GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization Paper β’ 2601.05242 β’ Published Jan 8 β’ 230 β’ 9
openai/whisper-large-v3 Automatic Speech Recognition β’ 2B β’ Updated Aug 12, 2024 β’ 4.92M β’ β’ 5.65k
openai/whisper-large-v3-turbo Automatic Speech Recognition β’ 0.8B β’ Updated Oct 4, 2024 β’ 7.57M β’ β’ 2.99k
Runtime error Agents Featured 102 Oryx π¬ 102 Generate detailed descriptions from images and videos
Running on Zero Agents Featured 990 Tile Upscaler π 990 Enhance and upscale images with HDR and AI details
Running on Zero Agents Featured 2.08k PuLID-FLUX π€ 2.08k Generate custom images from text and a reference photo
Running on Zero Agents 1.68k Flux.1-dev Upscaler π 1.68k Upscale lowβresolution images to higher resolution
Running on Zero Agents 1.02k Whisper Turbo π€― 1.02k Transcribe or translate audio and YouTube videos to text
stabilityai/stable-video-diffusion-img2vid Image-to-Video β’ Updated Jul 10, 2024 β’ 49.3k β’ 1.03k
stabilityai/stable-video-diffusion-img2vid-xt Image-to-Video β’ Updated Jul 10, 2024 β’ 346k β’ 3.29k