KNXO's experimental crappy model mix (Anything 4.5 based)
Anything 4.5 OG VAE FP16
knxo
Edit:
I screwed up and uploaded the anything 4.5 with the original VAE i knew it was suspiciously blurry. I am adding the correct version. will leave the other one as it still has a fix and the conversion to FP16 (btw making test images with dudes is not only frustrating but unrewarding.)
Update:
Saw some people using the baked in vae which is the original in anything 4.5 which sucked. So i added a new version with some fixes and clearvae baked in.
The fixes I had also done on the original anything 4.5 by andite. So i decided to post the fixed file too. It should work basically the same as the original but it has clearvae baked in and is saved at FP16 making the file smaller than the other posted in civitai. This fixes the common blurriness issue to some extent.
Old:
Erm, was playing with Kohya's model merge then with supermerger. A couple days back I made a negative embedding for anything 4.5 So the idea went like this: what if i do a crap lora with my negative embedding dataset and then invert it and merge it onto anything 4.5.
So i trained a literally crappy lora and stuffed it into 4.5 with a couple of my LORAs. Honestly the result isn't that great but it doesn't need as many negatives as OG 4.5.
The result is: horny! In average a slightly bigger cup size, thinner waist and bigger hips. Bias towards making females is even bigger. Bias towards nudity increased by a lot. Dudes look odd! (Might like it if you like slightly feminine bishonen types?)
So I spent about a week playing with it to tweak the block weight and it was likely going to simply rot in my hdd forever so instead here it is.
IT should work ok-ish without negatives or positives, you can still use them and it looked better with my negative embedding
What is KNXO's experimental crappy model mix (Anything 4.5 based)?
KNXO's experimental crappy model mix (Anything 4.5 based) is a highly specialized Image generation AI Model of type Safetensors / Checkpoint AI Model created by AI community user knxo. Derived from the powerful Stable Diffusion (SD 1.5) model, KNXO's experimental crappy model mix (Anything 4.5 based) has undergone an extensive fine-tuning process, leveraging the power of a dataset consisting of images generated by other AI models or user-contributed data. This fine-tuning process ensures that KNXO's experimental crappy model mix (Anything 4.5 based) is capable of generating images that are highly relevant to the specific use-cases it was designed for, such as anime, base model, experimental.
With a rating of 0 and over 0 ratings, KNXO's experimental crappy model mix (Anything 4.5 based) is a popular choice among users for generating high-quality images from text prompts.
Can I download KNXO's experimental crappy model mix (Anything 4.5 based)?
Yes! You can download the latest version of KNXO's experimental crappy model mix (Anything 4.5 based) from here.
How to use KNXO's experimental crappy model mix (Anything 4.5 based)?
To use KNXO's experimental crappy model mix (Anything 4.5 based), download the model checkpoint file and set up an UI for running Stable Diffusion models (for example, AUTOMATIC1111). Then, provide the model with a detailed text prompt to generate an image. Experiment with different prompts and settings to achieve the desired results. If this sounds a bit complicated, check out our initial guide to Stable Diffusion – it might be of help. And if you really want to dive deep into AI image generation and understand how set up AUTOMATIC1111 to use Safetensors / Checkpoint AI Models like KNXO's experimental crappy model mix (Anything 4.5 based), check out our crash course in AI image generation.
Popularity
Info
Latest version (Anything 4.5 OG VAE FP16): 2 Files
About this version: Anything 4.5 OG VAE FP16
The original Anything 4.5 by andite with Some fixes applied, saved as fp16 I screwed up and added the one with the original VAE
4 Versions
Go ahead and upload yours!
