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.
  • 160 unique users in the last 30 minutes (including lurkers)
    First
    [1]
    		Last
    File: 00027-2216965335.png
    (1.46 MB, 1024x1280) ▶
    1534751
    No.4264 [Report] AS
    ▶
    Lora request rules got buried in my previous thread so making a new thread with them clearly at the top.

    At the time of creating this thread I only make PonyXL lora's so the following will mainly be for PonyXL. But since the "best" checkpoints are always changing make sure to check through the thread if I'm doing anything else if. Should be easy enough by just Ctrl+F searching my name and quickly skimming through the thread.

    I want to accept as many Lora requests as possible but to make the best use of my time and yours I request that you provide the following when you make a Lora request.

    1. At least 20 images high quality images that clearly show the concept/character/clothing you want in your Lora (quality > quantity)
    a. By high quality I don't mean high resolution. Anything above 512x512 is good enough (That said higher res is always better so avoid downloading samples if possible, only one dimension needs to be above 512. So something like 512x368 is fine)
    b. Shows what you want trained clearly. If many images partially obstructed it may not train correctly
    c. Avoid full comic pages, and things that may have a lot of detail. If its a part of a comic page, just crop it out and send me the panel. I crop out a few myself but if you send something like 50% of your images as comic pages I may decline the request.
    d. Images should be of a anime/cartoon style, 3D renderings, etc. Lets avoid realistic images whenever possible (They're also guro-chan rules)

    2. Upload all of your images onto a easy to download file service. Any is fine.
    a. Catbox seems like the most popular file upload method but anything is fine so long as I can get them.
    b. I would recommend zipping it with a password if you're going to use Catbox. (They typically don't allow anything super hardcore guro so just to make sure its contents are hidden)
    c. And obviously if you use a password make sure to share it here

    Where you get the images doesn't matter but I would recommend gelbooru or pixiv. When using gelbooru make sure you download the full image and not the sample you typically see by default. If you need any help gathering images or don't know what tags to use, just ask here and me or other users can share tags/pointers for getting them.

    There is no need for you to rename, tag or sort the images yourself. Although appreciated I will be doing that part myself.

    Check out the other stuff I'm doing:
    Pixiv: https://www.pixiv.net/en/users/32339993
    Fanbox: https://www.fanbox.cc/@entropy-game
    >>
    No.4265 [Report]
    ▶
    >>4264

    You can check out all Lora's made by the Guro-chan community here: https://rentry.org/R-18G_Stable_Diffusion
    Look under PonyXL to find most of my Lora's. (https://rentry.co/r-18g_stable_diffusion_pony_v6)
    >>
    No.4266 [Report]
    ▶
    File: Untitled-1.png
    (3.57 MB, 1536x2048) ▶
    3744436
    >>4264
    Sharing some of my favorite Lora's I've worked on

    QuadrupleAmputee Lora >>698
    Pussy Stab Lora >>1800
    Self-harm scars Lora >>3370
    >>
    No.4300 [Report]
    ▶
    I'm still not ready to try training the _v2 ('s) for the pussy stabbing Lora, yet. But I've also started collecting material for a few other potential datasets on the wayside. One would be a hard vore Lora with mostly dinosaurs/dragons biting/eating a girl whole and another would be basicly the same but debreasting/breast eating focussed (so the dino/dragon/monster with a severed breast in its maws and the half debreasted girl next to it. My question: is it even feasible to mix the type of monsters/animals or would the dataset have to be one type of creature only?

    Also iirc you made an impalement Lora for pony some time ago with which you weren't too happy back then. Do you have an idea about what kind of pics you would need to try again?
    >>
    No.4330 [Report]
    ▶
    File: 00030-3566967234.png
    (1.19 MB, 896x1280) ▶
    1251888
    >>4300
    I think it would be fine. But even if it doesn't work no harm in trying. Dinosaurs & dragons are already trained in the base model so I don't think we would need a lot of monster specific training data. As long as we have enough for the biting/eating it should just translate to any creature. To answer the question since we would be training the concept of biting/eating as long as there is sufficient data in the base model it should be feasible to mix monster types easily. Which I believe there is. If it made properly it should mix well with other monster lora's like pic releated, so you can always just pull monster data from other Lora's

    For the impalement Lora I would need at least 20 images with people being impaled on a stick of any kind. Shouldn't matter. If I recall correctly I didn't even have 20 which is why I think it failed. I wasn't very good at collecting images back them. Although I'm still not tbh but especially so back then, I had no idea how to navigate gelbooru/pixiv properly.
    >>
    No.4358 [Report]
    ▶
    >>4330

    I've collected all the good impalement pics I've got, also polished up some of my own gens and de-censored some works of others. I think if you combine it with the set you already have it should provide for a nice training set. I sent you the link on pixiv. :)

    Hmmm, if we don't need animal/monster - specific data for the biting vore concept(s) I'll need a few more days to sort through all my archives again and pick what I've had left out so far.
    >>
    No.4400 [Report]
    ▶
    In your previous thread someoen was asking for a branding LoRA.

