Just my junky models I use to fix up my MJ/Niji images
I merge a bit...maybe a bit too much π and sometimes I mix models that I end up liking, so I thought I would share,
Will they work for you? I do not know... but good luck π
One of the custom models I have been using a bit for my current images, so I thought I share... :p
Don't ask for recipe, I did not save it, I just know some of the more popular ones when in, then merged into oblivion to create something that fits my taste buds.
works best with Eulear a
VAE baked in
I like this model because I enjoy how it makes my male characters look :p
simple prompts work best and go easy on the parentheses (( ))
Face fix is a must
Hands are a hit or miss, sometimes they are decent, other times they are an abomination lol.
__________________________________________________________________________________________________
it's exactly what it sounds like, deranged, unhinged and chaotic.
highlights: Chaotic, complex backgrounds (with proper prompting), dynamic, nsfw π more on semi-real 2d elements, but have been able to do realistic (semi) images. It's a bit toasty so be careful when using Loras at high weights, but I have been able to stack loras with proper adjustments. Ad 3d to neg to flatten it, if you want :p
negatives: Hands can be an issue at times, sometimes things can get a bit too chaotic, crazy, toasty, tried to fix the shiny skin issue buuuuut, whoopsie still kinda there π, some artifacts at times, some prompts can break images
Sampling methods:
Eulear a = softer, less saturated
DPM++ 2M = harsher lines, bolder lines, more chaos, saturated
__________________________________________________________________________________________________
ADETAILER is highly advised, please use it - https://github.com/Bing-su/adetailer
(If you can't use adetailer I advised to to not use this model.)
If you must, use inpaint to fix issues like messed up hands.
if you need help with prompting just take the parameters from my images, I will always share my prompts :D need more help, just hit me up, always happy to help.
I have been using both models to help with my artwork, both offer something different, similar? Maybe but I have been alternating with them. I usually just make stuff that fits my tastes, it may not be for everyone and that's okay, but hey if you find it helpful or you end up enjoying it, that's all that matters right? π
Dercius for testing the model out for me β₯
tamtamx1332 for the amazing block merger comfyui workflow β₯ and for the base model π
sulph for making this: https://civitai.com/articles/6183/merge-block-weights (Thank you π)
most of the models are merged to oblivion (using the block merge method) so I end up forgetting the parent model (original). I will remember to write down whenever I take a parent model and add it to credits.
Permissions on this model: if you ever use it to merge and upload the model, I just ask you allow merge share and free download. I believe in open source and freedom, I want the public to be allowed to better things with out restrictions and I want to allow others to be able to share creations. AI art is a blessing.
JunkJuice is a highly specialized Image generation AI Model of type Safetensors / Checkpoint AI Model created by AI community user skumerz. Derived from the powerful Stable Diffusion (Pony) model, JunkJuice 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 JunkJuice is capable of generating images that are highly relevant to the specific use-cases it was designed for, such as base model, woman, man.
With a rating of 0 and over 0 ratings, JunkJuice is a popular choice among users for generating high-quality images from text prompts.
Yes! You can download the latest version of JunkJuice from here.
To use JunkJuice, 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 β 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 JunkJuice, check out our crash course in AI image generation.
if you see this, congratulations. poke your nose.
Go ahead and upload yours!
Your query returned no results β please try removing some filters or trying a different term.