seedance (video)

[video][api]

7 in catalog

Seedance 1.0 Lite

cost-optimised 1.0 tier

Seedance 1.0 Pro

multi-shot 1080p text and image to video

[video][2 endpoints]

Seedance 1.5 Pro

joint audio-visual generation

Seedance 2.0

text, image, audio and video input; multi-shot storytelling

Seedance 2.0 Fast

faster 2.0 endpoint

Seedance 2.5

30-second clips from up to 50 multimodal references

sources:en.wikipedia.org seed.bytedance.com fal.ai

OmniHuman (human animation)

[api]

1 in catalog

OmniHuman

single image plus audio or video to full-body human video

[multimodal]newest

sources:arxiv.org