Our great sponsors
-
automatic
SD.Next: Advanced Implementation of Stable Diffusion and other Diffusion-based generative image models
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
-
Olive
Olive is an easy-to-use hardware-aware model optimization tool that composes industry-leading techniques across model compression, optimization, and compilation. (by microsoft)
-
WorkOS
The modern identity platform for B2B SaaS. The APIs are flexible and easy-to-use, supporting authentication, user identity, and complex enterprise features like SSO and SCIM provisioning.
To be specific, Automatic1111 run on Linux (ROCm) or the fork for Windows DirectML use (https://github.com/lshqqytiger/stable-diffusion-webui-directml). Some people mistakenly pull the main branch instead of the directml fork.
The Vladmandic fork of Automatic1111 (SD.Next) can do the Linux and DirectML from the same branch. Speeds being poor on DirectML's end of the problem. It is to the point that you might as well load a Linux boot and use ROCm there. All hope is on ROCm coming to Windows eventually.
Microsoft has provided a path in DirectML for vendors like AMD to enable optimizations called ‘metacommands’. In the case of Stable Diffusion with the Olive pipeline, AMD is building driver support for a metacommand implementation intended to improve performance and reduce the time it takes to generate output from the model. This feature will be validated on AMD RDNA™ 3 devices including AMD Radeon™ RX 7900 Series graphics cards and AMD Ryzen™ 7040 Series Mobile processors with Radeon™ graphics.