DINOv3 Collection DINOv3: foundation models producing excellent dense features, outperforming SotA w/o fine-tuning - https://arxiv.org/abs/2508.10104 β’ 13 items β’ Updated Aug 21, 2025 β’ 516
ObjectClear: Complete Object Removal via Object-Effect Attention Paper β’ 2505.22636 β’ Published May 28, 2025 β’ 2
Describe Anything: Detailed Localized Image and Video Captioning Paper β’ 2504.16072 β’ Published Apr 22, 2025 β’ 64
Wan2.1 14B 480p I2V LoRAs Collection A collection of Remade's Wan2.1 14B 480p I2V LoRAs β’ 49 items β’ Updated May 24, 2025 β’ 208
Molmo Collection Artifacts for open multimodal language models. β’ 5 items β’ Updated Dec 23, 2025 β’ 309
Text-to-Image History Collection How Text-to-Image evolved on HF and inspired the Community β’ 55 items β’ Updated Nov 7, 2024 β’ 16
view article Article Enhancing Image Model Dreambooth Training Through Effective Captioning: Key Observations Jun 19, 2024 β’ 18