nvidia/DeepSeek-V4.1-Flash-1017-NVFP4 Image-Text-to-Text β’ 665B β’ Updated 17 days ago β’ 77.6k β’ 187
Running on Zero Agents Featured 186 ReconViaGen π₯ 186 High-fidelity 3D Geometry Generation from multi-view images
utrobinmv/t5_summary_en_ru_zh_base_2048 Summarization β’ 0.3B β’ Updated Mar 18, 2025 β’ 59 β’ 47
openai/whisper-large-v3 Automatic Speech Recognition β’ 2B β’ Updated Aug 12, 2024 β’ 3.25M β’ β’ 6.83k
Running on Zero Agents Featured 2.39k Bark πΆ 2.39k Generate realistic speech and sounds from any text
Runtime error Agents Featured 2.19k Wan2.1 π» 2.19k Wan: Open and Advanced Large-Scale Video Generative Models