cancel
Showing results for 
Search instead for 
Did you mean: 

Introducing Amuse 2.2 Beta: With Stable Diffusion 3.5 Support and AMD Ryzen™ AI Image Quality Update

AMD_AI
Staff
Staff
1 0 10.2K

 

 Stable Diffusion 3.5.jpg

Figure 1 Prompt: A prince stands on the edge of a mountain where "Stable Diffusion" is written in gold typography in the sky.

A step-by-step guide on how to run Stable Diffusion 3.5 Medium, Stable Diffusion 3.5 Large and Stable Diffusion 3.5 Turbo is available here.

Amuse 2.2 Beta is now available for AMD Ryzen™ AI 300 Series processors and Radeon™ 7000 Series graphic users and can be downloaded from the Amuse AI website. Amuse Beta is a dependency free, AI image generation studio optimized for AMD hardware. The new 2.2 Beta version brings support for Stable Diffusion 3.5 (SD 3.5) family of models by Stability AI: including Stable Diffusion 3.5 Medium, Stable Diffusion 3.5 Large and Stable Diffusion 3.5 Large Turbo. It also includes an image quality enhancement for AMD Ryzen™ AI family of products.

Stable Diffusion 3.5 Support

Stable diffusion comparison 1.jpg

 

Stable Diffusion 3.5 family of models introduce a 8.1 billion parameter model called Stable Diffusion 3.5 Large. This base model provides a powerful addition to the Stable Diffusion family and presents state of the art image capability for 1 MP (~1024x1024) images. Stable Diffusion 3.5 Large Turbo is a distilled version of the same model which can generate an image in just four steps with a slight quality trade off.

Stable diffusion comparison 2.jpg

 

Stable Diffusion 3.5 Medium is another new model with 2.5 billion parameters and can generate images all the way up to 2 Mega Pixels (~1536x1536). Since it is a smaller model, it also has a smaller memory footprint and wider hardware support. Both the SD 3.5 Large and SD 3.5 Medium models are fine-tuneable and feature improved text support and prompt adherence.

 

All the Stable Diffusion 3.5 models are now available for AMD users starting with the Amuse 2.2 Beta release. Amuse allows partial offload of larger models that may not fit inside the vRAM of the device using a “minimum” mode, which sequentially loads the different parts of an image generation model. Performance in this mode is affected by your disk read/write speeds and RAM speeds.

 

The product support matrix is given below: 

Models

Products

Stable Diffusion 3.5 Large

 

Maximum Mode: AMD Radeon™ PRO W7900, AMD Radeon™ PRO W7800 graphics

Minimum Mode: AMD Radeon RX 7900 XTX graphics with 32GB RAM

Stable Diffusion 3.5 Large Turbo

Maximum Mode: AMD Radeon™ PRO W7900, AMD Radeon™ PRO W7800 graphics

Minimum Mode: AMD Radeon RX 7900 XTX with 32GB RAM

Stable Diffusion 3.5 Medium

Maximum Mode: AMD Radeon™ PRO W7900, AMD Radeon™ PRO W7800, AMD Radeon RX 7900 XTX graphics, AMD Ryzen™ AI PRO 300 Series processor (64 GB)

Minimum Mode: AMD Radeon RX 7900 XT, AMD Ryzen™ AI 300 Series processor (32 GB)

 

Image Quality Enhancements for AMD Ryzen™ AI Users

Significant image quality updates have also been rolled out for AMD Ryzen™ AI 300 Series processors. Highly efficient architectures and checkpoints like Stable Diffusion Lightning are now fully supported and will be the default “HQ” mode while running Amuse in EZ Mode. This update brings a significant quality uplift to local AI image generation on thin and light systems while on-the-go and completely offline. Furthermore the native canvas size has been increased by 4x to 1024x1024 pixels (~1 MP) and when combined with AMD XDNA Super Resolution generates an output of 2048x2048 (~ 2MP). 

 

Ryzen AI image quality update copy.jpg

 

Because of these changes, the new HQ model in Amuse 2.2 Beta can deliver high quality images with significantly increase prompt adherence and visual fidelity.

 

Images are now more detailed and coherent. The HQ mode now also features a ”boost quality” option as well, which will increase image quality even further in most cases at the cost of increasing the generation time. To try out this new HQ model, download Amuse on an AMD Ryzen™ AI 300 Series laptop and change the quality slider to “HQ”.

 

The AMD XDNA™ architecture powers Super Resolution features has also been optimized and is now capable of end-to-end upscaling much faster than before. Combined with the AI Filters and AI Design tab which house powerful AI assistants, Amuse is a very easy to use AI toolkit that requires no technical knowledge and auto configures.

To try out Amuse 2.2, you can download the one-click installer from here.

Footnotes: 

Please note that Amuse 2.0 is a Beta release and 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. 

GD-220c - AMD Ryzen™ AI is defined as the combination of a dedicated AI engine, AMD Radeon™ graphics engine, and Ryzen processor cores that enable AI capabilities. OEM and ISV enablement is required, and certain AI features may not yet be optimized for AMD Ryzen AI processors. AMD Ryzen AI is compatible with: (a) AMD Ryzen 7040 and 8040 Series processors except Ryzen 5 7540U, Ryzen 5 8540U, Ryzen 3 7440U, and Ryzen 3 8440U processors; (b) AMD Ryzen AI 300 Series processors, and (c) all AMD Ryzen 8000 G-Series desktop processors except the Ryzen 5 8500G/GE and Ryzen 3 8300G/GE processors. Please check with your system manufacturer for feature availability prior to purchase.