Try Stable Diffusion's Img2Img Mode

Post by francisduvivier » Mon, Aug 29, 2022, 12:32 PM UTC

kgwgk wrote: post #58

comex wrote: post #13

If you have a GPU with >4GB of VRAM and you want to run this locally, here's a fork of the Stable Diffusion repo with a convenient web UI: https://github.com/hlky/stable-diffusion It supports both txt2img and img2img. (Not affiliated.) Edit: Incidentally, I tried running it on a CPU. It is possible, but it took 3 minutes instead of 10 seconds to produce an image. It also required me to hack up the script in a really…

There are as well forks for the GPU in Apple’s M1 chips: https://github.com/magnusviri/stable-diffusion

Post by bjtitus » Mon, Aug 29, 2022, 1:15 PM UTC

francisduvivier wrote: post #121

kgwgk wrote: post #58

Earlier quoted context omitted.

There are as well forks for the GPU in Apple’s M1 chips: https://github.com/magnusviri/stable-diffusion

Anyone knows how fast this runs on an m1 macbook air?

Post by gitfan86 » Mon, Aug 29, 2022, 1:29 PM UTC

BatteryMountain wrote: post #111

comex wrote: post #13

If you have a GPU with >4GB of VRAM and you want to run this locally, here's a fork of the Stable Diffusion repo with a convenient web UI: https://github.com/hlky/stable-diffusion It supports both txt2img and img2img. (Not affiliated.) Edit: Incidentally, I tried running it on a CPU. It is possible, but it took 3 minutes instead of 10 seconds to produce an image. It also required me to hack up the script in a really…

Nvidia GTX 1660 Super with 6GB of VRAM. I do runs at 384px by 384px, with batch size of 1. Sampling method has almost no impact on memory. Using k_euler with 30 steps renders an image in 10 to 20 seconds. The biggest thing that affect rending speed is the steps and the resolution, so 512x512 with C 50 using ddim is much slower than 256x256 with C 25 using k_euler. The sampling methods run mostly in the same timelines…

Post by salawat » Mon, Aug 29, 2022, 1:39 PM UTC

natch wrote: post #36

I guess documentation and clarity of UX design are not big strengths of Hugging Face.

Post by BeFlatXIII » Mon, Aug 29, 2022, 2:09 PM UTC

deanCommie wrote: post #20

omginternets wrote: post #5

Earlier quoted context omitted.

I’m not gonna lie, I’m quite disappointed at all the anti-NSFW shenanigans.

I'm not gonna lie, I'm quite disappointed by the wilful obstinance on HN whenever there is a discussion of anti-NSFW or anti-racism filters that are present on today's artificial intelligence research. First, the filters are only on the interface. The research is public. That's why there has been an explosion of new implementations. You are welcome to run the code yourself and make the horniest model you like. But mo…