Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
layoutlm-document-qa
Modelsdocument question answering model by impira · transformers
impira/layoutlm-document-qa -
layoutlmv3-base
Modelsmodel by microsoft · transformers
microsoft/layoutlmv3-base -
video to video model by Lightricks · ltx
Lightricks/LTX-2.5-22b-IC-LoRA-Layout-To-Render -
chandra-ocr-2
Modelsimage text to text model by datalab-to · transformers
datalab-to/chandra-ocr-2 -
PaddleOCR-VL
Modelsimage text to text model by PaddlePaddle · PaddleOCR
PaddlePaddle/PaddleOCR-VL -
granite-docling-258M
Modelsimage text to text model by ibm-granite · transformers
ibm-granite/granite-docling-258M -
dots.ocr
Modelsimage text to text model by dots-studio · dots_ocr
dots-studio/dots.ocr -
indra-ocr
Modelsimage to text model by datalab-to · onnx
datalab-to/indra-ocr -
Dolphin
Modelsimage text to text model by ByteDance · transformers
ByteDance/Dolphin -
PaddleOCR-VL-1.5
Modelsimage text to text model by PaddlePaddle · PaddleOCR
PaddlePaddle/PaddleOCR-VL-1.5 -
PaddleOCR-VL-1.6
Modelsimage text to text model by PaddlePaddle · PaddleOCR
PaddlePaddle/PaddleOCR-VL-1.6 -
surya-ocr-2.5
Modelsimage text to text model by datalab-to · transformers
datalab-to/surya-ocr-2.5 -
GroundAnything-VLM
Modelsimage text to text model by GroundingPI · transformers
GroundingPI/GroundAnything-VLM -
GroundingPI
Modelsimage text to text model by GroundingPI · transformers
GroundingPI/GroundingPI -
Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.
qwen/qwen2.5-vl-72b-instruct -
Z.ai: GLM 4.6V
ModelsGLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes complex page layouts...
z-ai/glm-4.6v
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.