kyuz0/amd-strix-halo-image-video-toolboxes

AMD Strix Halo Image & Video Toolbox is a Fedora toolbox container that provides a ROCm environment for image and video generation on AMD Ryzen AI Max Strix...

View on GitHub ↗Jump to charts ↓

Summary Information

Updated 28 minutes ago
Added to GitGenius on August 31st, 2025
Created on August 23rd, 2025
Open Issues & Pull Requests: 11 (+0)
Number of forks: 32
Total Stargazers: 175 (+0)
Total Subscribers: 8 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 3.1 days
Mean response time: 6.8 days
90th percentile: 20.7 days
Tracked items: 15

How this project is maintained

Around half of the issues opened in the past year never receive a reply. Only 9% of issues opened in the past year have been closed.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 8
New in 7 days: 0
Closed in 7 days: 0
Avg open age: 123 days
Stale 30+ days: 8
Stale 90+ days: 8

Recent activity

Opened in 7 days: 0
Closed in 7 days: 0
Comments in 7 days: 0
Events in 7 days: 0

Top labels

No label distribution available yet.

Most active issues this week

No issue events were indexed in the last 7 days.

Detailed Description

AMD Strix Halo Image & Video Toolbox is a Fedora toolbox container that provides a ROCm environment for image and video generation on AMD Ryzen AI Max Strix Halo processors.

The toolbox solves the problem of running generative AI models for image and video creation on AMD's latest integrated GPU architecture. It packages a complete ROCm nightly stack configured for the gfx1151 GPU found in Strix Halo systems, alongside three main tools: Qwen Image Studio for image generation and editing, WAN 2.2 for video generation across multiple modes including text-to-video and image-to-video, and ComfyUI for node-based workflow execution. Model weights are stored outside the container in the user's home directory, ensuring they persist across container updates or deletions.

The toolbox is designed for developers and creators working specifically with Strix Halo hardware who need to run these generative models locally. It has been tested on Framework Desktop systems and other Strix Halo machines including GMKtec EVO X-2 and HP Z2 G1a. The README notes that Ubuntu users should consult the toolkits documentation for compatibility information. However, the project is now discontinued and outdated; the README explicitly directs users to a newer, maintained successor repository for updated image and video generation capabilities, and references an official landing page as the authoritative source for current maintained toolboxes.

The project shows active development with recent stability fixes addressing Strix Halo-specific issues. Updates have been made to address stability concerns on the target hardware platform.