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
  • May be it is stupid and can't play a little, like artist will do?

    image

    image

    image

    sa7258.jpg
    509 x 506 - 44K
    sa7259.jpg
    507 x 504 - 49K
    sa7260.jpg
    507 x 510 - 64K
  • How about extremely complex scene - look at sunset snowy and misty forest through frosty window

    image

    image

    sa7266.jpg
    498 x 494 - 71K
    sa7267.jpg
    505 x 505 - 63K
  • image

    sa7261.jpg
    506 x 509 - 60K
  • 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!

    Personally I don't think it's a competition to the human neural network. Not because it's not good enough, but because people tend to enjoy filming. It's a tool that we can use, just like a camera is a tool.

    Then again, when SD gets video, I wouldn't mind using it for b-roll. I don't really enjoy filming branches swaying all that much.

    Then again, "middle aged man" turns out to be "white middle aged man with a belly".

    middle_aged_man_sitting_on_an_old_wooden_chair__in_a_small_room_with_wall_paper__lit_through_an_open_Seed-88416_Steps-50_Guidance-7.5.png
    512 x 512 - 489K
    0.jpg
    512 x 512 - 14K
  • image

    image

    image

    image

    image

    1524394608_pencil_drawing_colorful_art_female_with_red_fully_transparent_underwear_and_large_straw_hat__looking_away_the_right_hand_touches_itself_in_an_intimate_place__road_going_till_horizon__yellow_sunflowers_along_the.png
    512 x 512 - 486K
    1711508014_pencil_drawing_art_black_and_white__tender_loving_female_with_very_big_blue_eyes_caressing_male_neck.png
    512 x 512 - 465K
    2692316513_pencil_drawing_art_black_and_white__tender_loving_female_with_very_big_blue_eyes_caressing_male_neck.png
    512 x 512 - 472K
    238565697_beautiful_female_with_red_transparent_dress_and_large_straw_hat__long_hair__looking_away__paved_road_going_till_horizon__yellow_sunflowers_along_the_road__green_fields_to_the_right_and_left_side__sunset_with_sun.png
    512 x 512 - 427K
    1080427678_pencil_drawing_colorful_art_female_with_red_fully_transparent_dress_and_large_straw_hat__looking_away__right_hand_lifts_the_dress__road_going_till_horizon__yellow_sunflowers_along_the_road__green_fields_to_the_.png
    512 x 512 - 425K
  • @alcomposer

    It is not about prompts only.

    I am using some initial seed image, sometimes specially modified, on each iteration you select one of 9 varients, change how much it can change overall image, change prompt, also paint some areas to change more, and such can be 10, 15, 20 iterations.

    It is an art tool.

    Note how I am able to make dress transparent.

    Or how I can add innuendo, make you feel that girl is showing her private part to the sunflower. It was intentional, and source image had been same as both other reg dress girl. Even her clothes are being set not only buy prompts, but iterated and also painted and changed.

  • Another thing that appeared last week:

    Made form this (many iterations in SD)

    image

    780164983_pen_drawing_black_and_white__art__beautiful_smiling_female_with_deep_bright_blue_large_eyes__long_eyelashes_with_mascara___red_nice_long_slightly_curly_hair__bright_red_lips.png
    512 x 512 - 434K
  • Slightly more of my experiments with art made using Stable Diffusion.

    It used specially processed initial photo.

    image

    image

    image

    image

    sa7284.jpg
    504 x 503 - 48K
    sa7283.jpg
    481 x 505 - 40K
    sa7286.jpg
    501 x 475 - 39K
    sa7285.jpg
    493 x 480 - 37K
  • Now, let's try to play with depth of focus and precise lighting, while keeping exact flowers specs we need

    image

    image

    image

    sa7287.jpg
    509 x 505 - 57K
    sa7288.jpg
    505 x 506 - 42K
    sa7289.jpg
    509 x 505 - 65K
  • @Vitaliy_Kiselev sorry, I didn't mean to say that the AI's have no value, or that they are not creative in their own right.

    Actually, quite the opposite.

    I see them as being an addition to photography, digital art, painting etc.

    AI art is its own thing, and quite different to photography, et al. Firstly, as you have shown it takes a completely different skill set, one of describing, keywords, seed imagery etc.

    I think as opposed to 'we don't need photographers anymore' possibly it is more like: 'we don't need stock anymore'. Shutterstock & Adobe must be worried big time.

    Regardless, it's it's own thing, and AI for AI's sake is a valid artform. One that should be explored outside of "AI makes photographers redundant".

    Have a look at this if you haven't already:

    The big take away, is if it was perfect, like shot on camera, it would loose the important painterly, glitchy aesthetic. Sometimes, its the imperfections that make it better.

  • @alcomposer

    It can be almost perfect, it can be some style.

    This thing integrates different things and you can mix them.

    You own mind is functioning similar to it - it gets small focused spot image and previous image and makes estimate based on your own knowledge.

  • 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
  • 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
  • image

    image

    image

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

    image

    image

    sa7301.jpg
    510 x 508 - 36K
    sa7302.jpg
    507 x 483 - 35K
  • 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
  • Metals and colored neodymium magnet balls

    image

    image

    image

    image

    image

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

  • @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)/