Support wan2.5

[mose-zm]

Add input.audio_url to support wan2.5 video generation

[gemini-code-assist]

Summary of Changes

Hello @mose-zm, 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 significantly enhances the video synthesis capabilities by integrating audio input. It introduces a dedicated audio_url parameter within the VideoSynthesis functionality, allowing users to provide an audio source alongside other inputs for generating videos, particularly for the wan2.5 model. This addition broadens the scope of video generation to include synchronized audio, making the output more dynamic and complete.

Highlights

• Audio URL Support: Introduced a new audio_url parameter across the VideoSynthesis class methods (call, _get_input, async_call) to enable audio input for video generation, specifically supporting the wan2.5 model.
• Audio Input Processing: The _get_input method now includes logic to process the provided audio_url, handling potential local file uploads before passing the URL to the video synthesis model.
• New Test Case: A new sample file, samples/test_video_synthesis.py, has been added to demonstrate the usage of the audio_url parameter with the wan2.5-t2v-preview model, including a Chinese prompt and an example audio URL.

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 adds support for an audio_url parameter to the video synthesis API, allowing users to provide an audio track for video generation. The changes are applied consistently across both synchronous and asynchronous methods, and a new sample script is added to demonstrate the feature. My review focuses on improving documentation, code maintainability, and adherence to Python best practices in the new sample code.

[gemini-code-assist]

The docstring for audio_url is a bit brief. For better clarity and consistency with other parameters like img_url, consider providing a more descriptive explanation of its purpose. Also, this docstring is missing a period at the end. This feedback also applies to the audio_url docstrings on lines 209, 378, and 432.

Suggested change

	audio_url (str): The input audio url
	audio_url (str): The input audio URL, used for video generation.

[gemini-code-assist]

This logic for handling audio_url is very similar to the logic for other URL-based parameters like img_url, head_frame, etc., leading to code duplication. This can make the code harder to maintain and prone to errors if changes are not applied consistently across all blocks.

To improve maintainability, consider refactoring this repeated logic into a private helper method. For example:

@classmethod
def _maybe_upload_and_set_input(cls, inputs, key, url, model, api_key):
    if not url:
        return False

    is_upload, res_url = check_and_upload_local(model, url, api_key)
    inputs[key] = res_url
    return is_upload

Then you could use it like this:

if cls._maybe_upload_and_set_input(inputs, 'audio_url', audio_url, model, api_key):
    has_upload = True

This would make the _get_input method much cleaner and easier to read. Also, the check if audio_url is not None and audio_url: can be simplified to if audio_url:.

[gemini-code-assist]

For better readability and consistency with modern Python practices, consider using an f-string for string formatting.

Suggested change

	print('response: %s' % rsp)
	print(f'response: {rsp}')

[gemini-code-assist]

For better readability and consistency with modern Python practices, consider using an f-string for string formatting. It also allows you to write this on a single line.

        print(f'sync_call Failed, status_code: {rsp.status_code}, code: {rsp.code}, message: {rsp.message}')

[gemini-code-assist]

It's a standard convention to end files with a single newline character. Please add one here.

    simple_call()