PLEASE NOTE: The images you will receive when using this model unmixed will not in any way, shape, or form resemble the images provided here, which were generated by mixing this model with RealisticVision1.4. The images you will receive are, come to find out, against the ToS. (Though are not particularly gruesome; mostly they are just abstractly unsettling.)
I trained this on 640 photographs of crime scenes from the 1910s, taken from the NYC municipal archives. My intention was to make a thing that would generate random crime scenes for a noir/detective project without any need for prompting, and in that, it succeeds, though as a stand-alone, it is very much a one-trick-pony. It is very, very, very strong and inflexible—prompting is nearly useless—but I have mixed it with a few other ckpts to good effect (~30% of cr1m3 in the mix for best results, in my testing.) and you are encouraged to fuss around with it.
NOTE: If you see long crutch-looking metal poles around the edges of your synths, this is because many of the photos in the training data featured these. They're tripod legs.
Description
FAQ
Comments (12)
Definitely one of the more interesting and unusual uses for SD that I've ever seen. Not sure how I'd ever need it, but I'm glad someone made it.
A bit too graphic for my taste. Only thing I can see using it for is a Cthulhu or detective ttrpg game.
Your pictures above have the model described as:
Model
0.7(Realistic_Vision_V1.4) + 0.3(cr1m32_cr1m32_64800) did you merge these two?stealing an artist's style is one thing, but the likeness of murder victims? what's the matter with you? unbelievably tasteless, there is no use or justification for it and journos will have a field day with it if they catch wind of it.
I couldnt get images like the preview ones, even using the same generation data. I always get black and white messy pictures. Sometimes generating in batch I can distinguish the body in the picture but still its not like the preview.
Good model tho, I like the idea
Can you add, if possible, a smaller 2gb pruned fp16 no-baked-vae safetensor version ?
Lovely concept. Great idea.
Cool preview images, why don't mine look anything remotely like that?
That's the problem.
After many attempts ,I couldn't generate a single colored image. On the bright side, if you added "Aged Poloroid" to your prompt, and print it out the resulting image on glossy paper, you can hide it in an neighbor's house.
If they never find it, it becomes a generational prank and no one will -ever- be able to explain what the hell they're looking at.
I haven't tried this yet because I'm swamped with current projects, but major props for doing something new and not making yet another hentai lora.
Honestly, you should upload the mix. Looks cool
Can I ask you the meaning of the prompt word ([supermodel:goth:30]:1.3)?
真的无语 完全生成不出图
look pretty good, i have to try this with my corpse LoRA
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.