Vertext AI → Media Studio → Imagen 4: Cannot use images as part of a prompt?

[ylluminate]

When I attempt to use Imagen 4, I expect to be able to upload an image to use as part of a prompt as is done in ChatGPT and even other permutations of Google's AI image generation tooling. When I upload an image into the Vertex AI Media Studio I do not see any tooling / options to allow me to use the image that appears upon upload. The only choice I have is to hit the "X" in the upper right. After I do that, I am left without being able to use the image still and the prompt has no context of a sample image I need to use for discussion / generation purposes. Am I missing something or is this a missing feature?:

Eg, I'm back to this:

[ylluminate]

According to the documentation this should work without the above problem: https://cloud.google.com/vertex-ai/generative-ai/docs/image/img-gen-prompt-guide

[marckevin]

Hi @ylluminate,

Welcome to Google Cloud Community!

Since both Imagen 4 Generate Preview 05-20 and Imagen 4 Ultra Generate Experimental 05-20 are still in Preview, some features like image editing including outpainting, inpainting, etc. are not supported yet. Preview features often come with certain limitations and might not provide the full range of quality or functionality available in the final product. It may have bugs or unexpected behaviors. However, you can expect the quality to improve as the feature matures.

It’s possible that uploading photos for image editing or other AI actions is a restricted-access feature in your project. I suggest filling out the allowlist form in this sample documentation to request access to Imagen 3 for Editing and Customization (Imagen 3 Capability 001) which supports image editing.

Was this helpful? If so, please accept this answer as “Solution”. If you need additional assistance, reply here within 2 business days and I’ll be happy to help.