- You can download version 0.9 Pony as Digital Product or with Membership April 2025 models collection.
- You can download version 0.8 Pony as Digital Product or with Membership April 2025 models collection.
- You can download version 0.7 XL as Digital Product or with Membership April 2025 models collection.
- More cool models
ℹ️ XL/Pony version of 💛 xVision. 🌈
ℹ️ xVision 0.9 Pony - Many changes and improvements, intending to improve colors, bodies and faces, enhancements to default style.
ℹ️ xVision 0.8 Pony - has improvements to sexually explicit content.
ℹ️ xVision 0.7 XL - is a starting point for XL branch of xVision, it's not an exact copy of 💛 xVision 1.0, and I will continue to evolve it.
How it works?
Choose Product or Subscribe:
Get this model via a Ko-fi product, or
Join the appropriate membership tier:
Model released during current month: Current Month Content
If model released in previous months: All Months Content
You will be prompted to link your Hugging Face and Ko-fi emails.
Hugging Face access is checked by email, which might be different from your Ko-fi email. You will receive a link from Ko-fi to add the email and continue.Request Access on Hugging Face:
After you acquired product or subscription, you’ll receive a link to a gated Hugging Face repository.Click "Request Access".
Your access will be approved automatically within a minute.
Download & Use:
You can then download and use the model under the license provided in the repository (LICENSE.md).
Why I Created My Own Access Control
I have been a creator on Civitai since December 2022. My goal has always been to help make model training, design, and development a sustainable, professional activity, not only for myself, but for other creators too. Supporting people who want to create models professionally is good for users, for creators, for the entire community, including Civitai itself.
Civitai has shared some of this vision and has tried to create ways to support creators. Unfortunately, their current Creators Program has serious problems:
Civitai was deplatformed by payment processors and operates at a loss.
The current compensation model pays creators mainly for model usage in the generator.
Early Access limits paid access to only 15 days, after which models must be free.
Buzz extraction value has dropped to ~45% of its original worth, making withdrawals basically a 55% fee.
Bugs and creator feedback are ignored for months, and several team members who used to listen have left.
I believe this system is unfair, harmful, and exploitative. Creators should be able to:
Sell models without arbitrary time limits.
Pay a fair platform fee of 15% or less.
Civitai briefly tested a much better system called Clubs in early 2024, which worked well for creators, but it was canceled after backlash from a loud minority that opposed fair creator compensation. I have long hoped Civitai would fix these issues, as I’ve suggested in my articles:
But nothing has changed. Bugs remain unresolved, feedback is ignored, and I’ve lost optimism about Civitai’s willingness to improve.
That’s why I’ve decided to experiment with my own alternative access control system, a fairer way to share models with users who value my work.
Description
- You can download version 0.7 XL as Digital Product or with Membership April 2025 models collection.
ℹ️ Version 0.7 is a starting point for XL branch of xVision, it's not an exact copy of 💛 xVision 1.0, and I will continue to evolve it.
FAQ
Comments (15)
This model does not work for me. Generates pure white images. Assembly: Fooocus
Hi @shenija74 ,
I'm not sure, maybe it's something related to your GPU and VAE. Check your logs. Usually, WebUI switches automatically to fp32 VAE, or you can use your own VAE.
Maybe your WebUI is old, version 1.6+ should work.
EDG made a review with his system: https://civitai.com/models/314439?dialog=resourceReview&reviewId=603364
And it worked ok for him.
What do you mean by "Assembly: Fooocus"?
@shenija74
I'm not familiar with Fooocus.
I use: https://github.com/AUTOMATIC1111/stable-diffusion-webui
Version 1.6+
It doesn't seem that anyone else is complaining about issues with the model, so it's probably something in your setup/settings.
Make sure you have downloaded the whole file, around 6.5GB.
You can ask for help on Fooocus github, it might be some issue related to GPU and VAE fp16/fp32 - it's handled automatically in AUTOMATIC1111, so I would recommend using it.
I'm using Fooocus as well - it works perfectly with this model: https://civitai.com/posts/1499003
You are experiencing a typical Fooocus problem caused by it's styles, more specifically, by how they modify the prompts and some model parameters on the backend. Uncheck everything on "Styles" tab and turn them back on one by one to see what's causing the output to be garbled.
@latex_waifu
Thank you, hopefully, it will help @shenija74 .
@latex_waifu The method is certainly educational, but does not solve the fundamental problem what lies in the checkpoint)) it still doesn't create pictures correctly to prompt and have noise problems))
@agress74
Your image is lacking PNG info, I don't know how you made it.
Have you used Fooocus?
All my images have all the generation metadata with them.
@alexds9 yes its made in foocus, same problem in forge web ui. I can say what most users will not encounter this error. definitely aggravates this problem fooocus enhance. I have now assembled a checkpoint similar to yours from other components and on the same prompt I have the same error, they are a little less pronounced but it is still there! I dont know what to do with that
@agress74
I see. Unfortunately, I've never used Fooocus or Forge, so I wouldn't be able to help with that. Maybe you can ask on the GitHub pages for the relevant projects - they might have a workaround or be able to solve the issue in the code.
I do use Automatic 1111 WebUI, which works fine most of the time 🙂, and has the most users and the most support, so I would definitely recommend using it.
I'm not sure if it's related to your problems, but there were a few updates in the last Automatic 1111 WebUI 1.8 version, with torch and xformers updates, and many optimizations, and I have seen errors related to VAE fp16 starting to appear sometimes, then disappear.
Also, it seems that attention optimization xformers/sdp and others might produce half-generated images with smudges, so I think there is some bug related to it. Something less severe than the images you have published, but still noticeable.
Another issue, I saw sometimes certain prompts turn into clouds of noise. Some time ago, there was an article that said it was a bug related to a certain line in the code that used the wrong multiplication. I can't find the reference now, so I'm not sure if it was fixed. Removing brackets and high emphasis from prompts might help.
By the way, you said that you used similar components, what have you used exactly?
@alexds9 :mklan1831, mfcgPDXL, pilgrim unreal, quiet goodnight. In ConfyUi same fails
@agress74
Ah, interesting models, I haven't ever seen or used them...
If you are having same issue with ConfyUI too, it's probably related to your virtual environment, python/torch/xformers/diffusers or something else.
I can only think of making a clean virtual environment and use Automatic 1111 WebUI.
Do you have NVIDIA GPU with +8GB Vram?
@agress74 I can only speak about the experience I personally had. After completing the steps I already described it worked totally fine for me.
@alexds9 only 8gb 1070ti. Thats why i cant use xl models in clear automatic. My experience of using it suggests that these errors will also occur in automic. Might be it will be looks another way. I use this prompt to check for a few other errors, and usually more intricate variants of prompta lead to this result. But they are just passing by and this one is not.
@agress74
8GB is enough for XL models. I have RTX 2080 with 8GB and it works fine with Automatic 1111 and XL models, without a refiner - not sure anyone even using a refiner...
They added a lot of optimizations in Automatic 1111 version 1.8, which came out a couple of days ago, so I can make even relatively large images with XL.
With your 8GB Vram you should be able to make similar images to what I make, maybe a little bit slower...