ByteDance/Sa2VA-4B
Image-Text-to-Text • Updated
• 104k • 96
HTR
-
-
Finnish-NLP/Ahma-2-4B-Instruct
Text Generation • 4B • Updated • 159 • 4 -
black-forest-labs/FLUX.2-dev
Image-to-Image • Updated • 559k • • 1.41k -
mistralai/Mistral-Large-Instruct-2407
Updated • 7.06k • 857 -
Multicentury HTR Pipeline
🚀24Demo for handwritten text recognition model.
-
Htrflow Mcp
🔥1Image to text, alto- or page-xml
-
google/paligemma-3b-pt-896
Image-Text-to-Text • 3B • Updated • 512 • 123 -
Qwen/Qwen3-14B-GGUF
Text Generation • 15B • Updated • 61.2k • 73 -
HTRflow App
🏢53HTR (Handwritten Text Recognition) demo application
-
Riksarkivet/rtmdet_regions
Image Segmentation • Updated • 7 • 2 -
microsoft/table-transformer-structure-recognition-v1.1-all
Object Detection • 28.8M • Updated • 351k • 79 -
Riksarkivet/rtmdet_lines
Image Segmentation • Updated • 5 • 4 -
driaforall/mem-agent
Text Generation • 4B • Updated • 41 • 94 -
RT-DETRv4: Painlessly Furthering Real-Time Object Detection with Vision Foundation Models
Paper • 2510.25257 • Published • 5 -
Sapiens Pose
📊59Detect and estimate poses in images
-
Multicentury HTR Pipeline
🚀Demo for handwritten text recognition model.
-
Ovi [local]
🎥231Generate Hollywood Style Actors on your Local Machine
-
Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos
Paper • 2501.04001 • Published • 47