Running 550 550 Vision Arena (Testing VLMs side-by-side) πΌ Analyze images to detect and label objects
HyperGAI/HPT1_5-Air-Llama-3-8B-Instruct-multimodal Text Generation β’ Updated May 15, 2024 β’ 27 β’ 47
Running on T4 2.68k 2.68k XTTS πΈ Generate realistic voice synthesis using text and reference audio