AIBooru

Comments

Blacklisted:
[hidden]

Ralem said:

Bro how do you even go about making this? How would I get this pose with a different character using img2img? Sorry, complete noob who just started here. Also stunningly beautiful image.

It says img2img in the meta data, so we dont know how much of it is classic digital art and how much AI, but yes this is very nice and creative , very hard to do without controlnet

  • 0
  • Reply
  • [hidden]

    Sirius_fw said:

    @Ralem,
    It doesn't matter what model.

    It's just that some models have VEA built in, others don't.
    Without VAE they produce dim colors, some do not work at all.

    If you use WebUI by A1111 or WebUI Forge, then:
    Just download some VAEs, put them in the .\models\VAE folder and select them in the user interface.

    I recommend using these:
    https://huggingface.co/SiriusArchive/VAE/tree/main
    Which SDXL use for SDXL, which is different, use for SD1.5.

    P.S.
    In fact, just don't bother whether there is VAE inside the model or not, just use VAE manually, just in case.
    For SDXL this is not important at all, all VAEs there give almost the same result.
    For SD1.5 it depends more on VAE, but "perfect color VAE" usually gives a good result, I settled on it when I used SD1.5.

    P.P.S.
    Also, for anime models you almost always need to set the “Clip skip” parameter to 2.
    This has nothing to do with your colors problem, just saying in case you don't know.
    Almost all anime models work better with "Clip skip" 2.

    Thanks bro. And yeah I saw the clip skip in the tutorial. I think that I had a shitty model. Gonna try using the newer ones and if they have that issue I’ll download some of those. Appreciate it bro.

  • 1
  • Reply
  • [hidden]

    Ralem said:

    How to fix it? Sorry I’m brand new and was just completely following a tutorial. Using break domain v10 I believe for all of this style. Here’s the model I was using btw. https://civitai.com/models/135440/breakdomain
    Just bad model?

    @Ralem,
    It doesn't matter what model.

    It's just that some models have VEA built in, others don't.
    Without VAE they produce dim colors, some do not work at all.

    If you use WebUI by A1111 or WebUI Forge, then:
    Just download some VAEs, put them in the .\models\VAE folder and select them in the user interface.

    I recommend using these:
    https://huggingface.co/SiriusArchive/VAE/tree/main
    Which SDXL use for SDXL, which is different, use for SD1.5.

    P.S.
    In fact, just don't bother whether there is VAE inside the model or not, just use VAE manually, just in case.
    For SDXL this is not important at all, all VAEs there give almost the same result.
    For SD1.5 it depends more on VAE, but "perfect color VAE" usually gives a good result, I settled on it when I used SD1.5.

    P.P.S.
    Also, for anime models you almost always need to set the “Clip skip” parameter to 2.
    This has nothing to do with your colors problem, just saying in case you don't know.
    Almost all anime models work better with "Clip skip" 2.

    Updated

  • 2
  • Reply
  • [hidden]

    ElReyBlanco said:

    Seems desaturated, have you tried using VAE?

    What is that? Literally just started yesterday and was using this model a tutorial told me. Can you explain that a little more? Whenever I used this model it always seems to come out like that. It’s my favorite model when it comes to the actual art but the coloring looks kinda bad. Here’s the model I was using btw:
    https://civitai.com/models/135440/breakdomain

    Updated

  • 0
  • Reply
  • [hidden]

    deadsitelmao said:

    imagine having a dead site and STILL power tripping banning people. lmao. last bit of any interaction you'll be gettin on this site in a while from anyone, but go ahead and ban this one too lmao

    You need to touch grass, you seem to have mistake your ego trip as a mod's power trip.

    Imagine being so petty about auto delete posts(that could be appealed) which happened more than a week ago that you feel the need to create new accounts just to get back at a mod's neutral comment.

    If a post is rejected and you can't be bothered to ask for feedback(there is a forums for that) to improve in future uploads or ask for appeal politely, maybe you should learn to cope with rejects or leave the posting to the rest.

