fix qwen image max rope index to 10000 #139
Conversation
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Summary of Changes
Hello @akaitsuki-ii, 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!
I've implemented a fix for the Qwen image model by adjusting the maximum index for its Rotary Positional Embeddings (RoPE). This change expands the range of positional indices, which should resolve issues related to out-of-bounds errors or limitations when processing larger inputs within the model.
Highlights
- Qwen Image Model Fix: Increased the
pos_indexandneg_indexrange for Rotary Positional Embeddings (RoPE) from 1024 to 10000 indiffsynth_engine/models/qwen_image/qwen_image_dit.py. This change likely addresses an issue where the previous index limit was insufficient for certain inputs, potentially causing errors or incorrect behavior.
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 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 or fill out our survey 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
-
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.
Code Review
This pull request increases the maximum rope index for Qwen image models from 1024 to 10000, which should allow for handling longer sequences. The change is straightforward. My main feedback is to replace the hardcoded value 10000 with a named constant to improve code readability and maintainability.
| pos_index = torch.arange(10000) | ||
| neg_index = torch.arange(10000).flip(0) * -1 - 1 |
There was a problem hiding this comment.
The value 10000 is used as a magic number in two places. To improve readability and maintainability, it would be better to define it as a named constant at the module or class level. This makes the purpose of the number clear and simplifies future modifications.
For example:
# At module level
MAX_ROPE_INDEX = 10000
# In __init__
pos_index = torch.arange(MAX_ROPE_INDEX)
neg_index = torch.arange(MAX_ROPE_INDEX).flip(0) * -1 - 1
No description provided.