    I collected soem Brnading pics.
    https://files.catbox.moe/mb51w8.rar

    they imho are not enoug, 33, pics, but maybe something cna be done with them.


    Also I think we need a better impalement lora.

    here is my pics
    https://files.catbox.moe/shov58.rar


    Hope it can be added to yours.


    Also can You please train an imaplement for Illustrious too?

    I think Illutrisout is the future of Guro AI, not pony
    >>
    No.4677 [Report]
    ▶
    >>4400
    Hey, sorry I just saw your post. I'll start working on them. I never used Illustrious before so no promises on that one but I will try.
    >>
    No.4679 [Report]
    ▶
    >>4677


    I found some more branding pics.I will send you a more comp;ete folder tomorrow.


    i was told that using masks can help with training specific characters or things. You mask out parts of the image that are not relevant.

    I think it would be a good technique to use with branding.

    I myself never used, no pressure, just wanted to share a possibly useful tool.
    >>
    No.4686 [Report]
    ▶
    >>4679
    Here is the more complete folder of branding pics

    https://files.catbox.moe/ut04vc.zip

    81 pics, I hope it is enough.

    Thank you again for doing this for the community
    >>
    No.4736 [Report]
    ▶
    ANy progress on the branding LoRA?
    >>
    No.4739 [Report]
    ▶
    File: 1.jpg
    (581 KB, 1792x2560) ▶
    595170
    Impaled v3 - PonyXL lora
    Author: Entropy (https://www.pixiv.net/en/users/32339993), Eel (Image collection, tagging)

    DOWNLOAD: https://mega.nz/folder/P6JjTTBQ#jxAV2L4iKwYtt04GSLrW0w

    Triggers: impaled, all the way through, head back, pole from mouth
    Supplementary: object insertion, vaginal object insertion, arms behind back, metal pole
    Weight: 1.0
    Recommended Epoch: 8

    Notes: Creates an impaled person. Use "all the way through", and "pole form mouth" to create a pole going all the way through. These triggers sort of ended up being mangled together so use or both, the results are generally the same. All of the trigger words are slightly mangled together so txt2img results without "all the way through" may contain images that go all the way through and vise versa. If you want the pole coming out of a different part, other than the mouth/head consider using img2img. txt2img results for non-head pole extrusions are not good, as-in you'll rarely see them get generated.

    Head back results in the character tilting their head backwards (all the way back), most of the head not being in frame (hidden due to neck, rest of body) so having triggers that describe the face/head often conflict with this trigger. Consider the use of other trigger words carefully when using this one. Like seriously anything will stop it from generating (in txt2img), I had animal ears fuck it up. Took me a while to figure out what was the problem lol. If you want facial details while having a the head slightly tilted back, I would recommend img2img.

    Side view, from above: Has some issues. Not as great txt2img results when trying to generate from side or above. That said works well on img2img. Consider trying to make a txt2img image first then drawing in a pole using an image editing tool like paint, photoshop or gimp. Results are very good in img2img.
    >>
    No.4740 [Report]
    ▶
    File: 00021-3801036097.jpg
    (233 KB, 896x1280) ▶
    239320
    >>4739
    Typical "head back" result. The head goes all the way back so be careful about the other triggers
    >>
    No.4741 [Report]
    ▶
    File: 00037-216291709.png
    (1.19 MB, 896x1280) ▶
    1252599
    >>4739
    >>
    No.4742 [Report]
    ▶
    File: 00055-777991659.png
    (1.06 MB, 896x1280) ▶
    1115800
    >>4739
    Works with character lora's as well as other concept lora. Assuming they don't conflict.
    This is typically what happens with txt2img with a "from_above" trigger. The pole just doesn't want to go through. A little help from the user (paint, photoshop) going to be required if you want this view and img2img.
    >>
    No.4743 [Report]
    ▶
    File: 00092-336844415.png
    (3.68 MB, 1792x2560) ▶
    3859345
    >>4742
    >>
    No.4744 [Report]
    ▶
    >>4736
    Just finished the impalement Lora so no progress yet, I also want to look at making Illustrious version of the impalement Lora. But the branding Lora is going to be next. Obviously going to depend on how well it goes but should be done this week. I'm also working on a "walking on plank" Lora with EeL, although I'm struggling a bit with that one so no idea when I will publish that one.
    >>
    No.4781 [Report]
    ▶
    >>4744
    >Illustrious version of the impalement Lora


    this would be amazing.

    Just run the same dataset with the same tags, and just change the base model!



