Post from Apr 24, 2026
Released Easy Diffusion v4.3 (which updates to sdkit v3.2). This adds support for Ernie Image (and Ernie Turbo), as well as improved support for Anima models.
sdkit¶
Post from Mar 27, 2026
Got Easy Diffusion v4 working on Apple and Intel Macs. The performance difference ratio (vs ED v3) is similar to the ratio on Windows (with CUDA) and other deployment targets. So that indicates optimization opportunities in sd.cpp. It's currently about 1.5x slower than diffusers-based Stable Diffusion.
Post from Jan 08, 2026
For Z-Image, the performance of the stock version of chromaForge is poorer than sd.cpp's. Mainly because chromaForge isn't able to run the smaller gguf quantized models that sd.cpp is able to run (chromaForge fails with the errors that I was fixing yesterday).
Post from Jan 07, 2026
Worked on fixing Z-Image support in ED's fork of chromaForge (a fork of Forge WebUI). Fixed a number of integration issues. It's now crashing on a matrix multiplication error, which looks like an incorrectly transposed matrix (mostly due to reading the weights in the wrong order).
Post from Dec 08, 2025
The new engine that'll power Easy Diffusion's upcoming v4 release (i.e. sdkit3) has now been integrated into Easy Diffusion. It's available to test by selecting v4 engine in the Settings tab (after enabling Beta). Please press Save and restart Easy Diffusion after selecting this.
Post from Nov 27, 2025
Managed to get stable-diffusion.cpp integrated into sdkit v3 and Easy Diffusion.
Post from Nov 19, 2025
Following up to the previous post on sdkit v3's design:
Post from Nov 18, 2025
Successfully compiled the VAE of Stable Diffusion 1.5 using graph-compiler.
Post from Nov 13, 2025
PolyBlocks is another interesting ML compiler, written using MLIR. It's a startup incubated in IISc Bangalore, run by someone (Uday Bondhugula) who co-authored a paper on compiler optimizations for GPGPUs back in 2008 (17 years ago)!
Post from Nov 07, 2025
Wrote a simple script to convert ONNX to GGML. It auto-generates C++ code that calls the corresponding ggml functions (for each ONNX operator). This file can then be compiled and run like a normal C++ ggml program, and will produce the same results as the original model in PyTorch.