Automatic1111's inefficient SDXL implementation drove ComfyUI's viral user adoption
comfyanonymous (Comfy) · AI Engineering for Art - with comfyanonymous · Jan 4, 2025 · at 47:23
Comfy, the creator of ComfyUI, explains the inflection point in 2023 when Stability AI launched Stable Diffusion XL (SDXL) 1.0 and users needed an efficient open-source GUI.
0:00 / 0:31exact quote · 31.7s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“The big, one point zero release happened, and wow, Confu UI was the only way a lot of people could actually run it on their computers, because it just, like, automatic was so, like, inefficient and bad that most people couldn't act, like, it just wouldn't work, like, because he did a quick implementation, so people were forced to use Confu UI, and that's how it became popular, because people had no choice.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from comfyanonymous (Comfy)
Comfyanonymous criticizes Gradio for coupling interface logic with backends
“Yeah, Gradio, I don't like Gradio. It's bad. Like, the, that's one of the reasons why, like, Automatic was very bad. It's great because the problem with Gradio, it forces you to, well, not forces you, but it kind of makes your interface logic and your back-end…”
AMD GPUs perform horribly on Windows for generative AI tasks
“AMD works horribly on Windows. Like, on Linux, it works fine. It's lower than the price equivalent NVIDIA GPU. But it works, like, you can use it, generate images, everything works. On Linux, on Windows, You might have a hard time”
Comfy: Training on all internet images yields ugly outputs
“You can create a very good model that doesn't generate nice images, because most images on the internet are ugly, so if you, if that's like, if you just, oh, I have the best model that can, like, it's super smart, I create it on all the, like, I turn it on jus…”
Comfyanonymous considers Genmo's Mochi the best open video generation model
“There's, yeah, there's actually a few of them, but the one I've implemented in Comfy is Mochi, because that, that seems to be The best one so far.”