    Fially I see an impaled model that works with the shaft being consistent. Awesome work!
    >>
    No.4782 [Report]
    ▶
    >>4741
    https://www.youtube.com/watch?v=UcwfEMdV-aM
    >>
    No.4790 [Report]
    ▶
    >>4782
    lmao
    >>
    No.4791 [Report]
    ▶
    >>4736
    Alright quick update on the branding Lora. Started working on it, had a look through all the images. I'm breaking it down into three main triggers. Brand Mark, Branding Rod, and Branding Stamp.

    There isn't enough for some of them so I'll be doing some image gathering.
    >>
    No.4792 [Report]
    ▶
    File: illustrious.png
    (1.15 MB, 896x1280) ▶
    1207823
    >>4781
    Put an illustrious trained Lora in the same mega folder.
    https://mega.nz/folder/P6JjTTBQ#jxAV2L4iKwYtt04GSLrW0w

    Going to be honest, I have no idea how well this turned out. I don't use illustrious and don't know how to get good gens with it yet, keep getting noisy gens. Slapped the same training data into (https://civitai.com/models/795765/illustrious-xl) which I assume is the main illustrious model? I did a few tests and it seemed to turn out okay but I didn't extensively test it like the pony version. Let me know how it turned out if you use illustrious.
    >>
    No.4793 [Report]
    ▶
    File: illustrious_2.png
    (1.68 MB, 896x1280) ▶
    1763706
    >>4792
    >>
    No.4794 [Report]
    ▶
    File: ComfyUI_70094_.png
    (1011 KB, 768x1344) ▶
    1036225
    >>4793
    From what I see the illustrious version works better than pony.


    But i;m heavily biased towards Illustrious i the past month
    >>
    No.4795 [Report]
    ▶
    File: ComfyUI_70085_.png
    (818 KB, 896x1152) ▶
    838118
    >>4794
    >>
    No.4796 [Report]
    ▶
    File: ComfyUI_70099_.png
    (950 KB, 832x1216) ▶
    972943
    >>4795
    >>
    No.4797 [Report]
    ▶
    File: ComfyUI_70097_.png
    (983 KB, 768x1344) ▶
    1006839
    >>4796
    >>
    No.4798 [Report]
    ▶
    File: ComfyUI_70113_.png
    (1.07 MB, 832x1216) ▶
    1121179
    >>
    No.4799 [Report]
    ▶
    File: ComfyUI_70103_.png
    (1.31 MB, 832x1216) ▶
    1374003
    >>
    No.4800 [Report]
    ▶
    >>4791
    thanks, I've been trying to get branding irons working without a lora but no luck so far.
    I've had some luck with the speculum and bloodvessel(https://civitai.com/models/80321/blood) loras getting some mild gore.
    uploaded some of the works here:https://exhentai.org/g/3143593/1003385af1/
    >>
    No.4803 [Report]
    ▶
    File: ComfyUI_70142_.png
    (1.21 MB, 832x1216) ▶
    1268875
    Finally I can do imaplements. Thank you!

    combining it with Illustrious Ayaswan
    >>
    No.4804 [Report]
    ▶
    File: ComfyUI_70159_.png
    (1.01 MB, 832x1216) ▶
    1054812
    >>4803
    Just a little rotouch in photoshop required to fix this image
    >>
    No.4805 [Report]
    ▶
    File: ComfyUI_70162_.png
    (1.05 MB, 832x1216) ▶
    1097160
    >>4804
    same for this one.
    >>
    No.4808 [Report]
    ▶
    File: ComfyUI_70307_.png
    (633 KB, 832x1216) ▶
    648268
    >>
    No.4848 [Report]
    ▶
    File: cover.png
    (4.89 MB, 2560x2560) ▶
    5125326
    >>4800
    I have a few more idea's and I'm going to keep trying. But I have a few other projects I'm juggling so I'm going to leave at this for now. Maybe next week or near Christmas time I'll give it another shot.

    Download: https://mega.nz/folder/bmpVhCrQ#2ZOuT6c6VpJWRvzmdAPJHA
    Triggers: branding mark, branding stamp, branding rod
    Supplementary: <Trigger> on <Body part>, bruise, bound

    For now <Trigger> on <Body part> doesn't seem to really work with txt2img. (ex. branding stamp on ass, branding stamp on breast, branding rod on pussy etc..)

    I've had widely random results, with some generating what I would expect and other seeds just not wanting to work. 50/50 of getting something, and good luck getting something good after that. Definitely a img2img primary Lora in its current state. As I said before I definitely want to come back to this but I have other projects I want to keep up with. It's a good and bad thing to have commitments lol. On the one hand it gives me motivation and some pocket money on the other hand I can't spend hours just fucking around with Loras 😭. Anyways for anyone interested in this Lora go nuts and share feedback. Will be super helpful for when I take a crack at a v2. There was a lot of "on ass" images in the dataset so I found that to work pretty well when I tested it out. You can also check the training dataset tags and play around.
    >>
    No.4849 [Report]
    ▶
    File: 00026-3242441089.png
    (1.25 MB, 896x1280) ▶
    1315828
    >>4848
    A lucky txt2img example
    >>
    No.4850 [Report]
    ▶
    File: 00027-3242441090.png
    (1.19 MB, 896x1280) ▶
    1243794
    >>4848
    >>
    No.4851 [Report]
    ▶
    Wow, I'm amazed the ones you did came out so well.

