# LLM Image Actions

You can add an image that is valid input for GPT API questions, that includes public URLs and Base64 encoded images.\
\
In previously, you could choose **LLM Chat Answer** as an **Action Node** for use with the **LLM Gateway**. Now this option has been improved as ‘**LLM Chat Answer 2**’ with an easier setup configuration and the ability to take images as input.

**To Use the LLM Chat Answer 2 Option:**

Select **AI Automation > AI Workflow Studio**.

1. Select **AI Automation > AI Workflow Studio**.
2. Choose **+New Workflow** or open an existing **Workflow**.
3. Drag an **Action** node onto the **Workflow Studio** canvas.
4. Choose **Action Categories** from the **View Actions By** field.

![](https://aisera.gitbook.io/~gitbook/image?url=https%3A%2F%2F2983236984-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FiZkLJr3EjXkd2tHYiQJP%252Fuploads%252FkVWMo8nmX5T1zPgS2aMA%252Fimage.png%3Falt%3Dmedia%26token%3Dd6df1c7d-0c63-4a0d-8971-1b82cc0a2c47\&width=768\&dpr=4\&quality=100\&sign=635794b9\&sv=1)

5\. Specify your input parameters and variables in the **Edit Action Node** window.

![](https://aisera.gitbook.io/~gitbook/image?url=https%3A%2F%2F2983236984-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FiZkLJr3EjXkd2tHYiQJP%252Fuploads%252FTzEOoIt3HkkZO0u2307L%252Fimage.png%3Falt%3Dmedia%26token%3Dfae24e84-4a47-4324-95fa-0112d77ba9da\&width=768\&dpr=4\&quality=100\&sign=baec9c71\&sv=1)