Update blog

Author: cmdr2

content/blog/2025-10-10-1760085894.md

@@ -11,7 +11,7 @@ tags:
 The design constraints for Easy Diffusion's next engine (i.e. sdkit v3) are:
 * Lean: Install size of < 200 MB uncompressed (excluding models).
 * Fast: Performance within 10% of the best-possible speed on that GPU for that model.
-* Capable: Supports Stable Diffusion 1.x, 2.x, 3.x, XL, Flux, Chroma, ControlNet, LORA, Embedding, VAE. Supports loading custom model weights (from civitai etc).
+* Capable: Supports Stable Diffusion 1.x, 2.x, 3.x, XL, Flux, Chroma, ControlNet, LORA, Embedding, VAE. Supports loading custom model weights (from civitai etc), and memory offloading (for smaller GPUs).
 * Targets: Desktops and Laptops, Windows/Linux/Mac, NVIDIA/AMD/Intel/Apple.
 
 I think it's possible, using ML compilers like TensorRT-RTX (and similar compilers for other platforms). See: [Some notes on ML compilers](https://cmdr2.github.io/notes/2025/10/1760088945/).