    I understand it is cehrry picked but I expected much worse.


    ANd I love you using Nami as a text subject!
    >>
    No.4866 [Report]
    ▶
    >>4848
    thanks
    if it helps at all I found this lora on civitai: https://civitai.com/models/502970/branding-concept-for-ponyxl
    it seems to get branding irons and lanterns confused a lot though
    >>
    No.4871 [Report]
    ▶
    >>4866
    Thanks for sharing. I'll have a look at it and see if there's anything I can get out of it.
    >>
    No.4880 [Report]
    ▶
    File: 00004-241210,casca _ berserk_ 1girl sol(…).png
    (3.24 MB, 1536x2304) ▶
    3395021
    >>4848
    having sporadic successes with this, and combining it with some other loras.
    the png info should be intact on these if anyone wants to use them as a jumping off point. though this is the second iteration of the image after being upscaled using tiled upscale in img2img.
    >>
    No.4881 [Report]
    ▶
    File: 00021-241210,casca _ berserk_ 1girl sol(…).png
    (3.35 MB, 1536x2304) ▶
    3508066
    >>4880
    the sdxl impalement lora is also really good. does seem to also randomly be a bloody amputation lora too though.
    >>
    No.4882 [Report]
    ▶
    File: 00028-241210,casca _ berserk_ 1girl sol(…).png
    (3.35 MB, 1536x2304) ▶
    3510635
    >>4881
    >>
    No.4883 [Report]
    ▶
    File: 00031-241210,casca _ berserk_ 1girl sol(…).png
    (3.28 MB, 1536x2304) ▶
    3437126
    >>4882
    >>
    No.4884 [Report]
    ▶
    File: 00019-241210,casca _ berserk_ 1girl sol(…).png
    (3.32 MB, 1536x2304) ▶
    3482800
    >>
    No.4885 [Report]
    ▶
    File: 00026-241210,casca _ berserk_ 1girl sol(…).png
    (3.63 MB, 1536x2304) ▶
    3806825
    >>4884
    >>
    No.4886 [Report]
    ▶
    File: 00002-241210,casca _ berserk_ 1girl sol(…).png
    (3.64 MB, 1536x2304) ▶
    3813855
    >>4871
    tested it a bit.
    it can kind of do branding iron like things, but they're overly bright and magically glowy. I think it's sort of a hack together of a few things that vaguely look like branding irons.
    your lora is definitely better for actual guro.
    >>
    No.4887 [Report]
    ▶
    File: 00165-241210,casca _ berserk_ 1girl sol(…).png
    (1.82 MB, 1024x1536) ▶
    1910213
    >>4880
    >>4792
    using this currently
    https://civitai.com/models/926443?modelVersionId=1061268
    and started by copying the png info from this guys images https://civitai.com/user/Uyu39 until I got it right, and then started customizing it

    example of one before img2img
    >>
    No.4891 [Report]
    ▶
    here what I have on hand:
    https://files.catbox.moe/05w3j5.zip
    password "branding"
    also
    there's some old threads on g with a bunch of branding iron pics if that helps
    https://boards.guro.cx/g/koko.php?res=19356
    https://boards.guro.cx/g/koko.php?res=66354
    there's also about 318 pics of branding iron on sankaku channel, but only 35 of branding iron+guro https://chan.sankakucomplex.com/en/posts?tags=branding_iron+guro
    I also found a exhentai gallery of branding iron https://exhentai.org/g/2839217/965165bdec/
    >>
    No.4903 [Report]
    ▶
    File: 00013-241211,casca _ berserk_ 1girl sol(…).png
    (3.23 MB, 1536x2304) ▶
    3382867
    i'd be interested in a needle torture lora, for needles or nails stabbed in breasts or pussy.
    here's a folder of images I collected for it: https://files.catbox.moe/q5jexn.zip password:needles

    I've been using this "acupuncture" lore that has been removed from civitai, but the results are mixed(id like a little blood from the insertion point, and/or thicker needles)
    reuploaded here:https://files.catbox.moe/d2q6wr.rar
    no password
    oddly it does seem to create random holes sometimes.
    >>
    No.4905 [Report]
    ▶
    I'd also be interested in a modification of the impalement lora for non-all-the-way-through impalement. so it's more like their dangling halfway through the process, and the pole is thicker so it's more like it's crushing their insides rather than strictly piercing. I've been trying to do this, like with one bar prison loras from civitai, but often times the pole/stake comes out too thin and generally doesn't seem as brutal. combining those with the current impalement lora is okay, but then I often get random things sticking out at odd angles.
    I've also seen the tag "insertion suspension" refer to this sometimes, but sometimes it means something else.

    here's some images, https://files.catbox.moe/zptb8u.rar
    password:insertion
    >>
    No.4906 [Report]
    ▶
    >>4905

    >I'd also be interested in a modification of the impalement lora for non-all-the-way-through impalement...

