diff --git a/CHANGELOG.md b/CHANGELOG.md
index 9fc9896..131e86e 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -11,6 +11,7 @@ All notable changes to Pixano will be documented in this file.
### Changed
+- Update README with a small header description listing main features and more detailed installation instructions
- Generate API reference automatically
- Update documentation website accent color to complementary color of the Pixano main accent color
- Add cross-references to Pixano, TensorFlow, and Hugging Face Transformers in the API reference of the documentation website
diff --git a/README.md b/README.md
index d691e09..2a2dd72 100644
--- a/README.md
+++ b/README.md
@@ -4,9 +4,7 @@
-**Inference models for Pixano,**
-
-**Data-centric AI building blocks for computer vision applications**
+**Inference models for Pixano**
**_Under active development, subject to API change_**
@@ -17,15 +15,36 @@
-# Installing Pixano Inference
+
+
+Pixano is an open-source tool by CEA List for exploring and annotating your dataset using AI features like **smart segmentation** and **semantic search**.
+
+This library provides the AI models like _SAM_ and _CLIP_ that power those features, as well as a PyTorch and TensorFlow models for pre-annotating your datasets.
+
+# Getting started
+
+## Installing Pixano Inference
+
+As Pixano and Pixano Inference require specific versions for their dependencies, we recommend creating a new Python virtual environment to install them.
+
+For example, with conda:
+
+```shell
+conda create -n pixano_env python=3.10
+conda activate pixano_env
+```
+
+Then, you can install Pixano Inference inside that environment with pip:
```shell
pip install pixano-inference@git+https://github.com/pixano/pixano-inference
```
-# Using Pixano Inference
+As it is a requirement of Pixano Inference, Pixano will automatically be downloaded if it is not already installed.
+
+## Using the models
-Please refer to [these Pixano notebooks](https://github.com/pixano/pixano/tree/main/notebooks/models) for information on how to use the inference models provided by this module.
+Please refer to these notebooks for information on how to use the models provided by Pixano Inference.
# Contributing