Skip to content

Conversation

@mohnjiles
Copy link
Contributor

Added

Changed

  • Moved the original Stable Diffusion WebUI Forge to the "Legacy" packages tab due to inactivity
  • Updated to cu130 torch index for ComfyUI installs with Nvidia GPUs
  • Consolidated and fixed AMD GPU architecture detection
  • Updated SageAttention installer to latest v2.2.0-windows.post4 version
  • Updated torch index for Forge-based UIs to rocm6.4 / cu128 depending on GPU - thanks to @NeuralFault!

Fixed

🌟 Visionaries

To our incredible Visionaries: Waterclouds, JungleDragon, bluepopsicle, Bob S, and whudunit! Your generosity drives this project forward and helps us turn ideas into reality. Thank you for being such a vital part of Stability Matrix!

🚀 Pioneers

A massive thank you to our Pioneer crew! Your support keeps the lights on and the updates flowing. Shoutout to: Szir777, Noah M, [USA]TechDude, Thom, SeraphOfSalem, Desert Viber, Adam, Droolguy, ACTUALLY_the_Real_Willem_Dafoe, takyamtom, robek, Phil R, Tundra Everquill, TheTekknician, and a warm welcome to our new Pioneers, Benjamin M and Ghislain G!

Add Wan2GP and misc fixes

(cherry picked from commit 1a844fe894b17e3d8a042f01a97f9f725de2ac4d)

# Conflicts:
#	CHANGELOG.md
Removed development version details and merged changelog entries.
[dev to main] backport: Add Wan2GP and misc fixes (1180)
Updated torch index for Forge-based UIs based on GPU type.
@gemini-code-assist
Copy link
Contributor

Summary of Changes

Hello @mohnjiles, 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, labeled as v2.15.5, significantly expands the application's capabilities by integrating new AI video generation packages like Wan2GP and an updated Stable Diffusion WebUI Forge - Neo. It also brings crucial improvements to GPU compatibility and performance, particularly for AMD and Nvidia users, through refined architecture detection and updated PyTorch indices. Furthermore, the PR addresses several user experience issues, including a fix for SD.Next launch options and duplicate custom node installations, ensuring a more robust and versatile platform.

Highlights

  • New Packages Introduced: Added Wan2GP for AI video creation and Stable Diffusion WebUI Forge - Neo as a separate, updated package.
  • GPU Architecture Detection: Consolidated and fixed AMD GPU architecture detection logic across Unix and Windows helpers, and expanded GpuInfo to include more RDNA architectures.
  • Torch Index Updates: Updated default CUDA index to cu130 for ComfyUI and Forge-based UIs, and adjusted SageAttention installer to support newer PyTorch versions (>=2.9.0) with cu128/cu130.
  • SD.Next --uv Argument: Introduced a togglable --uv argument for SD.Next launch options and fixed an issue where older SD.Next versions failed to launch due to a forced --uv argument.
  • Tiled VAE Decoding: Added Tiled VAE decoding as an Inference addon, thanks to @NeuralFault.
  • Package Management Improvements: Moved the original Stable Diffusion WebUI Forge to a 'Legacy' tab due to inactivity and fixed duplicate custom node installations in the Workflow Browser, also thanks to @NeuralFault.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

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.

Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a 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 introduces version 2.15.5, bringing a host of new features, updates, and bug fixes. Key additions include the Wan2GP and Stable Diffusion WebUI Forge - Neo packages. The AMD GPU architecture detection has been consolidated and refactored, improving maintainability. Dependencies like Torch and SageAttention have been updated to their latest versions. A notable bug fix makes the --uv argument for SD.Next optional, resolving launch issues for older versions. The codebase is cleaner with the removal of duplicated logic. My review includes a couple of suggestions for improving consistency in the changelog and dependency management for one of the new packages. Overall, this is a solid release with valuable improvements.


// Install additional packages
await venvRunner
.PipInstall("hf-xet setuptools numpy==1.26.4", onConsoleOutput)
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

high

The InstallNvidiaAsync method pins setuptools<70.0.0 to avoid distutils compatibility issues with Python 3.10. However, InstallAmdRocmAsync, which uses Python 3.11, installs setuptools without a version pin. Since distutils is also deprecated in Python 3.11, this could lead to similar installation issues. For consistency and to prevent potential build failures, consider pinning setuptools here as well.

                .PipInstall("hf-xet \"setuptools<70.0.0\" numpy==1.26.4", onConsoleOutput)

Comment on lines +23 to +26
#### 🌟 Visionaries
To our incredible Visionaries: **Waterclouds**, **JungleDragon**, **bluepopsicle**, **Bob S**, and **whudunit**! Your generosity drives this project forward and helps us turn ideas into reality. Thank you for being such a vital part of Stability Matrix!
#### 🚀 Pioneers
A massive thank you to our Pioneer crew! Your support keeps the lights on and the updates flowing. Shoutout to: **Szir777**, **Noah M**, **[USA]TechDude**, **Thom**, **SeraphOfSalem**, **Desert Viber**, **Adam**, **Droolguy**, **ACTUALLY_the_Real_Willem_Dafoe**, **takyamtom**, **robek**, **Phil R**, **Tundra Everquill**, **TheTekknician**, and a warm welcome to our new Pioneers, **Benjamin M** and **Ghislain G**!
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

The heading levels for "Visionaries" and "Pioneers" are ####, which is inconsistent with the ### level used for "Added", "Changed", and "Fixed". For better document structure and visual consistency, consider using ### for these sections as well. This would also align with the formatting in the pull request description.

Suggested change
#### 🌟 Visionaries
To our incredible Visionaries: **Waterclouds**, **JungleDragon**, **bluepopsicle**, **Bob S**, and **whudunit**! Your generosity drives this project forward and helps us turn ideas into reality. Thank you for being such a vital part of Stability Matrix!
#### 🚀 Pioneers
A massive thank you to our Pioneer crew! Your support keeps the lights on and the updates flowing. Shoutout to: **Szir777**, **Noah M**, **[USA]TechDude**, **Thom**, **SeraphOfSalem**, **Desert Viber**, **Adam**, **Droolguy**, **ACTUALLY_the_Real_Willem_Dafoe**, **takyamtom**, **robek**, **Phil R**, **Tundra Everquill**, **TheTekknician**, and a warm welcome to our new Pioneers, **Benjamin M** and **Ghislain G**!
### 🌟 Visionaries
To our incredible Visionaries: **Waterclouds**, **JungleDragon**, **bluepopsicle**, **Bob S**, and **whudunit**! Your generosity drives this project forward and helps us turn ideas into reality. Thank you for being such a vital part of Stability Matrix!
### 🚀 Pioneers
A massive thank you to our Pioneer crew! Your support keeps the lights on and the updates flowing. Shoutout to: **Szir777**, **Noah M**, **[USA]TechDude**, **Thom**, **SeraphOfSalem**, **Desert Viber**, **Adam**, **Droolguy**, **ACTUALLY_the_Real_Willem_Dafoe**, **takyamtom**, **robek**, **Phil R**, **Tundra Everquill**, **TheTekknician**, and a warm welcome to our new Pioneers, **Benjamin M** and **Ghislain G**!

@mohnjiles mohnjiles merged commit 3d76f0e into LykosAI:main Dec 29, 2025
2 of 3 checks passed
@github-actions github-actions bot locked and limited conversation to collaborators Dec 29, 2025
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Can't start older SD.Next with 2.15.x

2 participants