News for hackers. Stuff that matters.
Re:2023 was the year that GPUs stood still by brucethemoose2 on Friday December 29, 2023 @12:06PM (#38807323)
This is a pet peeve of mine, but A1111 is not a great example of a ML project. The backend codebase is a mess compared to diffusers, its slow even on Nvidia, its history is filled with controversy (including license breaking and outright piracy in the codebase), the frontend is buggy and unstable. I appreciate how it was a pioneer in 2022-H1 2023, but I am somewhat annoyed its still the de facto SD backend.

Better maintained inference projects are picking up considerable AMD/Intel support. Sometimes even Apple Silicon support.

Re:2023 was the year that GPUs stood still by Der_Einzige on Friday December 29, 2023 @12:17PM (#38807502)
The only real competitor is ComfyUI, because without the huge ecosystem around your other front end, you lose MASSIVE capabilities, for example, losing this is a big mistake: https://github.com/ljleb/prompt-fusion-extension
Re:2023 was the year that GPUs stood still by jadbox on Friday December 29, 2023 @01:41PM (#38808590)
Is there something like that extension for comfy yet?
Re:2023 was the year that GPUs stood still by pseudo0 on Friday December 29, 2023 @03:27PM (#38809819)
At least on Nvidia, A1111 has had near identical performance to ComfyUI on SDXL and SD1.5 for me. Besides that, there were typical minor problems that happen when some guy's hobby project goes viral and suddenly is under massive scrutiny. It was the first "good enough" interface and now there is massive community inertia with extensions, plugins, etc.

ComfyUI has found a place in the image pipeline design niche, but A1111 still seems like the best choice for new users who just want to spin up Stable Diffusion and generate some art for a D&D campaign or whatever.

Re:2023 was the year that GPUs stood still by brucethemoose2 on Friday December 29, 2023 @05:05PM (#38810802)
Thats because ComfyUI is also based on the old SAI backend, not diffusers like, say, VoltaML.