DFN Models + Data Collection CLIP Models trained using DFN-2B/DFN-5B datasets β’ 7 items β’ Updated Aug 25, 2025 β’ 18
EricRollei/HunyuanImage-3.0-Instruct-Distil-INT8-v2 Text-to-Image β’ 83B β’ Updated Feb 22 β’ 153 β’ 4
EricRollei/HunyuanImage-3.0-Instruct-Distil-INT8-v2 Text-to-Image β’ 83B β’ Updated Feb 22 β’ 153 β’ 4
EricRollei/HunyuanImage-3.0-Instruct-Distil-NF4-v2 Text-to-Image β’ 83B β’ Updated Feb 22 β’ 778 β’ 8
EricRollei/HunyuanImage-3.0-Instruct-Distil-NF4-v2 Text-to-Image β’ 83B β’ Updated Feb 22 β’ 778 β’ 8
view article Article Reading the Geometry of Learned Representations: How Synthetic Primitives Became a Rosetta Stone for VAE Latent Spaces Feb 18 β’ 1