feat(genai): Multimodal Image Reference Samples Migration to gemini-2.5-flash-image - #10336
Draft
Kef131 wants to merge 5 commits into
Draft
feat(genai): Multimodal Image Reference Samples Migration to gemini-2.5-flash-image#10336Kef131 wants to merge 5 commits into
gemini-2.5-flash-image#10336Kef131 wants to merge 5 commits into
Conversation
- Update ImageGenWithText to use client.models.generateContent with gemini-2.5-flash-image - Update ImageGenerationIT with configurable bucket, safe cleanup, and testImageGenWithText validation - Temporarily ignore remaining deprecated Imagen capability tests pending migration
…5-flash-image - Update Canny, RawReference, Scribble, Style, and Subject reference samples to use client.models.generateContent with multimodal Part inputs - Upload generated image bytes directly to destination GCS bucket URI - Enable and un-ignore all tests in ImageGenerationIT
product-auto-label
Bot
added
the
samples
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Code Review
This pull request updates several image generation Java snippets to migrate from the older Imagen models and edit/generate APIs to the new gemini-2.5-flash-image model using the generateContent API. It also updates the integration tests to reflect these changes and improves the cleanup phase. A review comment suggests optimizing ImageGenWithText.java by writing the raw image bytes directly to the file using Files.write instead of decoding and re-encoding them with ImageIO.
…hText.java Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
… retry in ImageGenerationMmFlashIT
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Description
Fixes #
b/549909475
client.models.editImagetogemini-2.5-flash-imageusingclient.models.generateContentwith multimodalPartinputs:ImageGenCannyCtrlTypeWithTextAndImage.javaImageGenRawReferenceWithTextAndImage.javaImageGenScribbleCtrlTypeWithTextAndImage.javaImageGenStyleReferenceWithTextAndImage.javaImageGenSubjectReferenceWithTextAndImage.javaImageGenerationIT.java, verifying full test suite passes against live Vertex AI.Checklist
Testing
mvn clean verifyrequiredmvn -P lint checkstyle:checkrequiredmvn -P lint clean compile pmd:cpd-check spotbugs:checkadvisory onlyCompliance & Style
pom.xmlparent set to latestshared-configurationPost-Approval Actions