AIBooru Beta

Comments

Blacklisted:
[hidden]

@Patchouli use the tag "original" when the character in the image is totally original and does not come from any anime, comic or video game.
please take the time to at least tag the character in the image correctly.
if you don't remember their name use "character request" or "copyright request".

  • 1
  • Reply
  • [hidden]

    Koisee said:

    Understandable
    but why would his shoulder connect to her body and who is he? Why does he want to connect his shoulder to her body, sounds very lewd man!

    Once again, my broken English has trolled me.
    as I said in danbooru, English is not my main language, and a recurring problem I have is forgetting that the term "her" existed.
    I'm trying to correct this, but every now and then I slip a "him".

  • 4
  • Reply
  • [hidden]

    Blob said:

    With all due respect, I personally do not see what you are pointing out as a mistake. The anatomy seems to add up fine for me. Also is the personal opinion of poor anatomy really a reason to not approve of a post?

    I might be looking too deep into this, but here's what the shoulder kinda would look like without the straps and hair, and my attempt at showing how it kinda should look like: https://youtu.be/cI-End5jQwM (I'm not an expert but just my own thought to this).

    So the problem is that the neckline is dipping down with a downwards angle and in order it properly to connect to this shoulder here it has to an unnatural curve.

  • 1
  • Reply
  • [hidden]

    tremolo_measure said:

    this looks really cute.
    but I can't help but notice his shoulder (LEWD LEWD LEWD) that doesn't connect properly to her body.
    if you fix it, I will gladly approve it.

    Understandable
    but why would his shoulder connect to her body and who is he? Why does he want to connect his shoulder to her body, sounds very lewd man!

  • 3
  • Reply
  • [hidden]

    tremolo_measure said:

    this looks really cute.
    but I can't help but notice his shoulder that doesn't connect properly to her body.
    if you fix it, I will gladly approve it.

    With all due respect, I personally do not see what you are pointing out as a mistake. The anatomy seems to add up fine for me. Also is the personal opinion of poor anatomy really a reason to not approve of a post?

  • 0
  • Reply
  • [hidden]

    Gumtree917 said:

    Hi do you know where I can see AI Generations?

    You can go on Pixiv and search for AI-generated images. And don't forget to go in settings and turn on R-18 images and AI-generated images in searching filter. To start with, you can find the link to pixiv of "artist" of this image and find, that there is not two but hundreds of images by this "author"

  • 2
  • Reply
  • [hidden]

    Parameters for pre-inpainted image:
    yakumo yukari, (gap \(touhou\):1.2), (multiple eyes:1.1), smug, reaching out, foreshortening, blonde hair, long hair, floating hair, yellow eyes, mob cap, purple tabard, frills, white elbow gloves, white background, glory wall, through wall, stuck <lora:gaptouhou:1> <lora:glory_wall_front:0.2>
    Negative prompt: (Worst Quality, Low Quality:1.2), border, nsfw, skimpy, 2girls, grayscale, (watermark:1.2)
    Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7.5, Seed: 1899778733, Size: 960x544, Model hash: 51e4b0d5e1, Model: SoushikiV1.0, VAE hash: f88e1cfb7c, VAE: WD1-4-kl-f8-anime2-bless09.ckpt, Denoising strength: 0.51, Clip skip: 2, ADetailer model: face_yolov8n.pt, ADetailer confidence: 0.3, ADetailer dilate erode: -28, ADetailer mask blur: 8, ADetailer denoising strength: 0.4, ADetailer inpaint only masked: True, ADetailer inpaint padding: 12, ADetailer version: 23.11.1, Hires upscale: 2, Hires steps: 15, Hires upscaler: 4x_NMKD-YandereNeoXL_200k, Lora hashes: "gaptouhou: 37dbd26a2507, glory_wall_front: 144896657680", Version: v1.6.0-2-g4afaaf8a

  • 3
  • Reply
  • [hidden]

    This image is the final result after some minor edits to the toes on the right foot and the ankle on the left leg then upscaling with tiled diffusion and only includes the upscale parameters. Here are the parameters for the original txt2img generation:

