view post Post 12939 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 (Jun 05, 2026) Comfy-Org/Ideogram-4 Updated 8 days ago • 142 jdopensource/JoyAI-Echo Text-to-Video • Updated 6 days ago • 9.2k • 133 litert-community/gemma-4-12B-it-litert-lm Updated 10 days ago • 23.9k • 29 google/gemma-4-12B-it-qat-q4_0-unquantized Any-to-Any • 12B • Updated 8 days ago • 19k • 44
Weekly Releases (May 29, 2026) Comfy-Org/PixelDiT Updated 11 days ago • 37.9k • 91 spiritbuun/buun-Qwen3.6-chat_template Updated 16 days ago • 44 avaturn-live/avtr-1 Image-to-Video • Updated 13 days ago • 370 • 32 Kwai-Keye/Keye-VL-2.0-30B-A3B Image-Text-to-Text • 31B • Updated 3 days ago • 4.5k • 112
Weekly Releases (Jun 05, 2026) Comfy-Org/Ideogram-4 Updated 8 days ago • 142 jdopensource/JoyAI-Echo Text-to-Video • Updated 6 days ago • 9.2k • 133 litert-community/gemma-4-12B-it-litert-lm Updated 10 days ago • 23.9k • 29 google/gemma-4-12B-it-qat-q4_0-unquantized Any-to-Any • 12B • Updated 8 days ago • 19k • 44
Weekly Releases (May 29, 2026) Comfy-Org/PixelDiT Updated 11 days ago • 37.9k • 91 spiritbuun/buun-Qwen3.6-chat_template Updated 16 days ago • 44 avaturn-live/avtr-1 Image-to-Video • Updated 13 days ago • 370 • 32 Kwai-Keye/Keye-VL-2.0-30B-A3B Image-Text-to-Text • 31B • Updated 3 days ago • 4.5k • 112