Personal View site logo
Make sure to join PV on Telegram or Facebook! Perfect to keep up with community on your smartphone.
Please, support PV!
It allows to keep PV going, with more focus towards AI, but keeping be one of the few truly independent places.
Where we are going we won't need roads... ooopsie.. photographers anymore
  • image

    image

    image

    image

    image

    image

    sa7269.jpg
    506 x 508 - 64K
    sa7268.jpg
    505 x 504 - 53K
    sa7262.jpg
    501 x 508 - 65K
    sa7263.jpg
    501 x 505 - 43K
    sa7264.jpg
    508 x 508 - 69K
    sa7265.jpg
    508 x 505 - 77K
  • 38 Replies sorted by
  • New stuff

    image

    image

    image

    image

    image

    image

    image

    image

    sa7392.jpg
    1020 x 1012 - 134K
    sa7393.jpg
    1020 x 1020 - 113K
    sa7394.jpg
    1021 x 1006 - 153K
    sa7396.jpg
    1014 x 1013 - 121K
    sa7397.jpg
    1016 x 1015 - 131K
    sa7398.jpg
    1011 x 1016 - 104K
    sa7395.jpg
    1015 x 1019 - 96K
    sa7399.jpg
    1020 x 1018 - 126K
  • Well i'm impressed...like i said it's a learning curve.

  • SD 1.5 with my style is much worse compared to MJ, but sometimes not so bad

    image

    image

    image

    sa7389.jpg
    507 x 509 - 61K
    sa7388.jpg
    510 x 509 - 70K
    sa7390.jpg
    509 x 511 - 69K
  • Mot mine, but nice SD with custom mixed models

    image

    image

    sa7382.jpg
    720 x 1021 - 81K
    sa7383.jpg
    714 x 1048 - 107K
  • Some of my Midjourney V4 art

    image

    image

    image

    image

    image

    image

    image

    image

    sa7386.jpg
    800 x 800 - 137K
    sa7380.jpg
    800 x 789 - 160K
    sa7379.jpg
    800 x 800 - 125K
    sa7376.jpg
    800 x 803 - 129K
    sa7377.jpg
    800 x 832 - 142K
    sa7378.jpg
    800 x 804 - 112K
    sa7387.jpg
    800 x 810 - 101K
    sa7381.jpg
    626 x 628 - 57K
  • Was playing just a little but guess it's a learning curve. I'm not impressed by AI...

    IMG_20221128_123745_303.jpg
    512 x 512 - 32K
    over-mountains-crevasses-smoking-and-fire-breathing-volcanoes-flight-slows-down-the-thunder-of-roari (2).jpg
    512 x 512 - 47K
  • I've been playing with SD quite a bit, and have to say it's probably one of the best tools for mood boards, I'll explain why.

    Due to the data dragnet style of training, it tends to generate imagery that is stereotypical. So it kinda forces you to be creative with prompts, and to think about what image you really want, and what constitutes that image.

    "Person sitting on chair" quickly turns into: "middle aged man sitting on an old wooden chair, in a small room with wall paper, lit through an open window."

    Then you can get an infinite amount of permutations of this. Just brilliant for mood board generation!

    That's a very good point indeed! Very useful indeed for mood boards. Maybe with a bit more development and tailored suggestions it could even be handy for quick and dirt storyboards as well.

  • Shishkin style

    image

    image

    image

    image

    image

    image

    image

    image

    image

    sa7356.jpg
    510 x 510 - 62K
    sa7358.jpg
    509 x 513 - 58K
    sa7357.jpg
    507 x 507 - 59K
    sa7351.jpg
    506 x 505 - 60K
    sa7354.jpg
    508 x 506 - 70K
    sa7350.jpg
    506 x 507 - 65K
    sa7349.jpg
    508 x 502 - 51K
    sa7348.jpg
    507 x 502 - 52K
    sa7352.jpg
    508 x 505 - 75K
  • image

    image

    image

    sa7333.jpg
    506 x 503 - 89K
    sa7332.jpg
    509 x 508 - 76K
    sa7331.jpg
    509 x 507 - 89K
  • image

    image

    image

    image

    image

    sa7339.jpg
    505 x 500 - 43K
    sa7337.jpg
    485 x 500 - 55K
    sa7336.jpg
    479 x 492 - 73K
    sa7335.jpg
    504 x 498 - 72K
    sa7334.jpg
    502 x 499 - 62K
  • image

    image

    image

    sa7342.jpg
    507 x 501 - 45K
    sa7341.jpg
    504 x 499 - 58K
    sa7340.jpg
    501 x 506 - 53K
  • image

    image

    image

    sa7345.jpg
    506 x 505 - 34K
    sa7344.jpg
    501 x 499 - 35K
    sa7343.jpg
    505 x 505 - 40K
  • @mitkoo

    I use hosted thing.

    But better you need 11GB or better VRAM and some high speed GPU with fast single precision CUDA.

    So, 3080, 3090, 3090 Ti.

    Or new 4090.

    note that Stable Diffusion v1.5 is still not public for download and local use (and this is that is used here)/

  • @Vitaliy Wow! How much RAM do you need for your cool experiments?

  • On lotus flowers

    image

    image

    image

    image

    image

    image

    image

    image

    image

    sa7326.jpg
    509 x 506 - 65K
    sa7321.jpg
    507 x 503 - 51K
    sa7325.jpg
    508 x 505 - 62K
    sa7317.jpg
    506 x 506 - 41K
    sa7319.jpg
    509 x 506 - 53K
    sa7324.jpg
    507 x 507 - 70K
    sa7318.jpg
    502 x 503 - 49K
    sa7323.jpg
    502 x 504 - 61K
    sa7320.jpg
    505 x 504 - 59K
  • Metals and colored neodymium magnet balls

    image

    image

    image

    image

    image

  • Experiments with mosaic and materials

    image

    image

    image

    image

    image

    image

    image

    image

    sa7310.jpg
    508 x 507 - 85K
    sa7309.jpg
    504 x 506 - 86K
    sa7308.jpg
    501 x 508 - 89K
    sa7307.jpg
    505 x 502 - 61K
    sa7306.jpg
    509 x 506 - 113K
    sa7305.jpg
    510 x 505 - 80K
    sa7304.jpg
    511 x 509 - 95K
    sa7303.jpg
    504 x 503 - 44K
  • Erotic Ice Art

    image

    image

    sa7301.jpg
    510 x 508 - 36K
    sa7302.jpg
    507 x 483 - 35K
  • image

    image

    image

    sa7298.jpg
    503 x 508 - 34K
    sa7299.jpg
    500 x 500 - 38K
    sa7300.jpg
    503 x 497 - 54K
  • image

    image

    image

    image

    image

    sa7293.jpg
    511 x 505 - 43K
    sa7294.jpg
    507 x 505 - 53K
    sa7295.jpg
    506 x 502 - 42K
    sa7296.jpg
    508 x 498 - 31K
    sa7297.jpg
    509 x 502 - 38K
  • Mathematically it looks like this

    image

    Where peaks are visually pleasing images (as it thinks of them). As people trained NN to provide them that they want (most probably using back propagation learning).

    sa7292.jpg
    455 x 432 - 29K