# Stable Diffusion Now Optimized for AMD Radeon™ GPUs and Ryzen™ AI APUs

DevFeed: [Stable Diffusion Now Optimized for AMD Radeon™ GPUs and Ryzen™ AI APUs](<https://devfeed.tech/articles/stable-diffusion-now-optimized-for-amd-radeontm-gpus-and-ryzentm-ai-apus-82876.md>)

Original publisher: [Read original article](<https://stability.ai/news-updates/stable-diffusion-now-optimized-for-amd-radeon-gpus>)

Author: Guest User

Published: 2025-04-16T13:02:52Z

Content type: release

Language: en

Sources: [News & Updates - Stability AI](<https://devfeed.tech/sources/news-updates-stability-ai.md>)

Topics: [stable-diffusion](<https://devfeed.tech/topics/stable-diffusion.md>), [AMD FidelityFX Super Resolution (FSR)](<https://devfeed.tech/topics/amd-fsr-upscaling.md>), [GPU](<https://devfeed.tech/topics/gpu.md>), [onnx](<https://devfeed.tech/topics/onnx.md>), [TensorRT](<https://devfeed.tech/topics/tensorrt.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [amd](<https://devfeed.tech/tags/amd.md>), [gpus](<https://devfeed.tech/tags/gpus.md>), [inference](<https://devfeed.tech/tags/inference.md>), [onnx](<https://devfeed.tech/tags/onnx.md>), [onnx-runtime](<https://devfeed.tech/tags/onnx-runtime.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [performance](<https://devfeed.tech/tags/performance.md>), [stable-diffusion](<https://devfeed.tech/tags/stable-diffusion.md>)

## AI overview

Stability AI and AMD released ONNX-optimized versions of four Stable Diffusion models for Radeon GPUs and Ryzen AI APUs. The versions are available on Hugging Face and Amuse 3.0. The article reports up to 2.6x faster inference for SD3.5 and up to 3.8x for SDXL compared with base PyTorch models.

## Source excerpt

We've collaborated with AMD to deliver select ONNX-optimized versions of the Stable Diffusion model family, engineered to run faster and more efficiently on AMD Radeon™ GPUs and Ryzen™ AI APUs.