Qwen-Image-Layered: Towards Inherent Editability via Layer Decomposition Paper • 2512.15603 • Published 17 days ago • 58
view article Article How to Choose the Best Open Source LLM for Your Project in 2025 Sep 9, 2025 • 74
CineScale: Free Lunch in High-Resolution Cinematic Visual Generation Paper • 2508.15774 • Published Aug 21, 2025 • 20
view article Article Building an AI Image Editor with Gradio and Inference Providers Aug 22, 2025 • 3
👁️ LFM2-VL Collection LFM2-VL is our first series of vision-language models, designed for on-device deployment. • 10 items • Updated 6 days ago • 61
DINOv3 Collection DINOv3: foundation models producing excellent dense features, outperforming SotA w/o fine-tuning - https://arxiv.org/abs/2508.10104 • 13 items • Updated Aug 21, 2025 • 436
view article Article Reachy Mini - The Open-Source Robot for Today's and Tomorrow's AI Builders Jul 9, 2025 • 748
Qwen2.5-Omni Collection End-to-End Omni (text, audio, image, video, and natural speech interaction) model based Qwen2.5 • 7 items • Updated 4 days ago • 160
Light-R1 Collection Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond • 7 items • Updated Oct 15, 2025 • 12
Cohere Labs Aya Vision Collection Aya Vision is a state-of-the-art family of vision models that brings multimodal capabilities to 23 languages. • 5 items • Updated Jul 31, 2025 • 70
Multimodal Representation Alignment for Image Generation: Text-Image Interleaved Control Is Easier Than You Think Paper • 2502.20172 • Published Feb 27, 2025 • 29