It seems a lot of people are using Grok to get violence and gore effects. But they have to play a lot of games to get around its content filters. Many don't want to pay for access to Grok either (I wouldn't) so they're making one dummy email account after another to get more free access.

I've decided to take the route of setting up my own ComfyUI setup at home, which require spending a bit for a decent graphics card. I've been concentrating at getting what I can out of Wan 2.2.

It's not an approach for the faint of heart. Lots of technical frustrations and challenges. I'm hoping that if I put in enough time and effort, however, I'll eventually be able to create decent stuff without dodging content filters.

I see... Any other alternative? Some software I can download? I heard something about Stable Difusion but I don't know what it is

If you don't want to use Comfyui, you should start with pinokio and get fooocus for image, WANGP for animation and forge for inpainting

What's comfyui and why wouldn't I want to use it?

>>16195
ComfyUI is a node-based AI tool (though it can do some other stuff) - very powerful, but also really difficult to use if you don’t have an existing workflow to use. It’s notorious for having a steep learning curve, but it’s pretty popular due to how flexible it is. I use it for my own guro gens, alongside other stuff.

>>16107
learn to make still images then learn how to turn those images into video. look up tutorials on stablediffusion and how to set up comfyui. browse civitai and see what other people have done - the galleries usually have the prompts and models used - and try to emulate them. there's also workflows for comfyui on civitai to try out. guro stuff is pretty niche so it's easier to learn how to make more vanilla content first then add in some ketchup.

if you don't have a monster computer it's gonna take forever to generate anything locally. but if you want explicit sexual content though running things locally is quickly becoming the only way, the big online models like grok are quickly becoming censorsed over time. they still do violence well, there's a thread with a bunch of prompts for grok to make guro content but just about anything sexual gets rejected.

While the previous answers are factually correct they are not very helpful.


Let's clear what you wnat to do.
What you want to generate? video or images?
Do you want to do in on cloud or on your local machine?

In steps.

Video on cloud. Your best option is grok. You can generate for free with an email. Quite good, only partially censored.

Video local. Wan 2.2 with specific LORA. I have no experience with . You will find more info on civitAI.

Image Cloud. Your best best is NovelAI. I have not tried it, so I cannot comment. You will need to pay.

Image local. THe most popular one as it has NO censorship whatsoever.
Stable diffusion is a family of models you can run. ComfyUI mentioned by other people is the software that allows you to run a model.

>>16264
FOr Local image generation here is the guide form 4chan.
>Pick one and install Stable Diffusion
https://github.com/comfyanonymous/ComfyUI?tab=readme-ov-file#installing
(new Forge) https://github.com/Haoming02/sd-webui-forge-classic/tree/neo
(deprecated) https://github.com/lllyasviel/stable-diffusion-webui-forge?tab=readme-ov-file#installing-forge
ComfyUI image/video model guides
https://github.com/comfyanonymous/ComfyUI?tab=readme-ov-file#examples

>Recommended XL models
NoobAI: https://civitai.com/models/833294/noobai-xl-nai-xl
DHXL: https://civitai.com/models/1291404/dhxlv10
Illustrious: https://civitai.com/models/795765/illustrious-xl
ConfettiTuneXL: https://civitai.com/models/184813/animeconfettitunexl
-
DMD2 speed LoRA: https://civitai.com/models/1608870/dmd2-speed-lora-sdxl-pony-illustrious

>Uncensored Flux model
Chroma: https://civitai.com/models/1330309/chroma | https://civitai.com/models/1807633/chroma-unlocked-q4ks (low VRAM)

>New models to try out
Z Image: https://civitai.com/models/2342797/z-image-base
Flux.2 Klein: https://civitai.com/models/2322332/flux2-klein

>AI image upscaler model database
https://github.com/OpenModelDB/open-model-database

>LoRA metadata viewer in HTML form
https://github.com/Xypher7/lora-metadata-viewer

>Optional extensions
https://github.com/DominikDoom/a1111-sd-webui-tagcomplete
https://github.com/hako-mikan/sd-webui-regional-prompter
For ComfyUI:
https://github.com/ltdrdata/ComfyUI-Manager

>IS MY GPU GOOD ENOUGH?
https://www.tomshardware.com/pc-components/gpus/stable-diffusion-benchmarks

>>16265
Once you decided what you want to do and start doing it, ask more questions. I can share the guro specific anime models.

>>16264

I've actually found that the default settings for Text to Image creation for the NetaYume Lumnia model for local ComfyUI generation works GREAT!

I set it to about 30 steps and its accuracy is pretty good! I can give it character names, what ever circumstances, and it usually comes pretty close!

>>16264
Which one was the Image Local? I think you missed stating which one it was.

>>16264
> FOr Local image generation here is the guide form 4chan...

Thank you for all of this!

I've been working with my first ComfyUI installation for about three weeks now. I'm slowly making progress, but there's still a lot I have to learn. You list of various resources looks like it could help me quite a bit.

Currently using chroma. Are there any guro related loras I should be aware of?