feat: nano banana pro model

[katiemn]

Description

Update image samples to use Nano Banana Pro

[gemini-code-assist]

Summary of Changes

Hello @katiemn, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request focuses on updating the image generation sample code to align with the latest model offerings. By migrating the samples to use the gemini-3-pro-image-preview model, it ensures that the examples are current and functional with the most recent API. Additionally, the changes include minor code cleanup by removing obsolete comments and simplifying model configuration where applicable.

Highlights

• Model Update: All image generation sample files have been updated to use the gemini-3-pro-image-preview model, replacing the older gemini-2.5-flash-image.
• Code Cleanup: Outdated example response comments have been removed from all modified sample files, streamlining the code.
• Configuration Simplification: In imggen_mmflash_with_txt.py, the candidate_count and safety_settings parameters were removed from the GenerateContentConfig for a cleaner configuration.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Summary of Changes

Hello @katiemn, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request upgrades the image generation examples to leverage a newer, more advanced model, gemini-3-pro-image-preview. It also includes minor code cleanup by removing obsolete example comments and simplifying model configuration in one of the samples, ensuring the examples are current and concise.

Highlights

• Model Update: The image generation samples have been updated to use the gemini-3-pro-image-preview model, replacing the older gemini-2.5-flash-image model.
• Code Cleanup: Outdated example response comments have been removed from all modified files, improving code readability.
• Configuration Simplification: Redundant candidate_count and safety_settings configurations were removed from the imggen_mmflash_with_txt.py sample, streamlining the model call.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request updates several image generation examples to use the gemini-3-pro-image-preview model, replacing gemini-2.5-flash-image. The changes also include removing some commented-out example responses and, in one case, removing generation configuration parameters. My review focuses on the implications of these changes. While updating the model and cleaning up comments is fine, I've raised a concern about the removal of safety_settings in imggen_mmflash_with_txt.py. Relying on default safety settings can be risky as they might change unexpectedly. I've recommended re-introducing explicit, valid safety settings to ensure predictable and safe behavior. Overall, the changes are straightforward, but addressing the safety settings would improve the robustness of the example code.

[gemini-code-assist]

Code Review

This pull request updates several image generation examples to use a new model, gemini-3-pro-image-preview, and removes some commented-out code. My review found one significant issue: the removal of safety_settings in one of the files. This is a potential security and safety concern, as it could lead to the generation of inappropriate content. I have provided a comment with a suggestion to restore the safety configuration.