    Already working on it. I'm currently reorganising the dataset(s) for the impalement Lora(s). "Not all the way through" pics were already in the dataset but sadly the triggerwords don't work. So the plan is to train on that seperately. There are a some nice pics in your upload that I will add to the "insertion_only_impalement" - dataset.
    >>
    No.4913 [Report]
    ▶
    >>4906
    great!

    also I know you said quality over quantity but if you're ever looking for a large amount of just quantity these forums have a bunch of stuff https://www.cruxforums.com/xf/threads/impalations.916/
    >>
    No.4914 [Report]
    ▶
    >>4903
    Request received! I'm a bit busy so it might take me a bit till I get to it, shouldn't take longer than a week but just want to let you know.
    >>
    No.4921 [Report]
    ▶
    File: 824-14581201.webp
    (46 KB, 906x1024) ▶
    47610
    I want a lora that draws y-incision autopsy stitches on characters. There's a few autopsy-related guro images on pixiv that contains the stitching pattern, but there's no exact tag for it other than the autopsy tag itself. I really need help with finding ways to find more of y-incision stitches on girls in order to build and train a lora with it. Any help is appreciated.
    >>
    No.4924 [Report]
    ▶
    This probably won't work but I'd like you to try making a Lora for graphic digestion, the kind where you see their skin dissolving and the flesh underneath without it getting too messy. I gathered some images to the best of my efforts but they're mostly from the same artist and don't exactly fit the anime style. See what you can do with them.

    https://files.catbox.moe/m8u2zj.rar
    password: 1234
    >>
    No.4929 [Report]
    ▶
    >>4924
    I added some more images, it that helps at all.

    https://files.catbox.moe/c3d1ln.rar
    password's the same
    >>
    No.4932 [Report]
    ▶

    >>4914

    I actually just found a needle and nail torture lora here: https://boards.guro.cx/ai/res/836.html#2448 still, it seems very rough and could use improvement or a seperate attempt.
    >>
    No.4935 [Report]
    ▶
    File: 00061-2208734229.png
    (4.3 MB, 1792x2560) ▶
    4509059
    Needle Torture - PonyXL lora
    Author: Entropy (https://www.pixiv.net/en/users/32339993), Anon (Image collection)

    Download: https://mega.nz/folder/j7RUzAaS#gaX_gYRBP1fnVm4p4HM-oA

    Triggers: needle, needle on <Bodypart>
    Supplementary: guro, blood
    Weight: 1.0
    Recommended Epoch: 12

    Notes: Creates a person stabbed by needles. Use both needle and needle on <Bodypart> where you would replace <bodypart> by where you want the needles to be. Trained on breasts, nipples, and pussy. Results for other body parts may vary.

    >>4932
    Just saw this as I was getting ready to upload this.😭
    Looks to be making nails that are a lot thicker so hopefully this Lora will provide a different use case. This lora makes needles that are a lot thicker.
    >>
    No.4936 [Report]
    ▶
    File: xyz_grid-0002-51363527.jpg
    (1.92 MB, 4800x2841) ▶
    2015721
    >>4935
    I would recommend raising the weights on the trigger words a bit. Here's an XYZ graph to show how the two main types of triggers interact. I think raising the weight of the needle on <Bodypart> triggers give better results. Raising the weight on just needle too high will start placing needles on all parts of the body.
    >>
    No.4945 [Report]
    ▶
    have any future plan to make ilXL Lora ?
    >>
    No.4958 [Report]
    ▶
    >>4945
    if you are interested in il models, maybe you shoule check this https://civitai.com/models/904011/punishmentdiffusionxl-05
    I have tested it, and it can do hanging,Garrote,drowning and roasting. I believe there are more, but due to the restriction of civitai, the creator didnt prove more prompts, as i checked that impalement is kind of working, but i dont know what prompt can make it work properly
    >>
    No.5180 [Report]
    ▶
    File: 00088-241230,Tanya Degurechaff Youjo Se(…).png
    (3.29 MB, 1536x2304) ▶
    3452114
    thanks for all the loras
    the "zunko" amputee loras works especially well.
    here's a dump of most of my stuff so far:
    https://exhentai.org/g/3178724/7226f3dbd8/
    some older stuff
    https://exhentai.org/g/3143593/1003385af1/
    >>
    No.5189 [Report]
    ▶
    File: ComfyUI_temp_kimao_00011_.png
    (1.76 MB, 1216x832) ▶
    1845704
    >>4929
    Made an illustrius lora. Activator is acid_digestion. Add other guro tags for best results. Works decent for what I tried. This is a 3 day DL so hopefully it gets re posted somewhere else!

