Show HN: Run Stable Diffusion Directly on iPhone (opens in new tab)

> The app should be able to run on iPhone 14 Pro

Can’t install it, says device is not supported.

Comparing the App Store listings, it looks like this app has a much simpler interface and far fewer features than Draw Things. Some users might prefer the simplicity of this app.

(Draw Things is by far the most advanced app that supports on-device Stable Diffusion on iOS devices and Apple Silicon Macs. It had a non-standard UI, but otherwise is really good.)

https://apps.apple.com/us/app/draw-things-ai-generation/id64...

To drawing things (yourself) it compares by not stealing. Yes, I know that’s not what you meant but with that name, I couldn’t not write it

It’s limited to iPhone 15

iPhone 15 Pro with 30 steps at 512x512 resolution (SD v1.5) should take around 35 seconds on iPhone 15 Pro with Draw Things. 1.5 mins are too slow. (I am the author of DT).

That's your 15 Pro at 100% compute, anything that makes it go to 100% compute for the same amount of time will make it as hot.

Not locally, though.

And they created about 50% of all useful npm packages too

https://www.npmjs.com/~sindresorhus

See: https://sindresorhus.com/amazing-ai#why-does-the-app-require...

"Developed exclusively for Apple silicon (M1/M2) - The app is NOT compatible with devices running on Intel chips."

I guess the app store redirected me to the desktop store?? Does not indicate an iphone 15 being required at all

Slightly OT but is there a decent setup for sprite generation out there? Non phone, I mean. It certainly seems like there's been some work in maintaining consistent style and even subjects across runs, does that work with 'character A walking frame 1, character A walking frame 2' etc anywhere yet?

This is a surprising thing when first working with these models (especially ones implementing NSFW filters, which are noisy). If you go check civitai.com you'll see that there's a lot of... well... porn. There's many LORAs to download but a very useful one ends up being the clothing slider. While I think the intention is to remove clothing, it is helpful in adding clothing. Unfortunately this doesn't look to support LORAs which are essential to getting many of those high quality images you see floating around.

My guess here is that the model is just trained on too many sexy pirates (it also has a propensity for producing asian women, which this model seems to do too). It does look like they support negative prompts but it requires you using "##" to separate positive and negative. Interesting design choice. You'll find these negative prompts helpful: disfigured, low quality, child, sexy, nude, extra limbs, ugly hands; and anything in the same vein. What works best is dependent on the base model and there is variance between different positive prompts. You may also have more success with something like automatic1111 which as long as you feel comfortable doing a git clone (which you're on HN, so I assume you are) then it'll be a better interface, but I don't know if there's a apple arm model or if baremetal has improved since last I checked.