view post Post 16,302 deepseek-ai/DeepSeek-OCR is out! 🔥 my take ⤵️ > pretty insane it can parse and re-render charts in HTML> it uses CLIP and SAM features concatenated, so better grounding> very efficient per vision tokens/performance ratio> covers 100 languages See translation
Weekly Releases (Oct 09, 2026) autotrust/GLM5.3-Flash-E192-DGX-Spark Image-Text-to-Text • 111B • Updated 8 days ago • 10.6k • 181 MicksHF/Qwen-Image-2.1-Anime-Fusal Image-to-Image • Updated 7 days ago • 89 akhaliq/Qwen-Image-2.1-Multiple-Angles-LoRA Image-to-Image • Updated 5 days ago • 2.28k • 95 speridlabs/iris-3b Text-to-Image • 3B • Updated 6 days ago • 1.45k • 312
Weekly Releases (Oct 02, 2026) SeerRay-Lab/Xiaomi-OCR-0 Image-Text-to-Text • 0.9B • Updated 11 days ago • 7.33k • 47 emperorofrome/Gmcoder Text Generation • 9B • Updated 17 days ago • 4.52k • 25 RunningHubAI/rh-qwen-image-2.1-lora-2104918997757157378 Text-to-Image • Updated 19 days ago • 88 vllm-sr/Decision-2.0-Vega-27B Zero-Shot Classification • Updated 8 days ago • 2.99k • 76
Weekly Releases (Oct 09, 2026) autotrust/GLM5.3-Flash-E192-DGX-Spark Image-Text-to-Text • 111B • Updated 8 days ago • 10.6k • 181 MicksHF/Qwen-Image-2.1-Anime-Fusal Image-to-Image • Updated 7 days ago • 89 akhaliq/Qwen-Image-2.1-Multiple-Angles-LoRA Image-to-Image • Updated 5 days ago • 2.28k • 95 speridlabs/iris-3b Text-to-Image • 3B • Updated 6 days ago • 1.45k • 312
Weekly Releases (Oct 02, 2026) SeerRay-Lab/Xiaomi-OCR-0 Image-Text-to-Text • 0.9B • Updated 11 days ago • 7.33k • 47 emperorofrome/Gmcoder Text Generation • 9B • Updated 17 days ago • 4.52k • 25 RunningHubAI/rh-qwen-image-2.1-lora-2104918997757157378 Text-to-Image • Updated 19 days ago • 88 vllm-sr/Decision-2.0-Vega-27B Zero-Shot Classification • Updated 8 days ago • 2.99k • 76
Running on Zero Agents Featured 83 UDOP 🏃 Generate answers or summaries from document images with prompts