    https://litter.catbox.moe/c6oat0.safetensors
    >>
    No.5190 [Report]
    ▶
    File: 115584532_p0_master1200.jpg
    (547 KB, 1200x877) ▶
    560714
    Could someone make or at least suggest a lora for neck snapping/broken? I've scrubbed every topic here and the concept just doesn't seem to exist.
    >>
    No.5191 [Report]
    ▶
    File: 00056-467876994.png
    (2.41 MB, 1344x1808) ▶
    2526897
    >>5190
    Ican get somewhat close at super low resolutions, but upresing always just turns it vanilla. I cant even get a head turned sideways.
    >>
    No.5193 [Report]
    ▶
    File: 00061-1099287480.png
    (2.34 MB, 1344x1808) ▶
    2457041
    >>5191
    With a lot of cherry picking and re renders I can almost aproximate it just by mixing other random Loras but the effect could be a lot better.
    >>
    No.5198 [Report]
    ▶
    File: 00039-3873542494.png
    (1.24 MB, 1024x1280) ▶
    1302326
    >>5190
    Whoops I forgot to post the neck snapping Lora someone requested me to make a few weeks back. I made both an illustrious and Pony version of this one. It creates a sort of "twist" effect on the neck, and it's not great at creating a sideways neck. I would recommend you use photoshop or something to manually put the neck sideways than apply this lora. neck twist can sometimes work with txt2img like pic related. It will create a neck that's facing backwards.

    DOWNLOAD: https://mega.nz/folder/m3wlxDQQ#2NMoAyU_231Tx2kNbOLP-A

    Neck Snap - lora
    Author: Entropy (https://www.pixiv.net/en/users/32339993), Anon (Image collection)

    Triggers: neck snap, neck twist
    Supplementary: guro, blood, asphyxiation, back view (if using neck twist)
    Weight: 1.0+ (~1.5 ish for Pony)
    Recommended Epoch: 20

    Notes: Another primarily img2img Lora. txt2img may not give ideal results.
    - Neck twist creates (**tries to create) a neck twisted backwards.
    - Neck snap is (supposed to be) a neck snapped to the side.
    Both create a "twisted" effect on the neck. Should work well with img2img/ControlNet
    >>
    No.5199 [Report]
    ▶
    >>4929
    >>4924
    Sorry I completely missed this. But it seems like someone else already made one?

    >>5189
    Link is already dead. Did someone manage to download this?
    If no one has the Lora I'll try making one myself.
    >>
    No.5200 [Report]
    ▶
    >>5189
    Link is dead for me too. Maybe try Mega because Catbox seems to be down right now. From that image alone it already looks better than my attempts.
    >>
    No.5201 [Report]
    ▶
    >>5198
    Hah, thanks, that would have saved me a lot of time. Would a sideways neck effect require its own lora? I'm not really sure what the process of training is like.
    >>
    No.5202 [Report]
    ▶
    >>5199
    It's fine. I realized that my dataset might not be the most consistent or diverse, since there aren't many artists who illustrate the concept and the few who do have vastly different takes on it.
    >>
    No.5203 [Report]
    ▶
    File: 00000-255470390.png
    (2.56 MB, 1536x1920) ▶
    2683124
    >>5198
    Having good luck so far, it combines well with the creepy head tilt lora

    https://civitai.com/models/864631/normal-and-creepy-head-tilt-slider-request
    >>
    No.5204 [Report]
    ▶
    >>5203
    Getting higher resolutions is almost impossible, their faces just start to bend like rubber.
    >>
    No.5207 [Report]
    ▶
    >>5199
    Hey all, I gave in and made a mega. Let me know how it works!
    Activation tag is acid_digestion
    https://mega.nz/file/iJIDTRKY#wx26DugxXpJ-mIpwc6B6Ax2cVqR_4cRcM5-zGhte2Is
    >>
    No.5210 [Report]
    ▶
    >>5198
    OMG!! It's so HOT! This reminds me a death scene from a movie called "Army of the Dead". If you know, you know.
    >>
    No.5237 [Report]
    ▶
    >>5190

    This neck snap Lora for Pony was uploaded to civit sometime in august and nuked within hours: https://files.catbox.moe/bo4tti.rar ...pw: gurochan

    Main triggers that were listed: neck_snap, head tilt, eyes rolled up. Check meta for more. I didn't have much success with this one but also didn't try very much. maybe you'll get more out of it.

