DocScope-R1
🖤
168
Cosmos-R1 / docscopeOCR / Captioner-7B / visionOCR-3B
IMAGE EXPLANATION
-
-
Salesforce/blip-image-captioning-large
Image-to-Text • 0.5B • Updated • 712k • 1.48k -
Qwen Image LoRA DLC
⛵54Qwen Image LoRA's
-
Florence-2 Models
🐠308Florence-2-large / Florence-2-base
-
bartowski/SicariusSicariiStuff_X-Ray_Alpha-GGUF
Image-Text-to-Text • 4B • Updated • 2.52k • 18 -
Multimodal VLM v1.0
⚡33OCR, VQA, Thinking and Object Detection.
-
Ovis2.5 9B
📊178High-accuracy vision & reasoning for complex tasks
-
Super OCRs Demo
🧪42Experiment with small super OCR models here.
-
Qwen3-VL-Outpost
🔥208Demo of a collection of Qwen3-VL models
-
mradermacher/UI-Venus-Ground-7B-i1-GGUF
8B • Updated • 47 • 2 -
openbmb/MiniCPM-V-4_5
Image-Text-to-Text • 9B • Updated • 85.6k • 1.09k -
MiniCPM-V-4 5-Demo
💬37Answer questions about images and videos
-
p-e-w/gemma-3-12b-it-heretic
Image-Text-to-Text • 12B • Updated • 503 • • 89 -
tencent/Youtu-Parsing
Image-Text-to-Text • 3B • Updated • 2.22k • 39 -
lmstudio-community/Qwen3-Coder-Next-MLX-4bit
80B • Updated • 188k • 23 -
Joy Caption Beta One
🖼1.09kGenerate custom captions, tags, or prompts for any image
-
mradermacher/Qwen2.5-VL-7B-Abliterated-Caption-it-GGUF
Image-to-Text • 8B • Updated • 6.94k • 73 -
Qwen/Qwen3.5-27B
Image-Text-to-Text • 28B • Updated • 2.56M • • 997 -
Open ASR Leaderboard
🏆1.39kCompare speech recognition models on benchmark scores