1.24k
Joy Caption Pre Alpha
π¬
Generate captions for images
VisΓ£o Computacional
-
-
502
Florence2 + SAM2
π₯Segment objects in images and videos using text prompts
-
21
Video Llava
π¨Generate descriptions by uploading images or videos
-
106
ChartGemma
π¨Generate insights from charts using text prompts
-
79
Chameleon 30b
π₯Generate descriptions for images using text prompts
-
87
TrOCR Handwritten
π’ -
microsoft/trocr-base-handwritten
Image-to-Text β’ Updated β’ 163k β’ 414 -
100
YOLOv10 Web
πUpload an image to detect objects
-
74
PDF to Markdown
πExtract text and metadata from PDF files
-
234
Video LLaVA
π -
52
Paligemma Doc
πTry PaliGemma on document understanding tasks
-
215
Microsoft Phi-3-Vision-128k
π»Generate image descriptions
-
microsoft/Phi-3-vision-128k-instruct
Text Generation β’ Updated β’ 17.9k β’ 959 -
322
Ovis1.6 Gemma2 9B
πChat with an AI that understands images and text
-
390
Llama-Vision-11B
πAsk questions about images and get detailed answers
-
4.33k
OpenGPT 4o
π₯GPT 4o like bot.
-
202
docTR
πExtract and recognize text from documents
-
103
Oryx
π¬Generate detailed descriptions from images and videos
-
74
ColPali fine-tuning Query Generator
πGenerate retrieval queries from document images
-
46
Microsoft Phi-3 Vision 128k
π₯Microsoft Phi-3 Vision 128k with Multimodal capabilities
-
ChaoticNeutrals/LLaVA-Llama-3-8B-mmproj-Updated
Updated β’ 260 β’ 20 -
koboldcpp/mmproj
Updated β’ 8.49k β’ 77 -
openbmb/MiniCPM-Llama3-V-2_5-gguf
Updated β’ 5.43k β’ 213 -
microsoft/trocr-base-printed
Image-to-Text β’ Updated β’ 474k β’ 176 -
21
Pangea
πA Fully Open Multilingual Multimodal LLM for 39 Languages
-
161
DocLayout YOLO
πDemo for DocLayout-YOLO
-
344
MinerU
πConvert PDF or image to Markdown
-
5
IMG 2 TEXT
π»Extract text from images
-
xtuner/llava-phi-3-mini-gguf
Image-to-Text β’ Updated β’ 1.95k β’ 134 -
xtuner/llava-llama-3-8b-v1_1-gguf
Image-to-Text β’ Updated β’ 3.54k β’ 218 -
213
JanusFlow 1.3B
πHuggingface space for JanusFlow-1.3B
-
389
Qwen2.5 Turbo 1M Demo
π»Upload documents for Q&A
-
227
ShowUI
π»Generate clickable coordinates on a screenshot
-
48
Paligemma2 Vqav2
π¨PaliGemma2 LoRA finetuned on VQAv2
-
bartowski/Qwen2-VL-2B-Instruct-GGUF
Image-Text-to-Text β’ Updated β’ 3.57k β’ 26 -
1
Chatbot-with-MaritacaAI-for-PDFs
π -
165
Gaze Demo
πGaze detection using Moondream
-
moondream/moondream2-gguf
Updated β’ 376 β’ 24 -
172
ViTPose Transformers
β‘Detect and annotate poses in images and videos
-
233
OCR
πimage and video understanding
-
16
OnnxTR OCR
π₯Extract text from documents
-
431
OmniParser V2
π’OmniParser, turn your LLM into GUI agent
-
119
Ovis2 16B
π¦«See, read, and reasonβbetter together.
-
90
Paligemma2 Mix
πGenerate text or segment objects from an image
-
318
Aya Models
πInteract with the Aya family of models.
-
ggml-org/gemma-3-4b-it-GGUF
Image-Text-to-Text β’ Updated β’ 10.5k β’ 25 -
68
Llava Video
πinteract with videos !
-
13
WebGPU MobileNet
πClassify images in real-time using your webcam
-
2
OLMOCR
πOCR for PDFs and Images using Mistral OCR
-
Nasa1423/RolmOCR-Q4_K_M-GGUF
Updated β’ 60 β’ 4 -
reducto/RolmOCR
Image-Text-to-Text β’ Updated β’ 124k β’ 419 -
19
Vanilla Js Object Detector
πUpload image to detect objects
-
56
VisionScout
π°Object Detection & Scene Understanding for Images and Video
-
320
Describe Anything
β‘Generate descriptions from images using masks
-
85
D-Fine - SOTA Real-Time Object Detector
β‘Object Detection on Images and Video
-
137
SmolVLM realtime WebGPU
β‘Describe objects in webcam feed
-
121
Seed1.5 VL
πSeed1.5-VL API Demo
