feat(genai): Add new samples for image editing

[katiemn]

Description

Add new samples for image editing with Imagen

[snippet-bot]

Here is the summary of changes.

You are about to add 5 region tags.

• genai/image_generation/imggen_inpainting_insert_with_txt_img.py:19, tag googlegenaisdk_imggen_inpainting_insert_with_txt_img
• genai/image_generation/imggen_inpainting_removal_with_txt_img.py:19, tag googlegenaisdk_imggen_inpainting_removal_with_txt_img
• genai/image_generation/imggen_mask_free_edit_with_txt_img.py:19, tag googlegenaisdk_imggen_mask_free_edit_with_txt_img
• genai/image_generation/imggen_outpainting_with_txt_img.py:19, tag googlegenaisdk_imggen_outpainting_with_txt_img
• genai/image_generation/imggen_product_background_with_txt_img.py:19, tag googlegenaisdk_imggen_product_background_with_txt_img

---

This comment is generated by snippet-bot.
If you find problems with this result, please file an issue at:
https://github.com/googleapis/repo-automation-bots/issues.
To update this comment, add snippet-bot:force-run label or use the checkbox below:

• Refresh this comment

[gemini-code-assist]

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!

Summary of Changes

Hello team,

Gemini (gemini-code-assist) here to provide a summary of this pull request. This PR introduces new sample code demonstrating various image editing capabilities using the Imagen model via the Google GenAI SDK. Specifically, it adds examples for inpainting (both insertion and removal), mask-free editing, outpainting, and product background swapping. The changes include adding the new Python sample files and updating the existing test suite to include tests for these new samples.

Highlights

• New Image Editing Samples: Adds five new Python sample scripts showcasing different image editing modes available with the Imagen model.
• Inpainting Samples: Includes samples for inpainting, demonstrating how to insert new objects into an image and how to remove objects from an image using text prompts and masks.
• Outpainting Sample: Adds a sample for outpainting, showing how to expand an image beyond its original boundaries based on a text prompt and a mask.
• Mask-Free Editing Sample: Provides a sample for general mask-free image editing using a text prompt.
• Product Background Swap Sample: Includes a sample specifically for swapping the background of a product image using a text prompt and a background mask mode.
• Test Coverage: Updates the image generation test suite to include tests for the newly added image editing samples, ensuring their basic functionality.

Changelog

Click here to see the changelog

• genai/image_generation/imggen_inpainting_insert_with_txt_img.py
  • New file added.
  • Contains a sample function edit_inpainting_insert demonstrating image inpainting insertion using EDIT_MODE_INPAINT_INSERTION with raw and mask reference images.
  • Includes example usage in if __name__ == "__main__": block.
• genai/image_generation/imggen_inpainting_removal_with_txt_img.py
  • New file added.
  • Contains a sample function edit_inpainting_removal demonstrating image inpainting removal using EDIT_MODE_INPAINT_REMOVAL with raw and mask reference images.
  • Includes example usage in if __name__ == "__main__": block.
• genai/image_generation/imggen_mask_free_edit_with_txt_img.py
  • New file added.
  • Contains a sample function edit_mask_free demonstrating mask-free image editing using EDIT_MODE_DEFAULT with a raw reference image.
  • Includes example usage in if __name__ == "__main__": block.
• genai/image_generation/imggen_outpainting_with_txt_img.py
  • New file added.
  • Contains a sample function edit_outpainting demonstrating image outpainting using EDIT_MODE_OUTPAINT with raw and user-provided mask reference images.
  • Includes example usage in if __name__ == "__main__": block.
• genai/image_generation/imggen_product_background_with_txt_img.py
  • New file added.
  • Contains a sample function edit_product_background demonstrating product background swap using EDIT_MODE_BGSWAP with raw and background mask reference images.
  • Includes example usage in if __name__ == "__main__": block.
• genai/image_generation/test_image_generation.py
  • Imports added for the new image editing sample files.
  • Removed a global OUTPUT_FILE variable.
  • Added five new test functions (test_img_edit_inpainting_insert, test_img_edit_inpainting_removal, test_img_edit_product_background, test_img_edit_outpainting, test_img_edit_mask_free) to test the new samples.
  • Moved the OUTPUT_FILE variable definition inside the test_img_generation function.

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 in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.

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 issue 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 is currently in preview and 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 to provide feedback.

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 introduces five new Python samples demonstrating various image editing capabilities with the Imagen API, along with corresponding tests. The new sample files are well-structured and clearly illustrate the usage of the google-genai SDK for features like inpainting, outpainting, mask-free editing, and product background replacement. The code is generally clean and easy to understand.

The tests for these new samples have also been added. While the additions are mostly good, there's a minor improvement suggested for the test function signatures. Overall, a good contribution to the examples.

Summary of Findings

• Copyright Year: The copyright year in the new sample files (e.g., imggen_inpainting_insert_with_txt_img.py) is set to 2025. This might be a placeholder or intended, but it's worth noting. This was not commented on directly due to review settings (severity: low).
• Clarity of output_file TODO in Samples: In the new sample functions (e.g., imggen_inpainting_insert_with_txt_img.py line 26-27), the output_file parameter is accepted by the function. However, there's a TODO(developer): Update and un-comment below line # output_file = "output-image.png". This could be slightly confusing as the function already uses the passed parameter. Consider clarifying or removing this TODO if the parameter is the primary way to set the output. This was not commented on directly due to review settings (severity: low).
• Error Handling in Samples: The new sample files do not include explicit error handling for operations like Image.from_file() or API calls (e.g., using try-except blocks). While this keeps the samples concise and is generally acceptable for example code, in production code, robust error handling would be necessary. This was not commented on directly due to review settings (severity: low).
• Direct Access to generated_images[0] in Samples: The samples access image.generated_images[0].image directly (e.g., imggen_inpainting_insert_with_txt_img.py line 49). This assumes the API call is successful and returns at least one image. For production code, checking the generated_images list before accessing elements would be a good practice. This is generally acceptable for example code. This was not commented on directly due to review settings (severity: low).

Merge Readiness

The pull request adds valuable new samples for image editing. The code for the samples themselves is clear and well-implemented. There are a few medium-severity suggestions regarding unused parameters in the new test functions. Addressing these would improve the clarity and maintainability of the test suite. I recommend that these changes be made before merging. As a reviewer, I am not authorized to approve the pull request; please ensure it undergoes further review and approval as per your team's process.