Qwen/Qwen2.5-Omni-7B
Any-to-Any • Updated
• 361k • 1.87k
Vision Language Models: 2025 Update
This collection includes all the models, datasets and Spaces mentioned in the blog Vision Language Models: 2025 Update
-
-
Qwen2.5 Omni 7B Demo
🏆366Chat with AI using text, audio, images, and video
-
Qwen2.5-Omni Technical Report
Paper • 2503.20215 • Published • 170 -
openbmb/MiniCPM-o-2_6
Any-to-Any • Updated • 106k • 1.28k -
deepseek-ai/Janus-Pro-7B
Any-to-Any • Updated • 28k • 3.57k -
Chat With Janus-Pro-7B
🌍2.02kA unified multimodal understanding and generation model.
-
Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling
Paper • 2501.17811 • Published • 8 -
Qwen/QVQ-72B-Preview
Image-Text-to-Text • 73B • Updated • 418 • 609 -
moonshotai/Kimi-VL-A3B-Thinking
Image-Text-to-Text • 16B • Updated • 75.8k • 446 -
Chat with Kimi-VL-A3B-Thinking-2506
🤔194Chat with Kimi-VL: respond to text, images, video, PDFs
-
Kimi-VL Technical Report
Paper • 2504.07491 • Published • 137 -
moonshotai/MoonViT-SO-400M
Image Feature Extraction • 0.4B • Updated • 933 • 36 -
google/siglip-so400m-patch14-384
Zero-Shot Image Classification • 0.9B • Updated • 1.99M • 654 -
moonshotai/Kimi-VL-A3B-Instruct
Image-Text-to-Text • 16B • Updated • 179k • 256 -
HuggingFaceTB/SmolVLM-Instruct
Image-Text-to-Text • 2B • Updated • 51.9k • 577 -
SmolVLM
📊144Generate text from images and queries
-
HuggingFaceTB/SmolVLM2-2.2B-Instruct
Image-Text-to-Text • Updated • 120k • 303 -
SmolVLM: Redefining small and efficient multimodal models
Paper • 2504.05299 • Published • 205 -
SmolVLM
📊81Generate answers by combining text and images
-
google/gemma-3-27b-it
Image-Text-to-Text • Updated • 1.66M • • 1.9k -
unsloth/gemma-3-27b-it-GGUF
Image-Text-to-Text • 27B • Updated • 167k • 188 -
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 10k • 380 -
meta-llama/Llama-4-Scout-17B-16E-Instruct
Image-Text-to-Text • Updated • 200k • • 1.22k -
meta-llama/Llama-4-Maverick-17B-128E-Instruct
Image-Text-to-Text • Updated • 9.36k • • 465 -
MoE-LLaVA: Mixture of Experts for Large Vision-Language Models
Paper • 2401.15947 • Published • 53 -
deepseek-ai/deepseek-vl2
Image-Text-to-Text • Updated • 4.27k • 380 -
Chat with DeepSeek-VL2-small
🌍587Chat with images and text using AI assistant
-
DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding
Paper • 2412.10302 • Published • 22 -
lerobot/pi0_old
Robotics • 4B • Updated • 650 • 307 -
nvidia/GR00T-N1-2B
Robotics • 2B • Updated • 244 • 348 -
google/paligemma-3b-pt-224
Image-Text-to-Text • Updated • 42.7k • 415 -
PaliGemma: A versatile 3B VLM for transfer
Paper • 2407.07726 • Published • 72 -
PaliGemma Demo
🤲314Annotate and describe images with text prompts
-
PaliGemma 2: A Family of Versatile VLMs for Transfer
Paper • 2412.03555 • Published • 133 -
Paligemma2 Mix
🌖96Generate text and segment images using PaliGemma 2
-
google/paligemma2-10b-mix-448
Image-Text-to-Text • Updated • 1.19k • 35 -
allenai/Molmo-72B-0924
Image-Text-to-Text • 73B • Updated • 6.69k • 296 -
Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Multimodal Models
Paper • 2409.17146 • Published • 121 -
Qwen/Qwen2.5-VL-72B-Instruct
Image-Text-to-Text • Updated • 264k • • 596 -
Qwen2.5-VL Technical Report
Paper • 2502.13923 • Published • 213 -
google/shieldgemma-2-4b-it
Image-Text-to-Text • Updated • 8.1k • 147 -
ShieldGemma 2: Robust and Tractable Image Content Moderation
Paper • 2504.01081 • Published • 3 -
ShieldGemma2 VLM
📉12Demo for ShieldGemma 2, multimodal safety model
-
meta-llama/Llama-Guard-4-12B
Image-Text-to-Text • Updated • 226k • • 81 -
Llama Guard 4
🦀1Check if text and images are safe
-
marco/mcdse-2b-v1
2B • Updated • 2.79k • 56 -
vidore/colpali-v1.3
Visual Document Retrieval • Updated • 34.8k • 88 -
ColPali: Efficient Document Retrieval with Vision Language Models
Paper • 2407.01449 • Published • 51 -
vidore/colqwen2.5-v0.2
Visual Document Retrieval • Updated • 27.4k • 96 -
vidore/colsmolvlm-v0.1
Visual Document Retrieval • Updated • 136 • 55 -
Qwen/Qwen2.5-VL-32B-Instruct
Image-Text-to-Text • Updated • 184k • • 476 -
Qwen2.5 VL 32B Instruct Demo
🏃164Chat with a multimodal AI using text, images, or video
-
Vision-CAIR/LongVU_Qwen2_7B
Video-Text-to-Text • 8B • Updated • 141 • 74 -
LongVU
🌖87Generate responses to video or image inputs
-
openbmb/RLAIF-V-Dataset
Preview • Updated • 814 • 206 -
HuggingFaceH4/rlaif-v_formatted
Viewer • Updated • 83.1k • 1.05k • 16 -
MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGI
Paper • 2404.16006 • Published • 2 -
Kaining/MMT-Bench
Viewer • Updated • 30k • 43 • 10 -
MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark
Paper • 2409.02813 • Published • 33 -
MMMU/MMMU_Pro
Viewer • Updated • 5.19k • 6.55k • 45 -
reducto/RolmOCR
Image-Text-to-Text • Updated • 2.53k • 581 -
Alpha-VLLM/Lumina-mGPT-7B-768
Any-to-Any • 7B • Updated • 6.39k • 38 -
facebook/chameleon-7b
Image-Text-to-Text • 7B • Updated • 54.7k • 196