README.md

---
license: creativeml-openrail-m
tags:
- coreml
- stable-diffusion
- text-to-image
---

# Core ML converted model

This model was converted to Core ML for use on Apple Silicon devices by following Apple's instructions [here](https://github.com/apple/ml-stable-diffusion#-converting-models-to-core-ml).\
Provide the model to an app such as [Mochi Diffusion](https://github.com/godly-devotion/MochiDiffusion) to generate images.

`split_einsum` versions are compatible with all compute units.\
`original` versions are only compatible with `CPU & GPU`.

# 3DKX V2

Sources: [Hugging Face](https://huggingface.co/unvailai/3DKX_V2) - [CivitAI](https://civitai.com/models/2504/handas-3dkx-11)

<img width="604px" src="https://cdn.discordapp.com/attachments/1051410188592226364/1076941914538004581/ezgif-3-7ac098980a.gif">
<img width="768px" src="https://cdn.discordapp.com/attachments/1051410188592226364/1076932535445098626/1.png">
<img width="768px" src="https://cdn.discordapp.com/attachments/1051410188592226364/1076932536120385657/2.png">
<img width="768px" src="https://cdn.discordapp.com/attachments/1051410188592226364/1076932536795664405/3.png">
<img width="768px" src="https://cdn.discordapp.com/attachments/1051410188592226364/1076932537416433835/4.png">
<img width="768px" src="https://cdn.discordapp.com/attachments/1051410188592226364/1076932538041372782/5.png">
<img width="768px" src="https://cdn.discordapp.com/attachments/1051410188592226364/1076932538783768626/6.png">
<img width="768px" src="https://cdn.discordapp.com/attachments/1051410188592226364/1076932539664580688/7.png">
<img width="768px" src="https://cdn.discordapp.com/attachments/1051410188592226364/1076932540327268413/8.png">
<img width="768px" src="https://cdn.discordapp.com/attachments/1051410188592226364/1076932541052895292/9.png">
<img width="768px" src="https://cdn.discordapp.com/attachments/1051410188592226364/1076932541614923818/10.png">
<img width="768px" src="https://cdn.discordapp.com/attachments/1051410188592226364/1076932544534151178/11.png">
<img width="768px" src="https://cdn.discordapp.com/attachments/1051410188592226364/1076932545117179924/12.png">


## Model Description

<!-- Provide a longer summary of what this model is. -->

3DKX V2 is a model that was trained on highly detailed 3D rendered pictures of various subjects such as landscapes, scenes, models, textures, and more. 
Our aim is to provide a useful tool that can produce consistent and high-resolution renders for creative purposes such as storyboarding, sketching, templates, wallpapers, and more.

- **Created By:** Unvail ai
- **Language(s) (NLP):** English
- **License:** **Modified** creativeml-openrail-m
- **Finetuned from model:** SimpMaker 3k3


# Uses

<!-- 3DKX is a model that was trained on highly detailed 3D rendered pictures of various subjects such as landscapes, scenes, models, textures, and more. 
Our aim is to provide a useful tool that can produce consistent and high-resolution renders for creative purposes such as storyboarding, sketching, templates, wallpapers, and more. -->
- 3D renders, cartoony or realistic
- Landscapes
- Scenery
- Fantasy, creatures, RPG renders
- Portraits
- Dramatic scenes, horror, dark, obscure

## Get started with the model, use our cheat sheet !

Use the guide in the link below to get started with the model !
[3DKX_V2 Presentation/Guide](https://docs.google.com/presentation/d/1zG-pvw47ZRO9JjCkU3B2YbcYNwOHoNQ27qN6h-Xs0mM)

## License & User Restrictions
You agree not to use the Model or Derivatives of the Model:
- To host, finetune, or do inference with the model or its derivatives on websites/apps/etc. If you want to, please email us at contact@unvail.ai
- Not to use this outputs of this model commercially if you are an organization/team of 10 members or more.
- In any way that violates any applicable national, federal, state, local or international law or regulation;
- For the purpose of exploiting, harming or attempting to exploit or harm minors in any way;
- To generate or disseminate verifiably false information and/or content with the purpose of harming others;
- To generate or disseminate personal identifiable information that can be used to harm an individual;
- To defame, disparage or otherwise harass others;
- For fully automated decision making that adversely impacts an individual’s legal rights or otherwise creates or modifies a binding, enforceable obligation;
- For any use intended to or which has the effect of discriminating against or harming individuals or groups based on online or offline social behavior or known or predicted personal or personality characteristics;
- To exploit any of the vulnerabilities of a specific group of persons based on their age, social, physical or mental characteristics, in order to materially distort the behavior of a person pertaining to that group in a manner that causes or is likely to cause that person or another person physical or psychological harm;
- For any use intended to or which has the effect of discriminating against individuals or groups based on legally protected characteristics or categories;
- To provide medical advice and medical results interpretation;
- To generate or disseminate information for the purpose to be used for administration of justice, law enforcement, immigration or asylum processes, such as predicting an individual will commit fraud/crime commitment (e.g. by text profiling, drawing causal relationships between assertions made in documents, indiscriminate and arbitrarily-targeted use).
Note: All derivatives of our model created by users **must** include the same license & user agreements.

## Important notes: 
- Our datasets contains no mentions of the artist's name, nor specific styles from any artist whatsoever. 
- The creators (unvail ai) will not be held accountable for the way this model is being used or the outputs that any person may generate.
- The purpose of this model isn't to replicate a style, but to provide a useful tool to creators of all kinds to generate 3D related contents
- Be advised that this model can generate explicit material and therefore shouldn't be used in any way to cause harm or produce non-consensual sexual content.  

# Training Details

**Base Model**: SD 1.5
**Steps**: 15,000
**Training Method**: Finetuning
**Trigger Keywords**: None really, but the main styles trained are "3d render" and "3d cartoon" see our presentation slide for more details.


<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
Big shoutout to this new code that allowed us to fix the diffusion noise, allowing for more depth, contrast, and white level balance in the outputs.
https://www.crosslabs.org//blog/diffusion-with-offset-noise