-
Notifications
You must be signed in to change notification settings - Fork 6.5k
feat(genai): video model version update #13383
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
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! Gemini or gemini-code-assist here to provide a summary of this pull request. This PR, authored by katiemn, is focused on updating the version of the video generation model used in the provided code examples. Specifically, it updates the model string from veo-2.0-generate-001
to veo-3.0-generate-preview
in two Python files demonstrating video generation from images and text.
Highlights
- Model Version Update: The core change in this PR is updating the model name used for video generation from an older version (
veo-2.0-generate-001
) to a newer preview version (veo-3.0-generate-preview
). - Code Examples Updated: The update is applied to two Python sample files: one for generating video from an image and another for generating video from text.
Changelog
- genai/video_generation/videogen_with_img.py
- Updated the video generation model name from
veo-2.0-generate-001
toveo-3.0-generate-preview
on line 28.
- Updated the video generation model name from
- genai/video_generation/videogen_with_txt.py
- Updated the video generation model name from
veo-2.0-generate-001
toveo-3.0-generate-preview
on line 28.
- Updated the video generation model name from
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.
Models change and grow,
New versions come and go,
Update the string,
Make the code sing,
Let the video flow.
Footnotes
-
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. ↩
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Code Review
This pull request updates the video generation model from veo-2.0-generate-001
to veo-3.0-generate-preview
in two files. This is a straightforward change, but there are a couple of points to consider for robustness and maintainability, primarily concerning the validation of the new model version and how the model identifier is managed in the code.
Summary of Findings
- Model Version Validation: Critical confirmation is needed for the new model identifier
"veo-3.0-generate-preview"
to ensure its validity, and to understand any associated API changes, output differences, or performance/cost implications. Adding documentation links to the PR description is recommended. - Hardcoded Model Identifier: The model identifier
"veo-3.0-generate-preview"
is hardcoded in two files. Defining this as a constant at the module level or in a shared configuration file would improve maintainability and consistency.
Merge Readiness
Before this pull request is merged, I recommend addressing the high
severity concern regarding the validation of the new model version (veo-3.0-generate-preview
). Please provide confirmation of its correctness and any associated implications, and consider adding relevant documentation links to the PR description. The suggestions for using a constant for the model ID are for improved maintainability and can be addressed as well.
I am not authorized to approve pull requests, but based on this review, changes are requested before it should be considered ready for merge by the maintainers.
Description
Veo model version update