Hugging Face’s cover photo
Hugging Face

Hugging Face

Software Development

The AI community building the future.

About us

The AI community building the future.

Website
https://huggingface.co
Industry
Software Development
Company size
51-200 employees
Type
Privately Held
Founded
2016
Specialties
machine learning, natural language processing, and deep learning

Products

Locations

Employees at Hugging Face

Updates

  • You may have heard about Segment Anything or Depth Anything. Now there’s also Match Anything, available in the Transformers library. Read more below:

    View profile for Niels Rogge

    Machine Learning Engineer at ML6 & Hugging Face

    Exciting model addition to Hugging Face Transformers: MatchAnything is now available! 🔥 MatchAnything is a strong universal image matching model, pre-trained on a large scale involving different imaging modalities. This allows it to exhibit remarkable generalizability on unseen multi-modality matching and registration tasks. Image matching has many applications, like image stitching (think about the "panorama" feature in your phone), merging satellite images to be displayed on Google Earth or Street View, stichting together medical images from a scan, etc. The key contribution of the MatchAnything paper is the pre-training framework. The authors collect a massive, diverse dataset synthesized with cross-modal stimulus signals. This includes multi-view images with 3D reconstructions, large-scale unlabelled video sequences, and vast single-image datasets. Furthermore, synthetic data is used via image generation techniques (like style transfer and depth estimation). Collecting such diverse data teaches the model to recognize fundamental, appearance-insensitive structures. The authors applied their framework to train 2 popular image matching models: EfficientLofTR and ROMA. EfficientLofTR was recently integrated in the Transformers library, hence the weights which the MatchAnything authors released are now available. The model is Apache 2.0 licensed, which means you can adopt it for commercial purposes too! Big kudos to Steven Bucaille for making image matching models easier accessible to the community. Resources: - model: https://lnkd.in/eba9Fukx - docs: https://lnkd.in/eba9Fukx - demo: https://lnkd.in/ekruNM7W

  • Hugging Face reposted this

    View profile for Ben Burtenshaw

    Machine Learning @ 🤗 Hugging Face

    DeepSeek-V3.1 is fully ready to integrate in your apps and projects, using Hugging Face Inference Providers, Powered by Fireworks AI! Main improvements are: - Hybrid thinking mode: One model supports both thinking mode and non-thinking mode by changing the chat template. - Smarter tool calling: Through post-training optimization, the model's performance in tool usage and agent tasks has significantly improved. - Higher thinking efficiency: DeepSeek-V3.1-Think achieves comparable answer quality to DeepSeek-R1-0528, while responding more quickly. OpenAI API compatible, so you can just swap it out like in the snippet in comments.

  • Hugging Face reposted this

    View profile for Sayak Paul

    ML @ Hugging Face 🤗

    New Diffusers release is out. Really great to see the state of things in image edits, video fidelity being pushed further and further, thanks to the community! This release also features new fine-tuning scripts for Qwen-Image and Flux Kontext (with support for image inputs). So, get busy making these models your own 🤗 We also improved the loading speed of Diffusers pipelines and models. This will become particularly evident when operating with large models like Wan, Qwen, etc. As always, don't forget to check out the release notes for the full disclosure. I will leave the link in the comments.

    • No alternative text description for this image
  • Hugging Face reposted this

    View profile for Sayak Paul

    ML @ Hugging Face 🤗

    New Diffusers release is out. Really great to see the state of things in image edits, video fidelity being pushed further and further, thanks to the community! This release also features new fine-tuning scripts for Qwen-Image and Flux Kontext (with support for image inputs). So, get busy making these models your own 🤗 We also improved the loading speed of Diffusers pipelines and models. This will become particularly evident when operating with large models like Wan, Qwen, etc. As always, don't forget to check out the release notes for the full disclosure. I will leave the link in the comments.

    • No alternative text description for this image
  • Hugging Face reposted this

    View profile for Yoni Gozlan

    ML Engineer @Hugging Face 🤗

    🚀 Better late than never, SAM2 is now available in Hugging Face 🤗 Transformers! introduced by Meta FAIR, Segment Anything Model 2 (SAM2) is the natural evolution of the first SAM: extending promptable segmentation from static images into the video domain. With its streaming memory architecture, SAM2 can track and refine object masks across long videos in real time, making it one of the most powerful models for interactive and automatic video segmentation. The model builds a memory bank of past frames and prompts, encoding both spatial features and compact “object pointer” tokens that summarize the target. Each new frame is then processed in relation to this memory through attention, letting SAM2 recall what the object looked like and where it was last observed. Combined with an explicit occlusion prediction head, this design allows SAM2 to keep track of objects robustly and to recover them with minimal user input after partial or full occlusion. Many thanks to the team at Meta FAIR for developing and releasing such a foundational model for vision. I am happy to have worked on bringing SAM2 into Transformers together with Daniel Choi, making it easier than ever for the open-source community to use. 👉 Try SAM2 video tracking directly in this Hugging Face Space (the demo video below was made with it!): https://lnkd.in/e-UR8t_N * 🤗 SAM2.1 Large checkpoint: https://lnkd.in/eEQ_YyVT * 🤗 Transformers docs (SAM2): https://lnkd.in/eZ2gAUfh * 🤗 Transformers docs (SAM2 Video): https://lnkd.in/e3vuJxjM

Similar pages

Browse jobs

Funding

Hugging Face 8 total rounds

Last Round

Series unknown
See more info on crunchbase