# \#diffusion

**URL:** https://devcommunity.amd.com/tag/diffusion/163.md

[Latest](https://devcommunity.amd.com/latest.md) · [Categories](https://devcommunity.amd.com/categories.md) · [Tags](https://devcommunity.amd.com/tags.md)

---

## [Faster Diffusion Inference on AMD: Sparse Video Attention and 4-bit Image Quantization](https://devcommunity.amd.com/t/faster-diffusion-inference-on-amd-sparse-video-attention-and-4-bit-image-quantization/1024)

<div class="topic-metadata">

**Author:** [@nirth\_AMD](https://devcommunity.amd.com/u/nirth_AMD)\
**Replies:** 0\
**Last updated:** [September 14, 2026, 2:32pm UTC](https://devcommunity.amd.com/t/faster-diffusion-inference-on-amd-sparse-video-attention-and-4-bit-image-quantization/1024 "2026-09-14T14:32:32Z")

</div>

Two AMD ROCm blogs tackle the compute and memory bottlenecks in diffusion model inference from complementary angles — one targeting the attention mechanism in video generation, the other pushing image diffusion to 4-bit …