view post Post 12757 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 (May 29, 2026) Comfy-Org/PixelDiT Updated 2 days ago • 55.3k • 74 spiritbuun/buun-Qwen3.6-chat_template Updated 7 days ago • 35 avaturn-live/avtr-1 Image-to-Video • Updated 5 days ago • 658 • 27 Kwai-Keye/Keye-VL-2.0-30B-A3B Image-Text-to-Text • 31B • Updated 7 days ago • 1.74k • 107
Weekly Releases (May 22, 2026) Efficient-Large-Model/SANA-WM_bidirectional Image-to-Video • Updated 17 days ago • 118 CohereLabs/command-a-plus-05-2026-w4a4 Image-Text-to-Text • 126B • Updated 9 days ago • 84.7k • • 220 FINAL-Bench/Darwin-28B-Coder Text Generation • 27B • Updated 16 days ago • 880 • 19 LatitudeGames/Equinox-31B 31B • Updated 14 days ago • 1.18k • 48
CohereLabs/command-a-plus-05-2026-w4a4 Image-Text-to-Text • 126B • Updated 9 days ago • 84.7k • • 220
Weekly Releases (May 29, 2026) Comfy-Org/PixelDiT Updated 2 days ago • 55.3k • 74 spiritbuun/buun-Qwen3.6-chat_template Updated 7 days ago • 35 avaturn-live/avtr-1 Image-to-Video • Updated 5 days ago • 658 • 27 Kwai-Keye/Keye-VL-2.0-30B-A3B Image-Text-to-Text • 31B • Updated 7 days ago • 1.74k • 107
Weekly Releases (May 22, 2026) Efficient-Large-Model/SANA-WM_bidirectional Image-to-Video • Updated 17 days ago • 118 CohereLabs/command-a-plus-05-2026-w4a4 Image-Text-to-Text • 126B • Updated 9 days ago • 84.7k • • 220 FINAL-Bench/Darwin-28B-Coder Text Generation • 27B • Updated 16 days ago • 880 • 19 LatitudeGames/Equinox-31B 31B • Updated 14 days ago • 1.18k • 48
CohereLabs/command-a-plus-05-2026-w4a4 Image-Text-to-Text • 126B • Updated 9 days ago • 84.7k • • 220