Image Studio

Start with an idea. Turn it into an image, then shape the details until it fits your purpose. In this chapter, we will create a campaign illustration for our fictional Willow Cafe, revise two areas, compare versions, and download the result. This demonstration uses the web app on a desktop computer.

In Studio, choose Images, then Generate. Write the brief in the Prompt field. You can start independently with an idea; you do not need a recorded conversation. In this example, the open session is not automatically included, so the prompt supplies the background.

Describe the subject, the mood, and where the picture will be used. Our brief asks for a coffee cup, a small plant, and soft morning light. We specify an editorial illustration in cream and forest green. We also ask for the objects on the right and clear space on the left, ready for a headline added later. These composition details help make the result useful.

Below the prompt, check the provider and model. We are using Google Gemini with Nano Banana Two, Flash. Available options can vary. Choose an aspect ratio that fits the destination. Here, Slides, sixteen by nine, gives us a wide composition. We select two K for image size. Check the allowance shown in your account before generating.

Choose Generate and follow the progress. The app takes time to create and save the image. We have shortened the waiting in this lesson. Once the result is ready, open it to review the actual output.

Here is our first version. The coffee cup and plant sit on the right, with room for a headline on the left. The details on the right record the prompt, model and source. This one is a freeform image, with no conversation context attached. Check the composition before deciding what to change.

Give the image a recognizable name using Rename. We call this Willow Cafe, opening campaign. That makes the work easier to find when the collection grows.

Now choose Revise. Instead of starting the brief again, work from the existing picture. Think about what you want to change and what should remain. A specific instruction gives the next version a clearer direction.

Drag a rectangle over the area you want to change. We select a clear part of the tabletop. The comment asks what should change here.

Ask for a small golden croissant on a cream ceramic plate, while keeping the coffee cup and plant. Choose Done to keep this instruction with its marked area.

Mark a second area around the outdoor view. This time, ask for soft, uncluttered greenery and keep the wooden window frame. Each area gets its own instruction, so the two changes remain easy to review.

The current edits appear as a numbered list. Review them before submitting. The controls beside each entry let you edit or remove that area. Zoom controls help you inspect the picture more closely while you work.

For a change across the whole picture, use the whole-image note. We ask for slightly warmer morning light, while preserving the clear headline space and the welcoming illustration style. This is separate from the two marked areas.

Check the generation settings again. In this recording, the revision form started at a smaller image size, so we select two K again. Do not assume a new revision has kept every earlier setting.

Apply the three edits: two marked areas and one overall instruction. Let the revision finish. Again, the waiting is shortened here.

The revised image now includes the croissant, a simpler outdoor view, and warmer light. Review the entire picture, including details outside the marked regions. AI revisions can change more than the exact area you selected.

Use the version buttons to return to the original. Compare the composition and the details you wanted to preserve.

Then select version two to see the revision again. Before another revision or a download, check which version is selected.

Return to the collection to find your saved work. A clear title helps you recognize it. The search field narrows the images already loaded, and the sort control changes their order. Here, we choose Title. Open the image to continue where you left off.

Download the selected version. Our actual download is a Web P image. Open the file and check the details at the size you plan to use.

From a clear brief to a finished visual: generate, mark changes, add overall direction, compare versions, and keep the result you want. Return to your image collection whenever the next idea is ready.