Hello! I am not a model maker, I am not the original creator of the models in this merge. I am only someone who weighted merged these two models together and sharing it.
This Model is NSFW biased.
This model is a merge of the "three" model by discord member Dr. Derp, and the iCoMixV2 found here:
https://civitai.com/models/16164/icomix
It was merge block weighted with RSmoothStep2, with "three" as Model A, hence the name Revese-Three-iCo.
Dr. Derp recommends aspect ratio 512x704 or similar. As far as I know, no VAE is needed, HOWEVER, the use of SD-VAE, or Anything-VAE is likely good due to iCo using Anything and SD-VAE being generally good.
SD VAE:
https://huggingface.co/stabilityai/sd-vae-ft-mse
Anything VAE:
https://huggingface.co/andite/anything-v4.0/blob/main/anything-v4.0.vae.pt
The sample images we generated using the Bad Prompt V2 embedding at a .50 weight (ex: bad_prompt_v2:0.50)
found here:
https://huggingface.co/datasets/Nerfgun3/bad_prompt/blob/main/bad_prompt_version2.pt
And ControlNet found in WebUI Extensions, I can't speak to other methods.
Here's my DeviantArt page where I post SFW and NSFW content:
https://www.deviantart.com/adellanuki
Reverse Three iCo is a highly specialized Image generation AI Model of type Safetensors / Checkpoint AI Model created by AI community user Adellanuki. Derived from the powerful Stable Diffusion (Other) model, Reverse Three iCo 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 Reverse Three iCo is capable of generating images that are highly relevant to the specific use-cases it was designed for, such as anime, character, girl.
With a rating of 5 and over 2 ratings, Reverse Three iCo is a popular choice among users for generating high-quality images from text prompts.
Yes! You can download the latest version of Reverse Three iCo from here.
To use Reverse Three iCo, 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 Reverse Three iCo, check out our crash course in AI image generation.
More Porn, More Style.
Merge weights provided in image form with model samples.