moondream2
🌔
442
a tiny vision language model
Images to Text
-
-
Candle Moondream 2
🕯37MoonDream 2 Vision Model on the Browser: Candle/Rust/WASM
-
Idefics 8b
🐠146Generate text from images and prompts
-
Stable Diffusion XL on TPUv5e
🏋2.04kGenerate images from text prompts
-
Llava Llama-3 8B
🔥88Meta Llama3 8b with Llava Multimodal capabilities
-
Paligemma HF
🤗85Generate text and segment images using PaliGemma
-
Llava Next
🔥150Ask questions about images
-
Microsoft Phi-3-Vision-128k
😻219Chat with an image using Phi-3 Vision model
-
Microsoft Phi-3 Vision 128k
🔥46Microsoft Phi-3 Vision 128k with Multimodal capabilities
-
Contemplative moondream
🌜51let's talk about the meaning of life
-
Gradio Lite
🖼3Convert images to grayscale
-
Florence 2
📉833Perform image captioning, detection, OCR and more with Florence‑2
-
SD3 Long Captioner
🏃259Generate detailed captions for any image
-
Florence 2 SD3 Captioner
⚡37Generate detailed image captions
-
Better Florence 2
🔥198Analyze images to detect objects, generate captions, or perform OCR
-
LLaVA WebGPU
🌋20A private and powerful multimodal AI chatbot that runs local
-
AuraFlow-v0.3 with Captioner
🖼90Generate images from prompts or images
-
Idefics3
📊102Generate text based on an image and prompt
-
Phi 3.5 Vision
👁31Ask questions about images
-
Phi 3.5 Vision
🔥224Generate answers to questions about any image
-
Tonic's GOT OCR
📲179GOT - OCR (from : UCAS, Beijing)
-
Llama-Vision-11B
🚀390Chat with Llama about images and text
-
JanusFlow 1.3B
🏃218Huggingface space for JanusFlow-1.3B
-
SmolVLM
📊144Generate text from images and queries
-
SD3 Long Captioner
🏃1Generate captions for images