all / g / s / fur / art / ai / 3dcg / f / rp / req / p2p / dis / lit / kaki chat
[Settings] [Home] [Catalog] [Search] [Thread list] [Stats] [Reports] [Watcher] [PMs] [Admin]
[Return] [Bottom]

Posting mode: Reply
BBCode
(for deletion)
  • Allowed file types are: gif, jpg, jpeg, png, webp, webm, mp4
  • Maximum file size allowed is 25000 KB.
  • Images greater than 255 * 255 pixels will be thumbnailed.
  • 141 unique users in the last 30 minutes (including lurkers)
    File: 00360-4239618668 v3.jpg
    (197 KB, 960x1264) ▶
    202187
    No.13910 [Report] AS
    ▶
    Finally a new version of the GuRO Checkpoint Model is here.
    And this time it also possible to download it as a seperate LoRA.


    I have successfully trained a guro checkpoint built upon the WAI 14.0 base.
    I added 1000 synthetic images to better teach it some concepts. Bleeding of concepts decreased compared to the previous version.
    This model was trained on a total dataset of 8,000 images.

    A comprehensive list of the tags used during training can be found here:
    https://rentry.co/r-18G_illustrious_tags_V2

    It is not perfect but much better than the previous iterations. Including, but not limited to:
    Hanging.
    decapitation and amputee
    Head used as a sex toy from both directions,
    eye penetration
    nipple penetration
    ear penetration
    brain penetrarion
    Cannibalism cooked body. with face and not
    impalement
    impaled and roasted over fire
    harakiri and evisceration
    debreasting
    drowning
    and more.

    For the complete list of tags consult here:

    Fine tune checkpoint.
    Civitai: https://civitai.com/models/1794928?modelVersionId=2499924
    Link to the LoRA. Reminder that the LoRA does not work as well as the fine tune, reccomended weight is 0.8. Depending on the tags it can vary between 0.6 and 1.0.
    Civitai: https://civitai.com/models/2221022


    I have been banned on pixiv for the time being.

    My old account got banned on pixiv.
    You can contact me through this one
    https://www.pixiv.net/en/users/101800918
    Viewing last 50 posts
    >>
    No.18146 [Report]
    ▶
    File: 00032-2995332511.png
    (2.06 MB, 1456x1456) ▶
    2160226
    >>18145
    TY again. I've been enjoying the lora version :)
    >>
    No.18148 [Report]
    ▶
    File: _Illustrious_20260414-131653_00001_.jpg
    (253 KB, 2008x2008) ▶
    259137
    One more fobia
    >>
    No.18189 [Report]
    ▶
    File: _Illustrious_20260415-141943_00001_.jpg
    (218 KB, 2344x1720) ▶
    223620
    How to generate more realistic organs?
    >>
    No.18190 [Report]
    ▶
    >>18148
    >>18189
    can you make the guts explode outwards?
    >>
    No.18200 [Report]
    ▶
    File: 00113.jpg
    (509 KB, 2048x2048) ▶
    521465
    >>
    No.18206 [Report]
    ▶
    >>18200
    Love the Hinata post. Awesome!

    I discovered that this model/Lora works better when used with a Controlent of a guro image.
    >>
    No.18218 [Report]
    ▶
    File: _Illustrious_20260417-111234_00001_.jpg
    (296 KB, 2344x1720) ▶
    303582
    >>18190
    Explosives are unstable...
    >>
    No.18222 [Report]
    ▶
    File: _Illustrious_20260417-173430_00001_.jpg
    (285 KB, 2008x2008) ▶
    292842
    >>18190
    It was hard...
    Some useful info:

    ### working tags: ###
    longitudinal_bisection,
    spread torso,
    uterine prolapse,
    empty chest cavity,
    organs,
    butchering,
    intestines,
    ovaries,
    heart organ,
    liver,
    bowel explosion,
    blood fountain,
    bursting stomach,
    eviscerated,
    severed uterus,
    guts explosion,
    organs explosion,
    carving,
    low guro,
    spinal cord,
    ribs,

    ### useless/bad tags: ###

    ryona,
    spread torso,
    sliced,
    carved,
    stitches,
    meat removed,
    guts,
    lungs explosion,
    kidneys explosion,
    entrails bursting,
    >>
    No.18224 [Report]
    ▶
    File: image.png
    (307 KB, 1462x659) ▶
    314429
    I’ve been struggling for over an hour trying to create a decent or even passable image, but to no avail. All the results are blurry and of poor quality. I don’t know how to go about it.


    Using Deepl For translation
    >>
    No.18225 [Report]
    ▶
    >>18224
    The model is SDXL finetuned so you need to use a resolution like 1024 by 1024. And 51 steps and 9.0 cfg could be too high. And maybe it doesnt understand some of the terms in the prompt.
    >>
    No.18226 [Report]
    ▶
    >>18224
    There are a lot of comfy files in this thread that still have all metadata, you can download them in full size and drag into comfy to see what other people are using, both in regards of settings and prompts
    >>
    No.18227 [Report]
    ▶
    >>18224
    Very good workflow for illustrous-type checkpoints is here:
    https://www.patreon.com/file?h=141551754&m=553120529

    How to use:
    https://www.youtube.com/watch?v=uo9wL95Cw3E
    >>
    No.18228 [Report]
    ▶
    >>18218
    >>18222
    super well done. you're amazing!
    >>
    No.18242 [Report]
    ▶
    File: Workflow Guide.png
    (1.73 MB, 1024x1024) ▶
    1812663
    >>18224
    I made a workflow with a few notes in it that should be helpful in rendering simple outputs.
    I have the initial input at 1024x1024, since that puts out the best results.