    Let me give you some feedback for your last 2 post:
    post #84065 - The resolution is low, grainy, blurry and the colors are also muted, it does not seem like an aesthetic choice, upsize and vae was not used. Not only that, the left leg seems to spilt into two, and the loop keep clipping her hands and merging it into her vagina.
    post #84064 - Same thing, low res, grainy, blurry, muted colors, does not seem like an aesthetic choice, also no upsize and vae. Artwork is great, could had been approved if it was an upsized image, but as a video, this quality is no longer consider good for AI generation, last year maybe, but now, no. Still, if it was asked for appeal NICELY, the mod may have allowed it.

    Regardless, it is too late to appeal anything after you chose to burn the bridges.

  • 0
  • Reply
  • [hidden]

    mooksmill said:

    cringe mod posts cringe photos and deletes good posts makes so much more sense.

    Thanks for the confirmation that I'm cringe, good to have that. Also I didn't personally delete your posts. The system deletes posts automatically after 3 days if they aren't approved.

  • 4
  • Reply
  • [hidden]

    Lyren said:

    If you know the model, why haven't you tagged it? There's no reason to not tag it and it seems like none of your uploads (at least the recent ones) don't have it for some reason.

    Sorry! Ill be doing that from now on

  • 2
  • Reply
  • [hidden]

    maimaimai said:

    The hands only look like that because of the watercolors painting style.
    This is not a generation flaw at all.

    The girl's hands aren't the only issue though. The two near her on the right side have fused arms.

  • 1
  • Reply
  • [hidden]

    the uploader claim to be calling an aibooru extractor by providing a link and not uploading the scaled version manually.

    I don't know what you mean by this tbh or know what you're getting at. But no I don't know which link I posted into the uploader @maimaimai, contact or mention a mod/admin of this site with any issues I guess.

  • 1
  • Reply
  • [hidden]

    I did a bit more research on it.

    The difference between the image in the current post and e.g. this one https://civitai.com/images/1317705 (which is PNG) is that the former is a civitai on-site generation and the latter is an external generation.
    It seems that "domestic" civitai generations are now(?) only provided in a jpeg format for some reason.
    screenshot 1 screenshot 2

    However, this is still an AIBooru problem since the original=true link return a different image (even if it's a JPG) but the uploader claim to be calling an aibooru extractor by providing a link and not uploading the scaled version manually.
    Maybe there is still some difference in how /posts/, /images/ and direct image links are handled.

    @Ocean3
    Do you remember what that link looked like?
    1. https://civitai.com/images/24358171
    2. https://civitai.com/posts/5440141
    3. https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/1d365646-7417-43c0-9b97-31ebb76c7f5b/width=700,original=false//KK0DRRHKJPVKMGZT8XAZKE0WG0.jpeg

  • 0
  • Reply
  • [hidden]

    maimaimai said:

    The problem with compressed civitai images still persists?.. 1.51 MB JPG

    Show
    URL:		https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/1d365646-7417-43c0-9b97-31ebb76c7f5b/original=true
    Content-Type:	Length: 1579835 (1,5M) [image/jpeg]
    Format:		/dev/shm/gmw5VAfV JPEG 832x1216+0+0 DirectClass 8-bit 1.5Mi 0.000u 0:01
    MD5:		70434f5c6a43d7c58a42804929a72630  -
    URL:		https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/1d365646-7417-43c0-9b97-31ebb76c7f5b/width=1200
    Content-Type:	Length: 191667 (187K) [image/jpeg]
    Format:		/dev/shm/gm8UhwE7 JPEG 1200x1754+0+0 DirectClass 8-bit 187.2Ki 0.000u 0:01
    MD5:		a78287a52d7e18edb7195246e87a89a2  -

    (this post md5:a78287a52d7e18edb7195246e87a89a2, https://aibooru.online/media_assets?commit=Search&search%5Bai_tags_match%5D=md5%3Aa78287a52d7e18edb7195246e87a89a2)

    @Ocean3 did you knowingly upload the 1200x JPG or just pasted the https://civitai.com/images/24358171 link in the upload form?

