![]() See here for a Python sample showing how to use Stable Diffusion with Olive. Stable Diffusion models with different checkpoints and/or weights but the same architecture and layers as these models will work well with Olive.Ĭheck out tomorrow’s Build Breakout Session to see Stable Diffusion in action: Deliver AI-powered experiences across cloud and edge, with Windows We’ve tested this with CompVis/stable-diffusion-v1-4 and runwayml/stable-diffusion-v1-5. See here for a sample that shows how to optimize a Stable Diffusion model. Once you’ve done this, follow the steps in our DML and Olive blog post Make sure your model is in the ONNX format you can use Olive to do this conversion. You can use Olive to ensure your Stable Diffusion model works as well as possible with DirectML. For more on Olive with DirectML, check out our post, Optimize DirectML performance with Olive We worked closely with the Olive team to build a powerful optimization tool that leverages DirectML to produce models that are optimized to run across the Windows ecosystem. Getting the best performance with DirectML For more on how Stable Diffusion lights up on our partners’ hardware with DML, check out: Our goal is to enable developers to infuse apps with AI hardware acceleration at scale. We’ve optimized DirectML to accelerate transformer and diffusion models, like Stable Diffusion, so that they run even better across the Windows hardware ecosystem. We are demonstrating what can be done with Stable Diffusion models in two of our Build sessions: Shaping the future of work with AI and Deliver AI-powered experiences across cloud and edge, with Windows. ![]() With some extra training, developers can fine-tune their model to generate images of any domain, subject, or style they want. The base model can create images from text and since it’s open-source developers can customize it for their own needs and preferences. Stable Diffusion is particularly interesting. Text-to-image models are amazing tools that can transform natural language into stunning images. ![]()
0 Comments
Leave a Reply. |