Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement Paper β’ 2608.31046 β’ Published about 1 month ago β’ 97
LibraGen: Playing a Balance Game in Subject-Driven Video Generation Paper β’ 2603.13506 β’ Published Mar 13 β’ 5
view article Article Weβre open-sourcing our text-to-image model and the process behind it Photoroom β’ Nov 12, 2025 β’ 102
fal/Qwen-Image-Edit-2511-Multiple-Angles-LoRA Image-to-Image β’ Updated Jan 7 β’ 63.6k β’ β’ 1.56k
Running on CPU Upgrade Featured 3.31k The Smol Training Playbook π 3.31k The secrets to building world-class LLMs
UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Reward Paper β’ 2509.06818 β’ Published Sep 8, 2025 β’ 29
USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning Paper β’ 2508.18966 β’ Published Aug 26, 2025 β’ 56
Phantom-Data : Towards a General Subject-Consistent Video Generation Dataset Paper β’ 2506.18851 β’ Published Jun 23, 2025 β’ 29
Phantom-Data : Towards a General Subject-Consistent Video Generation Dataset Paper β’ 2506.18851 β’ Published Jun 23, 2025 β’ 29
Alibaba-NLP/gme-Qwen2-VL-7B-Instruct Sentence Similarity β’ 8B β’ Updated Jun 9, 2025 β’ 1.41k β’ 72