7 Sources
[1]
AMD unveils industry-first Stable Diffusion 3.0 Medium AI model generator tailored for XDNA 2 NPUs -- designed to run locally on Ryzen AI laptops
AMD, in collaboration with Stability AI, has unveiled the industry's first Stable Diffusion 3.0 Medium AI model tailored for the company's XDNA 2 NPUs which process data in the BF16 format. The model is designed to run locally on laptops based on AMD's Ryzen AI laptops and is available now via
[2]
AMD gets GPU-quality AI art running on its NPUs
AMD and Stability AI on Monday said that the two companies have ported Stable Diffusion 3.0 Medium to Stability's Amuse AI art generator, allowing improved image generation, and even text, running just on the NPU alone. With most of the jaw-dropping advancements in AI art coming from the cloud
[3]
AMD Amuse 3.1 Release: BF16 Precision SD 3.0 Medium on Ryzen AI
The new BF16 Stable Diffusion 3.0 Medium model is now available in Amuse 3.1. This release brings bfloat16 precision to the widely used Stable Diffusion 3 framework, letting you run complex image generation tasks directly on an AMD Ryzen AI laptop without sacrificing too much memory or accuracy. By
[4]
AMD opens the door to local Stable Diffusion AI image generation on Ryzen AI NPUs
TL;DR: AMD and Stability AI have unveiled the world's first FP16 Stable Diffusion 3.0 Medium model, optimized for Ryzen AI 300 Series XDNA 2 NPUs, which delivers enhanced AI image generation quality and 4MP resolution without the need for a dedicated GPU. Amuse 3.1 software enables free, efficient,
[5]
AMD's New AI Image Model Can Run Locally on Ryzen AI Laptops
It is a text-to-image model that does not require Internet connectivity AMD has released a new Stable Diffusion 3 Medium artificial intelligence (AI) model optimised for XDNA 2 neural processing units (NPUs). The chipmaker claimed that it is the world's first AI model that processes outputs in the
[6]
AMD Intros "SD 3 Medium", The World's First BF16 NPU Model Designed For XDNA 2 AI NPUs, Offer Reduced Memory Footprint & Faster Text-To-Image Gen
AMD has launched the world's first BF16 NPU model for XDNA 2 NPUs, which it is calling SD 3 Medium, and makes for faster and uncompromised text-to-image generation. AMD's SD 3 Medium Is A BF16 Model That Is Optimized For XDNA 2 "AI" NPUs, Now Available In Amuse 3.1 To Try Out Press Release: At
[7]
AMD Intros "SDXL Turbo", The World's First BF16 NPU Model Designed For XDNA 2 AI NPUs, Offer Reduced Memory Footprint & Faster Text-To-Image Gen
AMD has launched the world's first BF16 NPU model for XDNA 2 NPUs, which it is calling SDXL Turbo, and makes for faster and uncompromised text-to-image generation. AMD SDXL Turbo Is A BF16 Model That Is Optimized For XDNA 2 "AI" NPUs, Now Available In Amuse 3.1 To Try Out Press Release: At
Share
Copy Link
AMD, in collaboration with Stability AI, has released a new Stable Diffusion 3.0 Medium AI model optimized for XDNA 2 NPUs, enabling high-quality image generation on Ryzen AI laptops without requiring internet connectivity or dedicated GPUs.
AMD, in collaboration with Stability AI, has unveiled the industry's first Stable Diffusion 3.0 Medium AI model tailored for XDNA 2 Neural Processing Units (NPUs)
1
. This innovative model is designed to run locally on AMD Ryzen AI laptops, marking a significant advancement in on-device AI image generation capabilities.
Source: TweakTown
The new AI model processes data in the BF16 format, optimized for local execution on machines equipped with XDNA 2 NPUs. It requires a PC with an AMD Ryzen AI 300-series or Ryzen AI MAX+ processor, an XDNA 2 NPU capable of at least 50 TOPS, and a minimum of 24GB of system RAM
2
.Users can access this technology through the Amuse 3.1 Beta software from Tensorstack, which is available for free download
3
. The model is subject to the Stability AI Community License, making it free for individuals and small businesses with less than $1 million in annual revenue.
Source: PCWorld
The Stable Diffusion 3.0 Medium model interprets written prompts to produce 1024x1024 images, which are then upscaled to 2048x2048 resolution using a built-in NPU pipeline
4
. This results in 4MP outputs suitable for print and professional use. The model supports advanced prompting features for fine control over image composition, allowing users to create customizable stock-quality visuals for design and marketing applications.AMD claims that each image generation (with 20 steps) takes about 90 seconds on compatible hardware
2
. While this is slower than cloud-based solutions, it offers unlimited local generation without internet connectivity requirements. The XDNA 2 NPU is designed to handle AI workloads efficiently, enabling consistent performance even during extended use on battery power3
.Related Stories
The BF16 Stable Diffusion 3.0 Medium model represents an evolution of previous block FP16 efforts. By adopting block-based tensor layouts and memory-efficient kernels, AMD and Stability AI have managed to reduce peak RAM usage from around 24GB to under 10GB while preserving image quality and color fidelity
3
.
Source: Tom's Hardware
This development opens up new possibilities for content creators, designers, and AI enthusiasts. It enables high-quality image generation without the need for dedicated GPUs or cloud services, making AI-powered creativity more accessible and portable
5
. Users can now generate and iterate on AI-created images quickly and efficiently, even in offline environments.As AMD continues to push the boundaries of on-device AI capabilities, this release signifies a notable step forward in making advanced AI technologies more widely available to consumers and professionals alike.
Summarized by
Navi
[1]
[5]
1
Technology

2
Technology

3
Policy and Regulation
