Best YOLO Alternatives?
Self-hosting LLMs seems pointless—what am I missing?
Best local vision models for use in "computer use" type application?
Should I use premiere, after effects or both of them?
Janus-1B vs Moondream2 for meme understanding
tracking peoples gazes in real time at retail stores w/ Moondream
I'm a C# developer. What should I do to keep up with AI?
deepseek is a side project pt. 2
deepseek was a hobby project
batch script for moondream
Coming soon: 100% Local Video Understanding Engine (an open-source project that can classify, caption, transcribe, and understand any video on your local device)
Local Video Transcription and Search Solution for Podcast Archives
Community Showcase: LCLV, real-time video analysis with Moondream 2B & OLLama (open source, local)
Thank you for 7,000 GitHub stars!
Coming soon: 100% Local Video Understanding Engine (an open-source project that can classify, caption, transcribe [Whisper v3], and understand any video on your local device)
is rag becoming an anti-pattern?
deepseek is a side project
Reliable Data Annotation Tool for Computer Vision Projects?
Why is Whisper Large hallucinating disclaimers when the audio is music?
Best small multimodal embedding model? that can be run with ollama and on cpu with reasonable time to embed documents.
Moondream integration
LCLV: Real-time video analysis with Moondream 2B & OLLama (open source, local). Anyone want a set up guide?
