DocScope-R1
🫓
168
cosmos reason1 / docscopeocr / visionocr / captioner relaxed
IMAGE EXPLANATION
-
-
Salesforce/blip-image-captioning-large
Image-to-Text • 0.5B • Updated • 684k • 1.45k -
Qwen Image LoRA DLC
⛵55Qwen Image LoRA's
-
Florence-2 Models
🐠302Florence-2-large / Florence-2-base
-
bartowski/SicariusSicariiStuff_X-Ray_Alpha-GGUF
Image-Text-to-Text • 4B • Updated • 1.46k • 17 -
Multimodal VLM v1.0
⚡32OCR, VQA, Thinking and Object Detection.
-
Ovis2.5 9B
📊176High-accuracy vision & reasoning for complex tasks
-
Super OCRs Demo
🧪38Experiment with small super OCR models here.
-
Qwen3-VL-Outpost
🔥199Qwen3-VL / Qwen2.5-VL Demo
-
mradermacher/UI-Venus-Ground-7B-i1-GGUF
8B • Updated • 98 • 2 -
openbmb/MiniCPM-V-4_5
Image-Text-to-Text • 9B • Updated • 73.3k • 1.06k -
MiniCPM-V-4 5-Demo
💬32Analyze images and videos with detailed reasoning responses
-
p-e-w/gemma-3-12b-it-heretic
Image-Text-to-Text • 12B • Updated • 403 • 41 -
tencent/Youtu-Parsing
Image-Text-to-Text • 3B • Updated • 143 • 37 -
lmstudio-community/Qwen3-Coder-Next-MLX-4bit
80B • Updated • 270k • 7