Vision

The Seed Vision team focuses on foundational models for visual generation, developing multimodal generative models, and carrying out leading research and application development to solve fundamental computer vision challenges in GenAI.

Latest advancements

Seedream

Seedream 5.0 Lite A unified multimodal image generation model endowed with deep thinking and online search capabilities.

Seedance

Seedance 2.0 adopts a unified multimodal audio-video joint generation architecture and has the most comprehensive multimodal content reference and editing capabilities in the industry.

SeedEdit

A universal image editing model which enables diverse editing operations on images through simple natural language input. These operations include photo retouching, clothing replacement, beautification, style transformation, as well as adding or removing elements in specified regions.

Selected papers

Dec 15, 2025

Seedance 1.5 pro: A Native Audio-Visual Joint Generation Foundation Model

Computer Vision and Pattern Recognition

Jun 11, 2025

Seedance 1.0: Exploring the Boundaries of Video Generation Models

Computer Vision

Jun 5, 2025

SeedEdit 3.0: Fast and High-Quality Generative Image Editing

Computer Vision

Featured roles

Research Scientist, Multimodal Foundation Model

Singapore

Experienced Hiring

Apply Now

Research Scientist- Foundation Model, Video Generation

San Jose

Experienced Hiring

Apply Now

Research Engineer- Foundation Model AI Platform- San Jose

San Jose

Experienced Hiring

Apply Now

Research Scientist Graduate (Foundation Model, Video Generation) - 2025 Start (PhD)

San Jose

Campus Recruitment

Apply Now

Student Researcher (Seed - Foundation Model, Video Generation) - 2025 Start (PhD)

San Jose

Internship

Apply Now

Student Researcher (Seed - Foundation Model AI Platform) - 2025 Start (PhD)

San Jose

Internship

Apply Now