AMD Blogs:
AI image generation is one of the most popular use-cases for generative AI and a quintessential AI PC experience is simply incomplete without it. Most of this local image generation happens using Stable Diffusion models created by Stability AI – which is a pioneer in this field. Multiple applications, GUIs, command lines and code blocks exist in the wild to run Stable Diffusion models on AI PCs but they are typically very cumbersome to install, require a high level of technical knowledge to run and may not have optimized performance for your PC.
AMD has partnered with TensorStack, an AI technology company based out of New Zealand, to bring a painless, easy to use and optimized end-user experience to AMD Ryzen™ AI 300 Series processors and Radeon™ RX 7000 Series graphics customers.
Figure 2 AI generated image created in Amuse 2.0.0 Beta on Ryzen AI(TM) 300 Series laptop.
Amuse 2.0.0 is an easy to install program, that has no dependencies, a simplified user interface called “Ez Mode” and will quickly take care of all the configuration required to jump start your AI image generation journey. It also features an AMD XDNA™ Super Resolution solution to speed up and increase output size by 2x at the end of the image generation stage. Some key features are:
- No command line needed
- Simple and easy to use
- AMD XDNA™ Super Resolution
- Single executable
- No dependencies
- Auto configuration and model selection
- Paint to Image
- Drawing to Image
- Create your own AI filters
- Multi-stage, ONNX based pipeline (Stable Diffusion, Control Nets, Feature Extractors)
Amuse 2.0.0 Beta auto detects and auto configures for your device. The official recommended system specifications for both discrete and integrated solutions are given below:
- AMD Ryzen™ AI 300 series processors with 24GB of RAM or higher
- AMD Ryzen™ 8040 series processors (AMD XDNA™ Super Resolution requires the latest OEM MCDM and NPU driver update) with 32GB of RAM
- Radeon™ RX 7000 Series Graphics Cards
If this is your first time using Stable Diffusion, we highly recommend the “Balanced” setting as it is a good mix of performance and quality. The application works by first generating an image using a 512x512 canvas (square aspect ratio) and will then run it through the AMD XDNA ™ architecture-powered super resolution solution to output a crisp image measuring 1024x1024.
One of the most transformative AI experiences, in our opinion, is that AI PCs enable everyone to become an artist and everyone to become a graphic designer. Creativity will know no bounds in the AI PC era and Amuse Design and AI Filters enable just that. So whether you are a content creator and a pro or are just someone that wants to make images for fun, Amuse has you covered.
You can also head over to the ‘AI Filters’ drawer to create your own AI filters and change the look and feel of existing images using generative AI – and of course, all of this happens completely locally thanks to the power of AMD Ryzen™ AI and Radeon™ graphics.
Footnotes:
Please note that Amuse 2.0 is a Beta release and an experimental software. It is being provided on an “as is” basis. As such, there may be bugs and the user experience may be unstable, or cause unintended behavior.
GD-97 - Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.
Source:
Introducing Amuse 2.0 Beta with AMD XDNA™ Super Resolution: a fully local, AI experience
AI image generation is one of the most popular use-cases for generative AI and a quintessential AI PC experience is simply incomplete without it. Most of this local image generation happens using Stable Diffusion models created by Stability AI – which is a pioneer in this field. Multiple...
