A nude/NSFW capable model that focuses on images with a female primary subject.
It is heavily biased towards nude images.
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...
Early Access is enabled to support the development of new versions and models.
Description
FAQ
Comments (16)
wow this is complete garbage, i wish i hadn't purchased that early access.
Sorry you didn't like it. What is the problem for you? Are you not able to get similar results to the sample images?
Are there any loras I should add for XXX porn photos?
No, look at the sample images. The workflow is included. Go nuts!
Just about every node is missing in ComfyUI, based on the image workflow. Is there a node pack that is associated?
Sorry if a noob question, I'm relatively new here.
Lots of nodes. I do not recommend it as a starting workflow. Use the default flux workflow and take it from there. Look at the image settings on CivitAI and try to match them.
Output images are always grey, does someone know how to fix that? (My gpu is 4090)
just go to grok or chatgpt and ask it for prompts to get the color, style you want.
There isn't a vae built in, so you need to add one in your generation settings.
I am new here .. but I am also getting grey blank image. It appears to be an issue with latest cuda 13.0 drivers. My GPU is 5080 and only supported by latest drivers.
Ooof, good to know. Is it only this model, or also others that give this issue?
@6tZ all other sd and sdxl models are working fine. This is the only flux model i have tried. I will try other flux models and see if the issue is consistent with flux.
same here, idk what's causing it
i have a 5090 and no issue what so ever with 20+ workflows on 10 different models varying from flux, flux 2, qwen, image turbo to wan 2.1, 2.2 and api stuff. switch to 12.8 cuda, torch 2.9.1 python 3.12. no issues whatsoever.
you should use rtx 3090 is the best gpu for ai
@mikihotAI dime short day late sadly, does it have high vram?
Details
Available On (2 platforms)
Same model published on other platforms. May have additional downloads or version variants.