Welcome to The Fux!
The goal of this model is to unlock full NSFW capabilities in Flux, one step at a time, starting with a photorealistic female focus. Enjoy the show!
Recommended Settings
Recommended Settings
Sampler is dpmpp_2m (DPM++ 2M) and the scheduler is beta
No VAE or CLIP is baked in. Use separate sources for those.
Each sample/preview image contains the used workflow. Here's a quick article with simpler more beginner-friendly workflow. This is a recommended starting point.
FP8 Download
For some reason, when you upload multiple formats (BF16 + FP8) on one model, which they now support, they hide the FP8 under the BF16 model group in the side menu...
Description
FAQ
Comments (12)
Hi. I really want to try your model, but I have a problem: I only have 6.5 GB models. Could you tell me if there will be a modern version?
Hey, you can always try it with the generator online.
But I do sometimes upload lower quality versions too. I intend to do it for this version.
@6tZ Yeah that would be great if you could do a Q4K_M, awesome model!
If you're on a 6GB GPU, my understanding is that these models do work if you use the Q4 GGUF versions with the GGUF workflow, but since they are based on Flux.1 DEV and not Flux.1 SCHNELL, with a weak GPU expect very very long creation times at 20 steps. Think like 10+ minutes for an image at 1216 x 864 or some similar high res and 5 minutes for 768 x 512.
Testing this right now to see if there is any workaround, and it looks like there are very few Schnell models out there which are uncensored like this one.
Listen, isn't it easier to release a 6GB Neural Network than for me to spend credits on generating content on the site? Yeah, I get it, the author needs money, but they also give him money for downloading, like, lightning.
I'm all for the author releasing a condensed version, that would be cool.
@olegator_T1000 Not for me it isn't :)
Civit is having problem with file uploads. I have been trying for 2 days to upload smaller versions of the models. It will bp FP8, not sure if it will fit in 6.5gb.
Smaller version now out @olegator_T1000
6tZ Will the 3050RTX laptop handle my 6GB of video memory? It weighs 22GB, though. I don't think it'll even come close to starting. :) Sorry for confusing you, I just really like your model, but I don't want to check the features and limits on the website. I use AI locally.
6tZ Well, like, release an XL version.
@olegator_T1000 It doesn't work like that.
It's a separate base model. You can't convert it to SDXL.
The FP8 version is out now, it's 11gb.