    Prompt: kirisame marisa, solo, sitting, on ground, (barefoot:1.2), (soles:1.2), knees up, braid, toe scrunch, (foot focus, foreshortening:1.2), legs, blonde hair, yellow eyes, witch hat, black dress, waist apron, neck ribbon, hair ribbon, messy hair, hair between eyes, glowing eyes, dark background, somber expression, depressed, looking down BREAK dark energy, reflection, colorful, vibrant colors, portal to another world, limited palette, blue
    Negative prompt: (Worst Quality, Low Quality:1.2), border, nsfw, skimpy, grayscale, 2girls, (watermark:1.2)
    Sampler: DPM++ 2M Karras
    Seed: 1387458770
    Steps: 20 + 15 Hires
    Cfg Scale: 7.5

  • 2
  • Reply
  • [hidden]

    sulph said:
    Prompt? This is really nice!

    very detailed, 1girl, solo, full body, (girl stands at headquarters, (points to astronomical map) with her hand, astronomical map on wall), glasses, medium skirt, bob cut red hair, astonished look, dynamic angle,
    Negative prompt: [(negative_hand-neg:1):0.2], (worst quality:1.4), (low quality:1.4), extra limbs, text, name, signature, logo, bad anatomy, disfigured, watermark, jpeg artifacts, bad eyes, ((lips, tooth)), navel, letterbox
    Steps: 30, Sampler: DPM++ 2M SDE Karras, CFG scale: 7, Seed: 2558751036, Size: 1920x1080, Model hash: 2523c9050f, Model: breakdomainxl_V05g, VAE hash: 551eac7037, VAE: sdxl_vae.safetensors, Clip skip: 2, Version: v1.6.0-2-g4afaaf8a, Hashes: {"vae": "551eac7037", "embed:negative_hand-neg": "73b524a2da", "model": "2523c9050f"}

    Hires with Kohya Hires.fix in size 1920x1080.

    Then processed with DarkSushiMix and corrected the hands by inpaint, and then did FHD->4k (multidiffusion with regional prompt) and corrected the hands by inpaint again.

  • 2
  • Reply
  • [hidden]

    antlers_anon said:

    upscale is a little blurry but these are some high quality pirates nonetheless, would plunder with

    Yeah, I'd love to be able to generate higher res, but my poor little 3070 runs out of ram if I go higher than 1280x1280 or 1024x1536. I've tried the SD upscale script, but it tends to throw too much cursed looking noise into the image, so I stick to ESRGAN to smooth over some of the leftover diffusion noise.

  • 2
  • Reply
  • [hidden]

    The name is a reference to a poem by Indonesian poet Sapardi Djoko Damono about the immortality of man and the ephemeral nature of time.

    Yang fana adalah waktu. Kita abadi:
    memungut detik demi detik, merangkainya seperti bunga
    sampai pada suatu hari
    kita lupa untuk apa.
    “Tapi, yang fana adalah waktu, bukan?”
    tanyamu.
    Kita abadi.

  • 2
  • Reply
  • [hidden]

    antlers_anon said:

    @zakiry It was a test version of antlersmix_11. I must have forgot to tag it, fixed now. I didn't end up liking this mix so I didn't post it anywhere, but here most of the style comes from the loras (mainly dreamwave - it's on civitai) so any semi-realistic model should look similar I think.

    You still remember how you created antlersmix_11?

  • 0
  • Reply
  • [hidden]

    antlers_anon said:

    @zakiry It was a test version of antlersmix_11. I must have forgot to tag it, fixed now. I didn't end up liking this mix so I didn't post it anywhere, but here most of the style comes from the loras (mainly dreamwave - it's on civitai) so any semi-realistic model should look similar I think.

    <3

  • 0
  • Reply
  • [hidden]

    @zakiry It was a test version of antlersmix_11. I must have forgot to tag it, fixed now. I didn't end up liking this mix so I didn't post it anywhere, but here most of the style comes from the loras (mainly dreamwave - it's on civitai) so any semi-realistic model should look similar I think.

  • 2
  • Reply
  • [hidden]

    Anonymous407 said:

    I may as well ask because I’m interested, but are these softwares free to use?

    To begin with, these are not software.
    Simply put, LoRAs are models plus additional training data that you can create yourself and use to generate images.
    This image is generated using several LoRAs created by others.
    So, I have listed the LoRAs I used to generate this image in the previous comment.
    The website civitai, which I often use to find LoRAs, allows you to download these for free.

  • 3
  • Reply
  • [hidden]

    Ocean3 said:

    good hand 👌

    Only the pinky finger was inpainted as it was bent too much to the right but no manual edits at all! (The only manual edit in this whole pic was removing the background)

    Your models are just something else, gotta love 'em.

  • 1
  • Reply
  • 1 8 9 10 11 12 13 14 15 16