https://noxengine.dev/benchmarks/Recent content in Benchmarks on Nox | INT8 image and video inferenceHugoen-ushttps://noxengine.dev/benchmarks/benchmark3090/Mon, 01 Jan 0001 00:00:00 +0000https://noxengine.dev/benchmarks/benchmark3090/<h1 id="benchmark-vs-comfyui">Benchmark vs ComfyUI</h1> <p>ComfyUI and Nox run the same generation jobs on the same machine, so the timings are directly comparable. Each pipeline is generated twice: a Cold run in a fresh process (including model and pipeline load) and a Warm run immediately afterwards. Speedup is calculated as <code>ComfyUI time / Nox time</code>; above 1x means Nox was faster. Both engines load the exact same checkpoints: INT8 ConvRot for every pipeline except SDXL, which runs in FP16 on both.</p>https://noxengine.dev/benchmarks/benchmark4080/Mon, 01 Jan 0001 00:00:00 +0000https://noxengine.dev/benchmarks/benchmark4080/<h1 id="benchmark-vs-comfyui">Benchmark vs ComfyUI</h1> <p>ComfyUI and Nox run the same generation jobs on the same machine, so the timings are directly comparable. Each pipeline is generated twice: a Cold run in a fresh process (including model and pipeline load) and a Warm run immediately afterwards. Speedup is calculated as <code>ComfyUI time / Nox time</code>; above 1x means Nox was faster. Both engines load the exact same checkpoints: INT8 ConvRot for every pipeline except SDXL, which runs in FP16 on both.</p>https://noxengine.dev/benchmarks/benchmark5090/Mon, 01 Jan 0001 00:00:00 +0000https://noxengine.dev/benchmarks/benchmark5090/<h1 id="benchmark-vs-comfyui">Benchmark vs ComfyUI</h1> <p>ComfyUI and Nox run the same generation jobs on the same machine, so the timings are directly comparable. Each pipeline is generated twice: a Cold run in a fresh process (including model and pipeline load) and a Warm run immediately afterwards. Speedup is calculated as <code>ComfyUI time / Nox time</code>; above 1x means Nox was faster. Both engines load the exact same checkpoints: INT8 ConvRot for every pipeline except SDXL, which runs in FP16 on both.</p>https://noxengine.dev/benchmarks/benchmarkh100/Mon, 01 Jan 0001 00:00:00 +0000https://noxengine.dev/benchmarks/benchmarkh100/<h1 id="benchmark-vs-comfyui">Benchmark vs ComfyUI</h1> <p>ComfyUI and Nox run the same generation jobs on the same machine, so the timings are directly comparable. Each pipeline is generated twice: a Cold run in a fresh process (including model and pipeline load) and a Warm run immediately afterwards. Speedup is calculated as <code>ComfyUI time / Nox time</code>; above 1x means Nox was faster. Both engines load the exact same checkpoints: INT8 ConvRot for every pipeline except SDXL, which runs in FP16 on both.</p>