Keye-VL-8B-Preview is an 8-billion parameter vision-language model developed by Kwai that can process both images and video inputs alongside text. It uses a unified architecture with special tokens for visual content and supports conversational interactions. The preview model is openly hosted on Hugging Face for developers building multimodal AI applications.
Keye VL 8B Preview sits in PulseGate's Foundation models & chat category. It focuses on understanding and reasoning over both images and videos within a single unified language model interface. It is built as an open-source project for developers. Keye VL 8B Preview is open source under the Open Source license. The product ships for the web, the command line, and API.
Behind Keye VL 8B Preview is Kwai, and the product first shipped in 2025. Development happens publicly on GitHub with 806 stars and 17 commits in the last 90 days. Key capabilities include Vision-Language Processing, Video Understanding, and Multimodal Chat. It exposes integrations via a public API.
Latest indexed changes and source events
Kwai-Keye/Keye-VL-8B-Preview verified by the PulseGate indexer
Other apps tracked under the same category.
