FacesComputer vision

InsightFace

The most widely used open toolkit for face detection and recognition. Many identity-preserving image generators are built on it. The pretrained weights are non-commercial.

Developer
InsightFace (deepinsight), China
First release
Jun 2021
Latest release
Sep 2026
Sizes
packages from 16 MB to 407 MB
License
Non-commercial onlyCode is MIT, but all pretrained weights (buffalo, antelopev2, raccoon) are for non-commercial research only; a commercial license is available on request
Running
On your own serverAlso runs without a GPU
Industries
Security, Retail and marketplaces, Public sector
Deploy on your server GitHub

What it does

  • Detecting and comparing faces in photos
  • Face-based access in prototypes
  • Face processing as part of other AI systems

Where it is used

Research and prototypesSecurity systems (with a commercial license)

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
no versions
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. InsightFace 2.0, пакеты raccoon_s и raccoon_l
  2. InsightFace 1.0 с настольным приложением
  3. Замена лиц inswapper в библиотеке 0.7
  4. Пакеты buffalo_l, buffalo_s, antelopev2

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.

Frequently asked questions

Can InsightFace be used in a commercial project?

No. License: Code is MIT, but all pretrained weights (buffalo, antelopev2, raccoon) are for non-commercial research only; a commercial license is available on request. A commercial product needs a different model or a separate agreement with the rights holder.

What hardware does InsightFace need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Some versions also run on an ordinary CPU, without a GPU. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does InsightFace support Russian?

Language does not matter for this model: it does not work with text.

Where can I download InsightFace and what does it cost?

The InsightFace weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

FacesLVFaceByteDance · ChinaNon-commercial only

Transformer-based face recognition from ByteDance, one of the most accurate open models on benchmarks. Weights are published in ONNX format but are non-commercial.

DetailsComputer visionSigLIP (наследник CLIP)Google · USACommercial use allowed

Models that map images and text into a shared space: you can search photos by words and classify images without training. OpenAI's CLIP (2021) is the predecessor.

Details

Source: github.com/deepinsight/insightface/blob/master/python-package/docs/mod. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.