    >>5191
    >>5204

    are you using High-Res-Fix and/or Adetailer? If so maybe you might want to try if multidiffusion is better at this.
    >>
    No.5260 [Report]
    ▶
    File: 1719501863363.jpg
    (892 KB, 4004x3395) ▶
    913527
    how specific do you think loras need to be? I'm wondering if it would be possible to make just a general torture guro lora trained on a huge variety of tortures? one use case would be for when you want to generate a guro torture image, but want to allow the ai some randomness on the specific torture thats being applied? or when you just want to make it clear to the ai that this is a guro torture scene, it should be bloody, and the character should be reacting as if in horrible pain?

    if that's not possible I'm also just interested in specific torture loras. pulling of fingernails, slicing off pieces of flesh, lingchi, flaying, roasting over coals/fire, hot metal(we did branding but what about just more red hot metal in general?), boiling oil, pliers, cats claw, pear of anguish, vaginal insertions covered in spikes, torture with medical instruments, tasers, crucifixion, stretching on the rack, etc. interested in anything were the person is experience extreme pain or fear.

    maybe even just a lora trained on pained horrified facial expressions
    alone could be good. often times the facial expression doesn't seem extreme enough in my generations.


    do you think any of those could be particularly easy to do or work particularly well?

    I could start collecting and categorizing images and come back with a large amount later.
    >>
    No.5264 [Report]
    ▶
    File: 8.png
    (2.14 MB, 1920x1275) ▶
    2245070
    >>
    No.5265 [Report]
    ▶
    File: 10.png
    (1.63 MB, 1291x1920) ▶
    1709825
    >>
    No.5267 [Report]
    ▶
    can you make a general or at least a throat slit lora for NoobAI new model? loras for noob need to be made for it due to how it handles light, but it seems to be the most advanced local model yet
    >>
    No.5307 [Report]
    ▶
    File: 00069-00004-250109,1girl upside down lo(…).png
    (3.19 MB, 1536x2304) ▶
    3347112
    >>5207
    not quite my thing but pretty good results
    >>
    No.5308 [Report]
    ▶
    File: 00071-00007-250109,1girl limbs dissolvi(…).png
    (4.31 MB, 1536x2304) ▶
    4520379
    >>
    No.5339 [Report]
    ▶
    >>5308
    This is stunning!
    >>
    No.5411 [Report]
    ▶
    >>5198
    >neck snap
    will you make an Il version of your not so fresh corpse lora?
    >>
    No.5412 [Report]
    ▶
    >>5260
    What is the source for this? Saucenao isn't bringing up anything and I'm not sure where else to look.
    >>
    No.5430 [Report]
    ▶
    File: 1719501851371.jpg
    (1.68 MB, 2893x3850) ▶
    1758892
    >>5412
    im not sure, but unfotunately I think it might have been from this artist https://x.com/natunisinu?t=TrQXGKiO1MtWyZcH8yaJ6w&s=09 who has privated and deleted all their guro content off pixiv. I could be wrong though.
    >>
    No.5510 [Report]
    ▶
    >>4266
    will you make illustrious version of those loras, as well as hanging and half-rotten corpse,arrow loras?
    >>
    No.5842 [Report]
    ▶
    I'm interested, I would love a "Vagina Dentata" LoRA, but I think my data set is too few pictures and maybe too low quality. What should I do?
    >>
    No.6025 [Report]
    ▶
    File: 127146919_p0.jpg
    (2.28 MB, 2480x3508) ▶
    2389337
    I'm starting to get interested in training loras myself.
    I think I've got enough vram to do it.
    looked up tutorials online.
    do you have any tips that might not be in the online tutorials? especially relating specifically to making guro loras?

    interested in making one's for general torture. needles. bleeding whip marks. burning with fire or hot metal. flaying alive. rack stretching. and maybe ones for horrified and pained facial expressions.
    >>
    No.6248 [Report]
    ▶
    >>5842
    Number 1 is check out pixiv or gelbooru (or any booru really) and try to get as many images as possible.

    Step 2 if you still don't have enough images you can try creating them yourself without a Lora. It'll be a lot more difficult but with creative use of inpainting, photoshop (or whatever art tool you prefer) you can create the necessary images to create an initial model.

    We can then use those to create a lora, then use that Lora to create more training images, which we can use to further improve the Lora. Let me know if you're interested in doing something like this
    >>
    No.6249 [Report]
    ▶
    >>6025
    I don't have many "guro specific tips". But I can share what worked for me in general.

    I would separate them out each into their own lora, you can try to put them all into their own lora but for beginners like you and me it'll save a lot of headaches if you just make each of them their own. A lot of triggers can conflict with each other or be affected by pre-existing keywords in the base model. Having multiple concepts in your Lora can make it really difficult to figure out which concept is causing issues.

