[Yandex Cloud documentation](../../../index.md) > [Yandex Cloud Stackland](../../index.md) > [Step-by-step guides](../index.md) > AI Studio > Enabling AI Studio

# Activate AI Studio

To use [AI Studio](../../concepts/components/ai-studio.md), enable Object Storage, Model Gallery, and Agent Atelier.

## Getting started {#before-you-begin}

1. Make sure the Model Gallery and Agent Atelier images are available in the registry used by the cluster. If the required images are not in the local registry, [upload them](install-images.md).
1. Make sure the cluster meets the [infrastructure requirements](../../concepts/components/ai-studio.md#infrastructure) for the selected models.
1. Make sure [NVIDIA® GPU support is enabled](../../concepts/components/gpu.md#enable) for the GPU worker nodes when deploying the cluster. Wait until NVIDIA® GPU support is ready.
1. Make sure [AI Studio dependencies](../../concepts/components/ai-studio.md#dependencies) are enabled. If Object Storage is disabled, enable it in the existing `StorageConfig` resource:

   ```bash
   kubectl patch storageconfig main --type=merge -p '{"spec":{"enabled":true}}'
   ```

   Wait for the storage to get ready. Check the installation status using the `kubectl get componentinstallation storage-main` command: the `PHASE` field should turn `Ready`.

## Enabling Model Gallery {#enable-model-gallery}

{% note info %}

Model Gallery installation may take more than an hour due to the large size of the model images. Consider this when planning the installation and wait until Model Gallery is ready before enabling Agent Atelier:

{% endnote %}

1. Save [this configuration example](../../concepts/components/ai-studio.md#model-gallery-configuration) to the `modelgalleryconfig.yaml` file.
1. Configure the models and resources. The example includes Embeddings, Ethics, and YandexGPT 5 Lite, which require one A100 80 GB and two H100 80 GB GPUs. Before enabling other models, make sure additional GPUs, CPUs, RAM, and disk space are available.
1. Compare the `nodeSelector` values with the cluster node labels:

   ```bash
   kubectl get nodes -L nvidia.com/gpu.product
   ```

1. Apply the manifest:

   ```bash
   kubectl apply -f modelgalleryconfig.yaml
   ```

1. Check the installation status:

   ```bash
   kubectl get componentinstallation model-gallery-main
   ```

   Wait for the `PHASE` field to turn `Ready`. If an error occurs, check the `MESSAGE` field in the command output.

## Enabling Agent Atelier {#enable-agent-atelier}

1. Save [this configuration example](../../concepts/components/ai-studio.md#agent-atelier-configuration) to the `agentatelierconfig.yaml` file.
1. If you do not need Code Interpreter, set `spec.settings.codeInterpreter.enabled: false`. To use it, make sure Certificate Manager is on and allocate [resources for sessions](../../concepts/components/ai-studio.md#code-interpreter-resources).
1. Apply the manifest:

   ```bash
   kubectl apply -f agentatelierconfig.yaml
   ```

1. Check the installation status:

   ```bash
   kubectl get componentinstallation agent-atelier-main
   ```

   Wait for the `PHASE` installation field to turn `Ready`.

## Opening the web UI {#open-ui}

Once the installation is complete, the AI Studio web UI will be available at `https://aistudio.sys.<cluster_domain>`. Use the Identity and Access Management credentials to log in.

## Updating settings {#configure}

To change the models, resources, or Code Interpreter settings, edit the relevant resource:

```bash
kubectl edit modelgalleryconfig main
kubectl edit agentatelierconfig main
```

For descriptions of settings, see [Configuration](../../concepts/components/ai-studio.md#configuration).

## What's next {#whats-next}

* [Disabling AI Studio](disable.md)
* [AI Studio](../../concepts/components/ai-studio.md)