Stable Diffusion evolves with AMD optimization! Achieving up to 3.8x speed improvements.
Stable Diffusion Now Optimized for AMD Radeon™ GPUs and Ryzen™ AI APUs
Original: Stable Diffusion Now Optimized for AMD Radeon™ GPUs and Ryzen™ AI APUs — Stability AI
Importance: 新機能としてAMD最適化モデルが発表され、広範な影響を持つため。
Summary
Stability AI has collaborated with AMD to release ONNX-optimized versions of the Stable Diffusion models. These models run faster and more efficiently on AMD Radeon™ GPUs and Ryzen™ AI APUs. Available on Hugging Face, models like SD3.5 and SDXL Turbo achieve up to 3.8x speed improvements compared to base PyTorch models, enhancing the efficiency of creative applications.
Key Points
- AMD optimization makes SD3.5 up to 2.6x faster
- SDXL Turbo achieves up to 3.8x speed improvement
- Easily integrates into existing ONNX-compatible environments
- New models available on Hugging Face
- Enhances efficiency for creative applications
View developer notes (APIs, breaking changes, migration)
Stability AI and AMD jointly engineered ONNX-optimized Stable Diffusion models to enhance inference performance without compromising quality. Available on Hugging Face with '_amdgpu' suffix, models like SD3.5 Large and XL Turbo achieve up to 3.8x faster inference compared to base PyTorch models, allowing seamless integration into existing workflows.
Source: https://stability.ai/news-updates/stable-diffusion-now-optimized-for-amd-radeon-gpus
Outlet: Stability AI
This article is an AI-generated summary (OpenAI GPT-4o-mini) of publicly available information from Anthropic, OpenAI, Google, Meta, Mistral, DeepSeek, Sakana, and other vendors. The original source URL is always provided in accordance with fair-use citation requirements. Summaries are AI-generated and may contain mistranslations or misinterpretations. Always verify details with the original source.