ComfyUI
To get an idea of the range of features provided by ComfyUI, click the Templates icon (which is on the left hand side). There are a whole raft of templates available. I’m only going to look at one. Image Generation which generates images from text prompts.
The next step is to install some models. That’s made easier using ComfyUI-Manager although you can manually download models and put them in the models directory. Click the Manager button (top right) which opens the ComfyUI Manager. I’ve clicked Model Manager which has opened up the window below, and lets me install models.
Let’s use the sd_xl_base_1.0.safetensors model. I’ve entered a text prompt. I’ll be creating a 512×512 image with 20 steps.
As the log shows, the image generation takes around 14 seconds with the Radeon 890M iGPU. For an iGPU that’s a good result. With the same model, steps and text prompt, a dedicated NVIDIA card (GeForce 3060 Ti with 8GB VRAM) completes the image generation much quicker, taking just over 3 seconds to generate an image. I’m still impressed by the iGPU.
Here’s an example of the output generated.
With different seeds:
This is just a taster for what ComfyUI offers. Performance is good with the iGPU.
Pages in this article:
Page 1 – Introduction
Page 2 – Installing ROCm under Manjaro
Page 3 – Installing Miniconda and ComfyUI
Page 4 – ComfyUI Performance
Complete list of articles in this series:
| Minisforum AI X1 Pro | |
|---|---|
| Introduction | Introduction to the series and interrogation of the Minisforum AI X1 Pro |
| Benchmarks | Benchmarking the Minisforum AI X1 Pro |
| Power | Testing and comparing the power consumption under various workloads |
| Jan | ChatGPT without privacy concerns |
| ComfyUI | Generate video, images, 3D, audio with AI |