---
license: creativeml-openrail-m
thumbnail: "https://m1.afileditch.ch/uJoodjDNVWxDqhhQHeRH.png"
language:
- en
tags:
- text-to-image
- stable-Diffusion
- stable-diffusion-diffusers
- diffusers
- safetensors
inference: true
---


   <p align="center"> <img src="https://s1.fileditch.ch/iMqyjOnUtxntHolBiNgT.png" width=35% height=35%> <p>
   <p align="center"> AniReal - A latent diffusion model fine-tuned to output High Quality Photorealistic anime illustrations!

<img src="https://m1.afileditch.ch/uJoodjDNVWxDqhhQHeRH.png">
 <p>

________
# 【 AniReal 】
Welcome to AniReal! a latent diffusion model Trained and Fine-Tuned on **Photorealistic High Quality** anime illustrations using the **Danbooru** tagging dataset aswell as **Blip** I made it so that it understands some natural text description alongside danbooru tags It may not work as well though but give it a shot! 
The model itself its made to output generally anything with an anime art style if u can think of it u can prompt it!
________


# Showcase
*Below are some examples generated with this model!*
<img src=https://s1.fileditch.ch/laCwJNcXRqnsDoLkbge.png width=100% height=100%>



# Usage!
- DPM++ 2S a Karras for both anatomy and quality
- Clipskip 1 or 2 works 
- Upscaler (Latent)
- Denoise Strength (0.53~0.7)
- below 0.53 Denoise Blocking can occur 



  # This project would be impossible without
- [Haisenberg](https://huggingface.co/haisenberguwu)
- [Thiros](https://huggingface.co/thiros)
- [Closertodeath](https://huggingface.co/closertodeath)
<img src="https://s1.fileditch.ch/FjLFnEcKHAFpEEEAawMP.png">

Many thanks, 
Hosioka.

# Note! 

for some reason huggingface wont let me upload ckpt or diffusers to this repo if you're looking for difffusers please revert to commit #0bb03505150d9b4b39975a9da8589b40190e7078


-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------
# License
This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage.
The CreativeML OpenRAIL License specifies: 

1. You can't use the **Model** to deliberately produce nor share illegal or harmful outputs or content 
2. The authors claims no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in the license

--------------------------------------------------------------------------------------
# TOS!
it seems that i have forgotten to update my HuggingFace repo abt my TOS so here you go.

- You are not allowed run on services that generate images for money!
- You are not allowed to Sell images they generate!
- You are not allowed to Sell this model or merges using this model!

  If a user is found to be selling my models or offering generation services you will face with consequences!
---------------------------------------------------------------------------------------
This TOS has been up on CivitAI since the release day which was a few hours away from civitAI i was not aware and did not change the TOS but here you go
<img src="https://s1.fileditch.ch/KzoisozrbwJYBVVhugW.png">
 <p>
 These models can easily be loaded to a google colab and used for FREE! stop milking my shit bruh
 heres an example colab: https://colab.research.google.com/drive/1wEa-tS10h4LlDykd87TF5zzpXIIQoCmq