Show HN: Stable Diffusion v2 web interface

On AWS, a g5 instance costs $1/hr. I can generate roughly 10 images per minute (should be able to get this down with some optimization), so 600 images per hour, so the cost per image is 1/6 of a cent, before adding overhead (idle time, start up/shut down).

Source: I run a similar project: https://synapticpaint.com/

I also offer dreambooth model training for around $2-$4 / model as well as inference on custom dreambooth models. Inference on custom models is where things get a little tricky because if users are using different models and you're loading up new models all the time just to generate 6 images, then that quickly becomes the majority of the work load, drastically pushing up the inference cost. I haven't solved this problem yet. If you have any great ideas, feel free to email me (email in profile)!

At the beginning it was just burning money, but it stars to turn into profit.

The only secret to making it affordable is to autoscale based on a current image generation traffic. It runs on a mix of Tesla V100 and RTX 3090 from runpod.io vast.ai and Lambda Labs.

I actually went through a couple of iterations with it, starting as completely free service, then offering one time payments for image credits and now settled on subscriptions as I see there is a demand for the product. Especially AI Editor[1] which I think offers a unique value to the users.

[1] https://getimg.ai/editor

Stable diffusion only needs 4GB of VRAM to run on the low end so you can rent low-end consumer GPUs (nvidia RTX for example) for around $0.10 an hour to do the renders.

https://vast.ai/ (not affiliated)

I'd love to know this as well.

Exactly. Put that bullshit up front before I waste time entering a prompt so I know not to bother.

It's a measure to prevent multi accounts. Some people really overuse free offering. Either your domain/IP is on a spam list or your email server may be misconfigured.

They took out a bunch of artist references, and a bunch of celebrities. The two things that made SD stand out. It's no longer the fun one.

Agreed. I like making abstract stuff, much more fun to be had with v1.5.

It seems like v2 is more photorealistic but it more often fails to follow any complex prompt.

I don't see this as baiting. The link to a tool page was shared. It's transparent on the homepage and in the header. The text to image page just shows how it works without the need to create an account.

FWIW, you're not the only one. On our product, we experimented adding login when the user tries to use any of our tools and something like ~60-70% of users dropped off. So essentially, whoever implements that is killing their user funnel at the very beginning which I'm guessing will have larger effects down the road (fewer users experience "magical moments" which leads to less word-of-mouth, etc).

On the flip side though, I'm sure it may help metrics in the short term especially since it's expensive to offer a service like this (which requires expensive GPU servers).

Does it generate images though? I gave it a prompt around an hour ago and it's still just spinning.

But do you allow high res nsfw Emma Watson prompts?