    Like the other anon said, just drag and drop this image into your ComfyUI window and it should load the workflow. Then just save it for future use.
    >>
    No.18243 [Report]
    ▶
    >>18242
    > I made a workflow with a few notes...

    Much appreciated!
    >>
    No.18249 [Report]
    ▶
    File: _Illustrious_20260418-114844_00001_.jpg
    (283 KB, 1680x2400) ▶
    290727
    >>
    No.18256 [Report]
    ▶
    File: _Illustrious_20260418-190329_00001_2.jpg
    (216 KB, 1320x3048) ▶
    221425
    >>
    No.18271 [Report]
    ▶
    Is there a good alternative now that Civitai has turned into garbage?
    >>
    No.18339 [Report]
    ▶
    File: final.jpg
    (1.06 MB, 2362x3496) ▶
    1108622
    Hello everyone. Thank you for the lora.
    >>
    No.18347 [Report]
    ▶
    File: _Illustrious_20260420-134937_00001_.jpg
    (314 KB, 1640x2464) ▶
    321621
    >>
    No.18518 [Report]
    ▶
    >>18339
    I love this.

    THought out stories are awesome!
    >>
    No.18521 [Report]
    ▶
    >>18222
    hi again! would you do Kim Possible? make her abdomen explode please
    >>
    No.19055 [Report]
    ▶
    File: _Illustrious_20260502-014925_00001_.jpg
    (232 KB, 1624x2480) ▶
    238387
    >>18521
    >>
    No.19249 [Report]
    ▶
    File: _Illustrious_20260505-202359_00001_.jpg
    (265 KB, 1568x2568) ▶
    271713
    >>
    No.19251 [Report]
    ▶
    File: _Illustrious_20260505-205900_00001_.jpg
    (244 KB, 1568x2568) ▶
    250122
    >>
    No.19257 [Report]
    ▶
    >>18090
    File not found.
    Can somebody re-upload this model?
    >>
    No.19331 [Report]
    ▶
    This is an excellent model! I'm curious—how did you source your dataset? Did you rely on annotation by large-scale models, specialized models, or was it done manually? And where did you download the images?
    >>
    No.19357 [Report]
    ▶
    >>19331
    mostly manually.

    I used one of the old waify captioners and the Joy cpation.
    https://huggingface.co/spaces/fancyfeast/joy-caption-beta-one

    Results were meh, so i manually remveod or added necessary captions.
    Mos tof the images were taken form years of browsing guro chan, and from specialized guro chan threads, like decap threads on /g/ etc.
    >>
    No.19428 [Report]
    ▶
    >>19055
    you're super good at this. can you do shego next?
    >>
    No.19683 [Report]
    ▶
    File: _Illustrious_20260514-161443_00001_.jpg
    (270 KB, 1552x2592) ▶
    276717
    >>19428
    >>
    No.19684 [Report]
    ▶
    File: _Illustrious_20260514-163354_00001_.jpg
    (275 KB, 1552x2592) ▶
    281901
    >>19428
    >>
    No.19717 [Report]
    ▶
    >>19683
    >>19684
    you're literally the best right now.
    >>
    No.19724 [Report]
    ▶
    Can someone upload the checkpoint please
    >>
    No.20817 [Report]
    ▶
    Please come back.
    >>
    No.20896 [Report]
    ▶
    >>19724

    Here you go fren
    https://mega.nz/folder/fiozmSAA#NFA18E1PEYNJ4Zvt1kXjaw
    >>
    No.21087 [Report]
    ▶
    File: ComfyUI_00421_.mp4
    (732 KB, 640x640) ▶
    749756
    Nice Lora
    >>
    No.21173 [Report]
    ▶
    File: _Illustrious_20260610-160228_00001_2.jpg
    (959 KB, 4464x2712) ▶
    982185
    >>
    No.21180 [Report]
    ▶
    >>14069
    These look real clean- great job. Would love to see different characters in different debreasting / torture scenarios.
    >>
    No.21260 [Report]
    ▶
    >>21173
    that is a cool one
    >>
    No.21275 [Report]
    ▶
    File: 1780144545760.png
    (326 KB, 882x1240) ▶
    334768
    How difficult do you like it? Can I request May getting a hose inserted into her butthole and her belly inflated big and round until it explodes into gore. If you could make it look like an outtake of the show that'd be AMAZING.
    >>
    No.21359 [Report]
    ▶
    Thanks for the Model.
    But can someone reupload the Lora? Cant find it anywhere anymore :(
    >>
    No.21428 [Report]
    ▶
    >>21359

    Same.
    >>
    No.21431 [Report]
    ▶
    >>21359
    Here is lora:
    https://gofile.io/d/e1iyVg
    >>
    No.21432 [Report]
    ▶
    >>21431
    Looks like it is another lora...
    You need Big_r-18G.safetensors
    >>
    No.21449 [Report]
    ▶
    >>21432
    https://gofile.io/d/LVF8tD I've got this, is it the one you want?
    >>
    No.21475 [Report]
    ▶
    Yeah! That's it thanks a lot!
    >>
    No.24241 [Report]
    ▶
    Are there LoRA and checkpoints for Big_R18G?
    Where can I get the full-size version?
    Or has everyone switched to CompilativeG?
    >>
    No.24255 [Report]
    ▶
    Can you make an anima of lora?
    >>
    No.24281 [Report]
    ▶
    I got ahead of myself when requesting >>21275
    sorry.
    >>
    No.25363 [Report]
    ▶
    File: _Illustrious_20260821-192837_00001_.jpg
    (240 KB, 1824x2208) ▶
    245865
    [Top]
    Delete post: []