https://cruver.ai/tags/image-generation/ Recent content in Image-Generation on Hullabalooing Hugo en Wed, 21 Jan 2026 00:00:00 -0700 https://cruver.ai/gpu-ai/posts/comfyui-mi60/ Wed, 21 Jan 2026 00:00:00 -0700 https://cruver.ai/gpu-ai/posts/comfyui-mi60/ <p>Node-based Stable Diffusion UI with AMD MI60 GPU acceleration via ROCm.</p> <h2 id="overview">Overview<a class="anchor" href="#overview">#</a></h2> <p>ComfyUI runs as a containerized service using a custom ROCm 5.7 image built for the MI60&rsquo;s gfx906 architecture. It can run standalone on both GPUs or alongside vLLM in the <code>image-chat</code> configuration.</p> <h2 id="quick-start">Quick Start<a class="anchor" href="#quick-start">#</a></h2> <div class="highlight"><pre tabindex="0" style="color:#e2e4e5;background-color:#282a36;-moz-tab-size:4;-o-tab-size:4;tab-size:4;"><code class="language-bash" data-lang="bash"><span style="display:flex;"><span><span style="color:#78787e"># Build the container image</span> </span></span><span style="display:flex;"><span><span style="color:#ff5c57">cd</span> comfyui </span></span><span style="display:flex;"><span>make build </span></span><span style="display:flex;"><span> </span></span><span style="display:flex;"><span><span style="color:#78787e"># Start ComfyUI (standalone, both GPUs)</span> </span></span><span style="display:flex;"><span>make up </span></span><span style="display:flex;"><span> </span></span><span style="display:flex;"><span><span style="color:#78787e"># Or use the image-chat config (vLLM on GPU0, ComfyUI on GPU1)</span> </span></span><span style="display:flex;"><span>curl -X POST -H <span style="color:#5af78e">&#34;Content-Type: application/json&#34;</span> <span style="color:#5af78e">\ </span></span></span><span style="display:flex;"><span> -d <span style="color:#5af78e">&#39;{&#34;config&#34;:&#34;image-chat&#34;}&#39;</span> http://localhost:9100/switch</span></span></code></pre></div><p>Access the UI at <a href="http://localhost:8188">http://localhost:8188</a>.</p>