view post Post 12909 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 6 days ago • 132 jdopensource/JoyAI-Echo Text-to-Video • Updated 4 days ago • 5.46k • 129 litert-community/gemma-4-12B-it-litert-lm Updated 8 days ago • 19.6k • 27 google/gemma-4-12B-it-qat-q4_0-unquantized Any-to-Any • 12B • Updated 6 days ago • 7.75k • 42
Weekly Releases (May 29, 2026) Comfy-Org/PixelDiT Updated 9 days ago • 91.1k • 90 spiritbuun/buun-Qwen3.6-chat_template Updated 14 days ago • 42 avaturn-live/avtr-1 Image-to-Video • Updated 12 days ago • 811 • 31 Kwai-Keye/Keye-VL-2.0-30B-A3B Image-Text-to-Text • 31B • Updated 1 day ago • 3.83k • 113
Weekly Releases (Jun 05, 2026) Comfy-Org/Ideogram-4 Updated 6 days ago • 132 jdopensource/JoyAI-Echo Text-to-Video • Updated 4 days ago • 5.46k • 129 litert-community/gemma-4-12B-it-litert-lm Updated 8 days ago • 19.6k • 27 google/gemma-4-12B-it-qat-q4_0-unquantized Any-to-Any • 12B • Updated 6 days ago • 7.75k • 42
Weekly Releases (May 29, 2026) Comfy-Org/PixelDiT Updated 9 days ago • 91.1k • 90 spiritbuun/buun-Qwen3.6-chat_template Updated 14 days ago • 42 avaturn-live/avtr-1 Image-to-Video • Updated 12 days ago • 811 • 31 Kwai-Keye/Keye-VL-2.0-30B-A3B Image-Text-to-Text • 31B • Updated 1 day ago • 3.83k • 113