AIM-Intelligence/COMPASS-Policy-Alignment-Testbed-Dataset Viewer β’ Updated Jan 6 β’ 5.92k β’ 92 β’ 11
Running Featured 379 Qwen3 VL Demo π» 379 Chat with AI using text and images for multimodal answers
QGuard:Question-based Zero-shot Guard for Multi-modal LLM Safety Paper β’ 2506.12299 β’ Published Jun 14, 2025 β’ 3
Running on L4 Featured 722 StyleTTS 2 π£ 722 Efficient, fast, and natural text to speech with StyleTTS 2!
stabilityai/stable-video-diffusion-img2vid-xt Image-to-Video β’ Updated Jul 10, 2024 β’ 137k β’ 3.23k
Running on Zero 616 Real-Time Text-to-Image SDXL Lightning β‘ 616 Real-Time Image Generation with SDXL Lightning