At NAB 2023, we are demonstrating the SHARK Stable Diffusion integration with Blender on AMD Radeon™ PRO W7900 featuring 48GB Memory. Come check it out in the AMD Innovation Zone.

Generative AI is transforming entire industries. Today we are demonstrating an integration of the SHARK Stable Diffusion REST API with the AI-Render plugin for Blender running on the recently announced AMD Radeon™ PRO W7900 GPUs with 48GB Memory to enable creative professionals to leverage the power of generative AI in their familiar 3D tools like Blender.
Here is an example of a scene with a tree rendered by default with Blender and the same using Stable Diffusion


Here are some more 3D scenes generated in Blender with SHARK on AMD RDNA™ architecture-based devices in the SHARK Discord server.









Give the SHARK Blender integration at try by following the instructions here. Share and show off what you can create with Blender + Generative AI in the SHARK Discord server. We plan to expose a more full fledged REST API with advanced upscaling, image to image and other features in the near future.
SHARK is an open source cross platform (Windows, macOS and Linux) Machine Learning Distribution packaged with torch-mlir (for seamless PyTorch integration), LLVM/MLIR for re-targetable compiler technologies along with IREE (for efficient codegen, compilation and runtime) and Nod.ai’s tuning. IREE is part of the OpenXLA Project, an ecosystem of ML compiler and infrastructure technologies being co-developed by AI/ML industry leaders including AMD, Google, Nod.ai and many more. OpenXLA aims to let ML developers build models in their preferred framework (TensorFlow, PyTorch, JAX) and easily execute them with high performance across a wide range of hardware backends (GPU, CPU, and ML accelerators).
Nod.ai is hiring: email us at stdin@nod.ai or apply at http://ai.compiler.engineer