Jump to content

Real Human Bean

Members
  • Posts

    1,002
  • Joined

Everything posted by Real Human Bean

  1. Looks like Midjourney v4 to me
  2. Thanks - yeh that was just my first little fool around with samplebrain output chucked into some samplers. I don't really make much glitchy stuff like this tbh, got pretty bored of it a long time ago.
  3. Stable Diffusion is out in the big wide world now: https://huggingface.co/spaces/stabilityai/stable-diffusion
  4. btw guys this is going to be possible with music and video soon
  5. AOTY https://hudsonmohawke.bandcamp.com/album/cry-sugar
  6. !dream "a painting of an extremely concerned artist by an extremely concerned artist " -n 8 -i
  7. When I first got access you had unlimited prompts and each generation returned 10 variations, then it was cut to 50 prompts per day with 10 variations returned, then 50 per day with 6 variations, then 50 with 4 and now the current situation of 15 per month or you have to pay (which I'm not doing as I way prefer to spend money on using fast GPUs on Google Colab to run diffusion models).
  8. Loads! I've generated around 3500 images and like a few hundred of them. I post a small fraction of them in this thread:
  9. DALL-E 2 was originally putting out 10 1024x1024 images in around 30 seconds nut now the number of variations has been reduced to 4 and it usually takes slightly longer.
  10. Take a look at the animations. What do you think? Typing a prompt into DALL-E 2 will output images but that doesn't have to be the beginning and end of your process. I tend to prefer other tools (JAX, Disco Diffusion, Pytti, VQGAN etc.) as they're more customisable and enjoy the more abstract output.
  11. Yes. Got in as part of the Artist Access program in May. ?Post AI stuff here sometimes.
×
×
  • Create New...

Important Information

We have placed cookies on your device to help make this website better. You can adjust your cookie settings, otherwise we'll assume you're okay to continue.