Hacker News
Automatic1111 for Apple metal, 40% speed up sd1.5
46 points by dmikey831
ago
|
18 comments
vanillax
|next
[-]
SD 1.5 is so insanely old at this point im not sure the point of this when you have Mini Max H3 on metal https://news.ycombinator.com/item?id=49252179
dmikeyanderson
|root
|parent
|next
[-]
old but relevant, it's like a production system. We can continue to tune and squeeze 1mp pictures out of it in high quality on relevant localized hardware without breaking a sweat. 1-3 seconds on a m3 system, and then cascade of tooling below stays the same.
SV_BubbleTime
|root
|parent
|previous
[-]
A1111 also had its time. Comfy takes a couple hours to learn, and then it’s vastly superior. Like, if you are already on Mac there is no reason to also kick yourself in the face trying to go back to 1111.
qclibre22
|root
|parent
|next
[-]
There's also sdcpp ( https://github.com/leejet/stable-diffusion.cpp ) . It is for people that know command line shells like bash or Powershell. SDCPP is like llama.cpp but it is for using text to image AI models. Not everyone likes the node/graph programming interface in Comfy or a Webpage interface. Some people need these GUI/web interfaces and get lost and frustrated in shell scripting.
dmikeyanderson
|root
|parent
[-]
Totally and sdcpp and drawthings were inspiration for this work. It's not just about the UI, there's a whole stack of plugins, APIs etc. It would be a bigger shift, than just use other UI. Composition etc.
Plus this was fun to learn where the attention and time spent is eating up. I plan to git into the UNet, and then do some Multi-Model Memory Attention tuning as well, for Refining and Inpaint Swaps for the 8Gb Macs.
vunderba
|root
|parent
|previous
[-]
A1111 (or rather Forge Neo at this point) can still be pretty useful (for a Windows user) if somebody just want a batteries-included approach because it makes it trivial to move back and forth between masking, manual inpainting, tacking on a high‑res fix and/or upscale, and swapping things out on the fly quickly.
Caveat: No idea how well A1111 and its variants function on Mac though.
These days I mostly use ComfyUI because after building out a node‑based workflow, it’s easy to export as a JSON file with websocket outputs that I can integrate into my programs.
https://github.com/Haoming02/sd-webui-forge-classic/tree/neo
jurgenburgen
|next
|previous
[-]
Trigger warning: AI content.
trencedamp
|root
|parent
[-]
If anyone is triggered by AI content they surely avoid HN
selectodude
|root
|parent
[-]
I love AI content. I hate content written by AI.
It's not serious. It shows that the author doesn't care about showing what he's up to.
He cares about making content to post on a blog.
And that's disrespectful to the reader.
dmikeyanderson
|root
|parent
[-]
I'm not an editorialist, I spend my time on the software side of things, but want a detailed technical journal of what happened to achieve the gains. Also why the github link is near the top of the intro which I wrote. I'm not trying to disrespect the reader, but the time of the user of the software. Appreciate your view. I've made adjustments.
jurgenburgen
|root
|parent
[-]
I spend all day reading AI generated text in one form or other in my day job. When I come to unwind in HN I’m not interested of more of the same. Seeing “load-bearing”, “landing things”, “it’s not x, it’s y” makes me think of work. I honestly would rather read human text with typos and warts.
IronWolve
|next
|previous
[-]
Automatic1111 wasnt being updated, people moved to Forge Neo, ComfyUI and Maestro.