view post Post 12775 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 3 days ago • 66k • 77 spiritbuun/buun-Qwen3.6-chat_template Updated 8 days ago • 37 avaturn-live/avtr-1 Image-to-Video • Updated 6 days ago • 710 • 29 Kwai-Keye/Keye-VL-2.0-30B-A3B Image-Text-to-Text • 31B • Updated 8 days ago • 2.24k • 108
Weekly Releases (May 22, 2026) Efficient-Large-Model/SANA-WM_bidirectional Image-to-Video • Updated 18 days ago • 119 CohereLabs/command-a-plus-05-2026-w4a4 Image-Text-to-Text • 126B • Updated 9 days ago • 85.1k • • 221 FINAL-Bench/Darwin-28B-Coder Text Generation • 27B • Updated 17 days ago • 883 • 19 LatitudeGames/Equinox-31B 31B • Updated 15 days ago • 1.23k • 48
CohereLabs/command-a-plus-05-2026-w4a4 Image-Text-to-Text • 126B • Updated 9 days ago • 85.1k • • 221
Weekly Releases (May 29, 2026) Comfy-Org/PixelDiT Updated 3 days ago • 66k • 77 spiritbuun/buun-Qwen3.6-chat_template Updated 8 days ago • 37 avaturn-live/avtr-1 Image-to-Video • Updated 6 days ago • 710 • 29 Kwai-Keye/Keye-VL-2.0-30B-A3B Image-Text-to-Text • 31B • Updated 8 days ago • 2.24k • 108
Weekly Releases (May 22, 2026) Efficient-Large-Model/SANA-WM_bidirectional Image-to-Video • Updated 18 days ago • 119 CohereLabs/command-a-plus-05-2026-w4a4 Image-Text-to-Text • 126B • Updated 9 days ago • 85.1k • • 221 FINAL-Bench/Darwin-28B-Coder Text Generation • 27B • Updated 17 days ago • 883 • 19 LatitudeGames/Equinox-31B 31B • Updated 15 days ago • 1.23k • 48
CohereLabs/command-a-plus-05-2026-w4a4 Image-Text-to-Text • 126B • Updated 9 days ago • 85.1k • • 221