Extremely hot

>>31621
Read the original post a few times before asking that question.

>>31622
just send that Goddamn KEY goddammit

>>31623
Christ, were you dropped on your head as a baby? Copy the entire fucking link.

>>31289
Can anyone send a new folder of kamebeya's stuff?

I think it's enough to introduce yourself to get 'club member' status and see full-sized pictures.

What’s dark spot??

https://thedarkspottwo.com/ , another snuff forum. Focused on executions but not exclusively.

found it on vk vk.com/ video847068425_456239017

>>17550
16$ for this piece of shit btw
anyways thanks

Link doesn’t work anymore

>>17572
Video deleted or unavailable

Good news, it is now active again
https://kemono.cr/gumroad/user/8960396908171/post/wuoak

artist is C2

brand new piece

>>35978
Well? We’re waiting

Fuck Im Slow af, sorry mah Ge

Anyone know where to find the artist and the rest of their work?

>>36001
Been trying to find who's the artist for this picture, but in all threads I tried finding there's little to no info, even I'm having a difficult time trying to find this image in scatbooru and pixiv.

Brains for dessert? The spoon is too big (or head too small) and they're goopy-er than I'd like, but it works.

https://files.catbox.moe/oopenr.mp4

Ground breast meat.

https://files.catbox.moe/z5iupb.mp4

I'm not usually a fan of cannibalism, but these are excellent works.

That fried womb was one of the hottest things I've ever seen. We definitely need more of that!

great story until here

maybe Phoebe could be cooked/roasted too

Just bumping to say that I liked the talk with the Principal and hope for more chapters. :)

I read your story with great interest. It's well-written and delves deeper into the psyche of a potential "meat girl" than is typical. Her character is convincingly portrayed. However, I also felt a certain sympathy for the girl. Ouch, that happened to me again. :D That's the danger with well-written, long stories.

The AI-generated imagery simulation showed that the metal skewer would fit well in her body. I'd be interested to know exactly where the wedding celebration would take place. I'm deliberately writing in the subjunctive mood. Like a previous commenter, I'm hoping for a surprise. And another question: would it be a vertical or horizontal skewer roast? With a vertical skewer roast, the extension of the skewer is triggered automatically on the grill. The "meat girl" can also operate the lever herself.

Some spit-roasted meats can be seen here in vertical mode. https://boards.guro.cx/ai/koko.php?res=14586&page=0#p13_15072

I hope for a sequel soon. However, I also know that quality content takes time. Best of luck with the rest of the writing.

@Symbri, I think you will enjoy this unfinished masterpiece from a friend of mine. You write with a similar tone :)

Read a little and it's good so far ^^

>>16611
Pretty bad, no inherent training on related concept.

Anima is the one that has the most potential. It understands most guro and nsfw concepts out of box, just need bit more training to add gore details. Have much better prompting control over IL/Pony/Noobs (tag+caption). You can migrate LoRA training dataset from SDXL to it very easily as well.

>>16613
Got it. Thanks!

It's not meant for guro. This is the best result I could get with Z-image. It doesn't understand wounds and most organs.

Don't interrupt people mid-word 😉😈

>>15797
done: https://files.catbox.moe/0mu9ww.zip

100 epochs, might be still slightly undercooked. trained with the same captions. i think i'll have to edit them and add natural language to help training.
pw is gurochan

if anyone has more datasets, please post them

>>15972
Thanks for the effort. I've tested it a bit. It did improve the interaction between the weapon and the body, but concepts like impaling_stabbed are weak and unstable.
I'm not familiar with Chroma LoRA training, but for the Illustrious version, I use 32/32 for Network Dim/Alpha to better capture the various stabbing concepts.
Also, the style leakage is substantial in Chroma, likely because most of my dataset is in Japanese anime/manga style (which is the default style for the Illustrious model). Captioning the art style might help isolate the leakage a bit.

>>16029
Yeah, style leaking is beacuse i didn't caption it the way you should for chroma. to remove the style from getting baked in you'd add something like "A digital illustration of" and variations thereof. i do intend to do this at some point of someone doesn't train a better one with fixed captions etc

Civitai link: https://civitai.com/models/2431926/stabby-toy-sword-anima

This is just a Beta version for testing training on the Anima[preview1], trained on a pruned dataset of 183 images. A larger dataset will be used once the official Anima base model is released.
The Anima base model itself is already very capable at drawing stabbing scenes with right descriptive prompt (compared to illustrious). This LoRA just give you better controls and refine the details (especially impaling_stabbed and assisting_stabbed).

The prompting guide is written in the civitai post, you can also check the images for references.


>>16035
Dataset with tags and captions(183images): https://drive.google.com/file/d/1Ez3jR7eWMsis45tyAvjNMYJiCLIuJ_vC/view?usp=drive_link
password: gurochan

You can try training this dataset on Chroma or other base model, just have to keep it opensource.
The dataset contains both danbooru tags and natural captions: I vibe-coded a custom pipeline to tag the images first with danbooru tags(using SmilingWolf/wd-vit-tagger-v3), then feed the image along with these tags as grounding into Gemini/Kimi-K2.5 to get descriptive captions in a fixed format (defined through system prompt), then check again manually to fix errors.

>>16955
fantastic already, getting great results from it. Thank you for making these.