🤖 models

• AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining

  •  [](https://huggingface.co/spaces/haoheliu/audioldm2-text2audio-text2music)

• BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models

  •  [](https://huggingface.co/Salesforce/blip2-opt-6.7b) [](https://colab.research.google.com/github/salesforce/LAVIS/blob/main/examples/blip2_instructed_generation.ipynb)

• OWL-ViT: Simple Open-Vocabulary Object Detection with Vision Transformers

  • ](https://huggingface.co/spaces/adirik/OWL-ViT) [](https://huggingface.co/google/owlvit-base-patch32)

• Depth Anything

  • ](https://huggingface.co/spaces/LiheYoung/Depth-Anything) [](https://huggingface.co/LiheYoung/depth_anything_vitl14) [](https://colab.research.google.com/github/NielsRogge/Transformers-Tutorials/blob/master/Depth%20Anything/Predicting_depth_in_an_image_with_Depth_Anything.ipynb)

• EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything

  •  [](https://huggingface.co/merve/EfficientSAM)

• ImageBind: One Embedding Space To Bind Them All

  • 

• LLaVA: Large Language and Vision Assistant

  • ](https://huggingface.co/spaces/badayvedat/LLaVA) [](https://huggingface.co/liuhaotian/llava-v1.6-34b)

• CLIP: Learning Transferable Visual Models From Natural Language Supervision

  •  [](https://colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/how-to-use-openai-clip-classification.ipynb)

• CogVLM: Visual Expert for Pretrained Language Models

  •  [](https://huggingface.co/THUDM/CogVLM)

• Fuyu-8B: A Multimodal Architecture for AI Agents

  • ](https://huggingface.co/adept/fuyu-8b)

• Ferret: Refer and Ground Anything Anywhere at Any Granularity

  • ![arXiv - ferret)

• OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models

  •  [](https://huggingface.co/openflamingo/OpenFlamingo-9B-vitl-mpt7b)

• Segment Anything

  • ](https://youtu.be/D-D6ZmadzPE) [](https://huggingface.co/spaces/radames/candle-segment-anything-wasm) [](https://huggingface.co/facebook/sam-vit-base) [](https://colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/how-to-segment-anything-with-sam.ipynb)

• Whisper: Robust Speech Recognition via Large-Scale Weak Supervision

  •  [](https://huggingface.co/openai/whisper-large-v3) [](https://colab.research.google.com/github/openai/whisper/blob/master/notebooks/LibriSpeech.ipynb)

• SigLIP: Sigmoid Loss for Language Image Pre-Training

  • ](https://huggingface.co/spaces/merve/compare_clip_siglip) [](https://huggingface.co/openai/clip-vit-base-patch16) [](https://colab.research.google.com/github/NielsRogge/Transformers-Tutorials/blob/master/SigLIP/Inference_with_(multilingual)_SigLIP%2C_a_better_CLIP_model.ipynb)

• YOLO-World: Real-Time Open-Vocabulary Object Detection

  • ](https://youtu.be/X7gKBGVz4vs) [](https://huggingface.co/spaces/SkalskiP/YOLO-World) [](https://colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/zero-shot-object-detection-with-yolo-world.ipynb)

• MetaCLIP: Demystifying CLIP Data

  •  [](https://huggingface.co/facebook/metaclip-b32-400m) [](https://colab.research.google.com/drive/1V0Rv1QQJkcolTjiwJuRsqWycROvYjOwg?usp=sharing)

• Nougat: Neural Optical Understanding for Academic Documents

  •  [](https://huggingface.co/facebook/nougat-small) [](https://colab.research.google.com/github/NielsRogge/Transformers-Tutorials/blob/master/Nougat/Inference_with_Nougat_to_read_scientific_PDFs.ipynb)

• Kosmos-2: Grounding Multimodal Large Language Models to the World

  • ](https://huggingface.co/spaces/ydshieh/Kosmos-2) [](https://huggingface.co/microsoft/kosmos-2-patch14-224)

• OWLv2: Scaling Open-Vocabulary Object Detection

  • ](https://huggingface.co/spaces/merve/owlv2) [](https://huggingface.co/google/owlv2-base-patch16-ensemble) [](https://colab.research.google.com/github/NielsRogge/Transformers-Tutorials/blob/master/OWLv2/Zero_and_one_shot_object_detection_with_OWLv2.ipynb)

• Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection

  • ](https://youtu.be/cMa77r3YrDk) [](https://huggingface.co/spaces/ShilongLiu/Grounding_DINO_demo) [](https://huggingface.co/spaces/merve/Grounding_DINO_demo) [](https://colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/zero-shot-object-detection-with-grounding-dino.ipynb)

• Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

  • ](https://huggingface.co/spaces/Qwen/Qwen-VL-Max) [](https://huggingface.co/Qwen/Qwen-VL)