    If you have enough sample data creating your own unique keyword can save you a lot of time. I'm currently working on an improved impaled Lora with another guro-chan user and the one thing we found is that using pre-exisiting triggers can be difficult with guro. Since guro is typically not a part of popular base models we constantly ran into issues with base version of the prompt messing up our gens. At the same time not having enough training data can make it hard to train a new trigger from scratch.
    >>
    No.6294 [Report]
    ▶
    >>5180
    What is this amputee lora?
    >>
    No.6296 [Report]
    ▶
    >>6294

    This one: >>698

    But there is only the 40 epoch version remaining in that mega link, the image in question used the 50 epoch version: https://files.catbox.moe/gkvv2a.rar
    >>
    No.6300 [Report]
    ▶
    >>6248
    I had not considered creating dentata images with existing tools before i saw your post. Yes, I'll try this. When I have 15 images, how should I get in touch with you?
    >>
    No.6301 [Report]
    ▶
    >>6296
    what password?
    >>
    No.6303 [Report]
    ▶
    >>6296
    >>6301

    Ah, shit, sry! Forgot that of course... >.< Pw is:

    gurochan
    >>
    No.6342 [Report]
    ▶
    >>6303
    thank u sir
    >>
    No.6608 [Report]
    ▶
    made a collection of "screaming in agony" images.
    maybe could be used to make a lora for agonized screaming facial expressions?

    this is part 1, of 6. catbox has a file size limit and is slow, I'll add the other parts when they finish upload.

    password for all parts is "guro"
    https://files.catbox.moe/o7m1dy.rar
    >>
    No.8495 [Report]
    ▶
    >>5180
    where download this lora?
    >>
    No.8608 [Report]
    ▶
    Looking for a basic throat slit lora. Not bloody but like the body is ready to be cooked
    >>
    No.8615 [Report]
    ▶
    Looking for a lora that those stump fucking. Especially the neck/throat
    >>
    No.8638 [Report]
    ▶
    File: 00452-2598348382.png
    (1.37 MB, 1024x1024) ▶
    1432965
    >>6608
    hey my guy not to shoot you down or anything but I took a look at this file and most of these can be attained through prompting without the need of a lora. Something like "wide-eyed, pain face, constricted pupils, foaming at the mouth, drooling, screaming". You can play with other tags too but they'll get you pretty consistent results.
    >>
    No.9012 [Report]
    ▶
    Anyone has prompting tips, or lora suggestions, to make guro eye stuff? As in eye gouging, pulling eye from the socket, pushing finger or fingers inside the eye socket, anything eye trauma related
    >>
    No.13876 [Report]
    ▶
    https://uploaditonline.com/download/wLzUnZRTeKa

    Acid Digestion Lora for IllustriousXL remade.
    Trained again with the images provided.

    Example prompt (for Forge UI)

    pink background
    high quality photo front, laying, safe_pos, score_9, score_8_up, score_8, (front), (highres), (solo), visible face,
    of one medium build woman, large breasts, european, 25 years old, worried, beautiful face, (blue) eyes, (looking at viewer), open mouth, (brown hair:1.4), medium hair, (visible feet), (full body portrait:1.8), (muscles), nude, barefoot, wet body, (ripped white shirt), (red nail), (pubic hair), ripped clothes, ((guro)), gore, acid_digestion, wounds, blood, stomach interior, (ripped skin:1.2), (exposed flesh:1.2), ((disemboweled:1.2)), (intestines), ((green liquid:1.4)), ((bones:1.2))

    Negative
    (((extra fingers:1.6))), gilf, old, grandma, ((bangs)), child, underage, extra limbs, deformed hands, deformed feet, (((hand with 4 fingers:2))), (((hand with 6 fingers:2))), 7 fingers, (((foot with 4 fingers:2))), (((foot with 6 fingers:2))), ugly, ((childface)), ((chinese:)),, (low res), ((squint eyes)), ((deformed hand)), ((extra limb)), ((third arm)), deformed, ((missing finger))
    >>
    No.13877 [Report]
    ▶
    Trained with:
    illustriousXLPersonalMerge_v30Noob10based
    https://huggingface.co/Toc/toc/blob/main/models/illustriousXLPersonalMerge_v30Noob10based.safetensors
    >>
    No.14921 [Report]
    ▶
    File: 61060348_p27_master1200.jpg
    (285 KB, 800x800) ▶
    292757
    Been experimenting with trying to replicate something like this for a while, albeit focused on specific genre niches, but it's been difficult to get it to work correctly. I'm wondering if it's a problem with either my training data or my tagging...

    Specifically, I've been trying to come up with a LoRA that will do a heart that is either midway through bursting apart or is already exploded, showing the heart interior or as a limp chunk of flesh. It's been *maddeningly* difficult to get the training to work for that though, so I'm hoping all of you would have better luck making it work...

    Old image provided as a little context for what I'm after, don't remember who originally made it.
    >>
    No.15074 [Report]
    ▶
    >>4264
    Dang. High quality abdominal inflation is plenty but exploding bellies bursting gorily are rare.
    >>
    No.24392 [Report]
    ▶
    anyone can share a link to debreast LORA for illustr? Thanks!
    [Top]
    Delete post: []
    First
    [1]
    		Last