    I just pasted the link like I had in the past. I don't know what civitai has done on their end, but on their site images don't even display metadata on post for whatever reason. But then they did the next day on different uploads 🤷‍♂️. I didn't realize this was a .jpg which is probably what they switched to I guess. Seemed like the full resolution though. @maimaimai

  • 1
  • Reply
  • [hidden]

    The problem with compressed civitai images still persists?.. 1.51 MB JPG

    Show
    URL:		https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/1d365646-7417-43c0-9b97-31ebb76c7f5b/original=true
    Content-Type:	Length: 1579835 (1,5M) [image/jpeg]
    Format:		/dev/shm/gmw5VAfV JPEG 832x1216+0+0 DirectClass 8-bit 1.5Mi 0.000u 0:01
    MD5:		70434f5c6a43d7c58a42804929a72630  -
    URL:		https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/1d365646-7417-43c0-9b97-31ebb76c7f5b/width=1200
    Content-Type:	Length: 191667 (187K) [image/jpeg]
    Format:		/dev/shm/gm8UhwE7 JPEG 1200x1754+0+0 DirectClass 8-bit 187.2Ki 0.000u 0:01
    MD5:		a78287a52d7e18edb7195246e87a89a2  -

    (this post md5:a78287a52d7e18edb7195246e87a89a2, https://aibooru.online/media_assets?commit=Search&search%5Bai_tags_match%5D=md5%3Aa78287a52d7e18edb7195246e87a89a2)

    @Ocean3 did you knowingly upload the 1200x JPG or just pasted the https://civitai.com/images/24358171 link in the upload form?

  • 0
  • Reply
  • [hidden]

    Story in image #1:

    A loli with very long beautiful black hair who finds herself deep inside a random dungeon, she is completly nude and the only piece of clothing she have on her is a form of a white t-shirtdress, which is very loose and comfy. Though ain't sure where in the dungeon she is. She is certain that she is in a dungeon who share a similar ecosystem to that of another familiar cave. This relieves her.

  • 1
  • Reply
  • [hidden]

    Lyren said:

    If you know the model, why haven't you tagged it? There's no reason to not tag it and it seems like none of your uploads (at least the recent ones) don't have it for some reason.

    This reminds me, how do I add new tags for models/checkpoints?

  • 1
  • Reply
  • [hidden]

    hjqjjwbeb said:

    Pony, autismmix

    If you know the model, why haven't you tagged it? There's no reason to not tag it and it seems like none of your uploads (at least the recent ones) don't have it for some reason.

  • 2
  • Reply
  • [hidden]

    Nur said:

    I remember I got easily some Lovecraft's on LeonardoAI service a year ago, so I guess it is a thing of censorship.

    Maybe. Anyway I wouldn't entrust this task to any base model because all base models on my memory didn't like any kind of likeness. In my opinion it's better to use LoRA or IP-adapter for sure.

  • 0
  • Reply
  • [hidden]

    aidistef said:

    I think he is a really die hard concerning AI generating. Well, I tried to get a light bulb in some cool mystic environment and accidentally summoned this abyss demiurge. Even Cthulhu might be scared of him.

    I remember I got easily some Lovecraft's on LeonardoAI service a year ago, so I guess it is a thing of censorship.

  • 0
  • Reply
  • [hidden]

    Nur said:

    This reminds me, I could not get Lovecraft on Dall E 3 some months ago.

    I think he is a really die hard concerning AI generating. Well, I tried to get a light bulb in some cool mystic environment and accidentally summoned this abyss demiurge. Even Cthulhu might be scared of him.

  • 1
  • Reply
  • [hidden]

    You're work is amazing! I have no idea how you get such good results, but I find myself checking on here everyday because of it. Please do more of these progression sets! Cute girls getting loved and filled with cum!

  • 2
  • Reply
  • [hidden]

    noppersnop said:

    Very well good sir. Let me reiterate my previous statement and articulate my point with greater precision . For you see, by saying "God damn the amount of pixels" i was praising this particular image for the quality and excellence of various small details, fine textures as well as brilliant lighting and colour schemes. And not simply implying the resolution of the image is big.

  • 1
  • Reply
  • [hidden]

    iodoff said:

    its small

    Very well good sir. Let me reiterate my previous statement and articulate my point with greater precision . For you see, by saying "God damn the amount of pixels" i was praising this particular image for the quality and excellence of various small details, fine textures as well as brilliant lighting and colour schemes. And not simply implying the resolution of the image is big.

  • 5
  • Reply
  • 1 2 3 4 5 6 7