← Back to context

Comment by avocado2

4 years ago

web demo for stable diffusion (txt2img): https://huggingface.co/spaces/stabilityai/stable-diffusion

github with web ui: https://github.com/hlky/stable-diffusion

dev repo (more features, may have bugs): https://github.com/hlky/stable-diffusion-webui

repo with docker: https://github.com/AbdBarho/stable-diffusion-webui-docker

colab repo (new): https://github.com/altryne/sd-webui-colab

can also run it in colab (includes img2img): https://colab.research.google.com/drive/1NfgqublyT_MWtR5Csmr

demo made with gradio: https://github.com/gradio-app/gradio

Why do you keep posting the same comment under every SD post? It doesn't contribute to the discussion, and it's not very relevant to the OP. Some of the links don't even work anymore.

Or if you don’t want to tweak anything, just use the hosted version? https://beta.dreamstudio.ai/

  • It's pretty expensive. They give you 100 free credits but I burned though that in about 10 minutes just trying to figure out how things worked. Didn't get any nice images.

    After that, it's $1 per 100 credits, so about $6 an hour maybe.

    • One credit is one regular-sized picture generation. If you want to make it bigger or run more steps (in my experience, this is less useful than it would seem), then it can run up to 3 or more credits per generation. That's still 3 cents a picture. Compared to Dall-E and even Midjourney, that's crazy cheap.

    • I put $10 in and it’s lasted a long time, but I don’t generate images every day. Cheaper than getting a good graphics card, anyway.