New toolbox for Image and Video generation with ComfyUI on Strix halo, comes with built-in tested workflows for open models like Qwen Image, WAN 2.2 and the new LTX2: this is finally stable and performance has been improving.
Let me know how you get along with it and what workflows/models you’d like to the toolbox and benchmarks!
Benchmarks: AMD Ryzen AI Max “Strix Halo” ComfyUI Benchmarks