Open Source
Explore the latest AI open-source projects from GitHub and HuggingFace.
Explore the latest AI open-source projects from GitHub and HuggingFace.
LLaVA-OneVision-1.5 is a fully open-source framework for democratized multimodal training from EvolvingLMMs Lab. It operates on native-resolution images using a three-stage training pipeline with an 85M concept-balanced pretraining dataset and 22M instruction dataset. The complete framework trains state-of-the-art 4B and 8B multimodal models within a $16,000 compute budget, surpassing Qwen2.5-VL across multiple benchmarks. A reinforcement learning extension was also released in late 2025.
hacksider
Real-time AI face swap and one-click video deepfake with only a single image
harry0703
AI-powered short video generator that automates scripting, footage sourcing, subtitles, and composition — supporting 10+ LLM providers and batch production.
microsoft
Microsoft's official 1-bit LLM inference framework achieving 1.37x-6.17x speedup and up to 82% energy reduction, enabling 100B parameter models to run on consumer CPUs.
bytedance
ByteDance's open-source multimodal AI agent stack for GUI automation with vision-language model integration