Skip to content

Seed1.5-VL

ByteDanceVisual question answeringVideo descriptionLanguage modeling/generationQuestion answeringCharacter recognition (OCR)

Seed1.5-VL is a visual question answering model from ByteDance released in 2025.

About Seed1.5-VL

We present Seed1.5-VL, a vision-language foundation model designed to advance general-purpose multimodal understanding and reasoning. Seed1.5-VL is composed with a 532M-parameter vision encoder and a Mixture-of-Experts (MoE) LLM of 20B active paramet

Details

Provider
ByteDance
Task
Visual question answering,Video description,Language modeling/generation,Question answering,Character recognition (OCR)
Released
2025-05-11
Open weights
No
View model source

Explore

FAQ