---
license: creativeml-openrail-m
language:
  - en
pipeline_tag: text-to-image
tags:
  - art
  - anime
  - stable-diffusion
library_name: safetensors
---

<style>
  .custom-table {
    table-layout: fixed;
    width: 100%;
    border-collapse: collapse;
    margin-top: 2em;
  }
  .custom-table td {
    width: 50%;
    vertical-align: top;
    padding: 10px;
    box-shadow: 0px 0px 10px 0px rgba(0,0,0,0.15);
  }
  .custom-image {
    width: 100%;
    height: auto;
    object-fit: cover;
    border-radius: 7px;
    transition: transform .7s;
    margin-bottom: 1em;
  }
  .custom-image:hover {
    transform: scale(1.05);
  }
</style>

<p align="center", style="font-size: 3.6rem; font-weight: bold">🎑 ~ Amedira ~ 🎏</p>

<hr>

<table class="custom-table">
  <tr>
    <td>
      <a href="https://huggingface.co/AshtakaOOf/Amedira/blob/main/Images/gawr-rain.webp">
        <img class="custom-image" src="https://huggingface.co/AshtakaOOf/Amedira/resolve/main/Images/gawr-rain.webp" alt="Gawr Rain">
      </a>
    </td>
    <td>
      <a href="https://huggingface.co/AshtakaOOf/Amedira/blob/main/Images/sunflower.webp">
        <img class="custom-image" src="https://huggingface.co/AshtakaOOf/Amedira/resolve/main/Images/sunflower.webp" alt="Sunflower">
      </a>
    </td>
    <td>
      <a href="https://huggingface.co/AshtakaOOf/Amedira/blob/main/Images/miko-miku.webp">
        <img class="custom-image" src="https://huggingface.co/AshtakaOOf/Amedira/resolve/main/Images/miko-miku.webp" alt="Miko Miku">
      </a>
    </td>
  </tr>
</table>

<p align="center", style="font-size: 1.2rem; ">These are samples from bV3 without negative embeddings</p>

<hr>

## 🎈 ❱ A model merge using clip transfer and more

This model is capable of doing multiples styles, such as flat and 2.5d.

You can also prompt Hololive vtubers with their danbooru tags (you will need to prompt their outfit too for some of them).

And it is somewhat compatible with LoRA and lyCORIS.

Every models in this repository should be made using some sort of clip transfer, except if said otherwise.

<hr>

### 💡 ❱ Useful Tokens to make the most out of Amedira
- **SLE** is a token that will improve eyes quality and saturation, and it come from [AuroraOne](#🥁-❱-credits).
```
SLE
```
and
```
masterpiece, detailed background, mksks style
```
Don't change the weight of these tokens

### Style tokens:

#### [Check out the AuroraOne page](https://huggingface.co/SweetLuna/Aurora#%E2%96%BC-versatility) (most should work)

These tokens won't work very well on bV3, cV and Dreams

<hr>

## 📥 ❱ Downloads section

#### These are the models I have merged and published
**bV** retains most of AuroraOne features

**bV2** and **2.5** are somewhat competent Models

**bV3** is a big improvement in my opinion

**cV** is a mix of both bV3 and Counterfeit 3

**mV** is a very good model made with more MeinaMix 10

Don't hesitate to try the inpainting versions on InvokeAI canvas.

### Amedira
- [Amedira **bV**](https://huggingface.co/AshtakaOOf/Amedira/blob/main/Amedira-bV.safetensors) Original version (still good)

- [Amedira **bV2.5**](https://huggingface.co/AshtakaOOf/Amedira/blob/main/Amedira-bV2.5.safetensors) bV2 but with a new improved clip
  - [Amedira **bV2**](https://huggingface.co/AshtakaOOf/Amedira/blob/main/Amedira-bV2.safetensors) Nope ~~better than bV overall~~

- [Amedira **bV3**](https://huggingface.co/AshtakaOOf/Amedira/blob/main/Amedira-bV3.safetensors) The best version

- [Amedira **cV**](https://huggingface.co/AshtakaOOf/Amedira/blob/main/Amedira-cV.safetensors) Counterfeit style but better?

- [Amedira **mV**](https://huggingface.co/AshtakaOOf/Amedira/blob/main/Amedira-mV.safetensors) Bit more MeinaMix sprinkled in

#### Dreams
- [Dreams variant folder](https://huggingface.co/AshtakaOOf/Amedira/tree/main/Dreams)

The Dreams variant are experimental/accidental merges that I keep because they have unique styles.

<details id="Dropdown">
 <summary style="font-size: 1.10em"><strong>📜 Changelogs </strong> (click to open the dropdown)</summary>

### October 11 2023
- Overhauled README.md
- Added images

### September 11 2023
- Added bV3 inpainting version
- Added cV which is a nice Counterfeit mix
- Added link to embeddings for negative prompt

### August 30 2023
- Added Amedira bV3 which fixes bg even more + misc fixes

### July 24 2023
- Added the clip models used in 1.0 and 2.5

### July 9 2023
- Added Amedira bV2.5 which fix some downgrades from bV2

### July 6 2023
- Added Amedira bV2 which is bV but better background etc

#### July 5 2023
- Added Fuzzy and Scenic Dreams variant

#### June 24 2023
- Added Koofy and Ligne Dreams variant

#### June 22 2023
- Added inpainting version of mV

#### June 20 2023
- Added Dreams variant
- New README

#### June 19 2023
- Added Amedira mV
- Amedira renamed to bV
- New huggingface repo

#### June 11 2023
- Added Inpainting version
- Released Lunamedira eV1 and eV2

#### June 10 2023
- Added Amedira
</details>
<hr>

## 🧬 ❱ Usage

#### Negative prompt
```
(worst quality, low quality:1.2), [an10:fcNeg-neg:8], (etone:0.4), negative_hand-neg, nsfw, lowres, bad hands, bad anatomy, watermark
```
`negative_hand-neg` isn't needed and is very luck based

#### Embeddings Downloads

- [**fcNeg-neg**](https://civitai.com/models/81575), [Direct download](https://civitai.com/api/download/models/97691?type=Negative&format=Other)
- [**an10**](https://civitai.com/models/58726), [Direct download](https://civitai.com/api/download/models/144998?type=Model&format=PickleTensor)
- [**negative_hand-neg**](https://civitai.com/models/56519), [Direct download](https://civitai.com/api/download/models/60938?type=Negative&format=Other)
- [**etone**](https://cdn.discordapp.com/attachments/1019446913268973689/1126669053105287279/etone.safetensors) by closertodeath

#### VAE
- [**WD 1.4 Blessed09**](https://huggingface.co/NoCrypt/resources/resolve/main/VAE/wd-blessed09.vae.safetensors) (kl-f8-anime2 but blessed down)

# 🥁 ❱ Credits

- Checkpoints
  - [**AuroraOne**](https://huggingface.co/SweetLuna/Aurora) by SweetLuna
  - [**Based66 V3.0**](https://civitai.com/models/61643) by AnonymousM
  - [**MeinaMix V1.0**](https://civitai.com/models/7240) by Meina
  - [**DiaMix V2.0**](https://civitai.com/models/75949) by Cinsdia
  - [**OpenNiji V2**](https://civitai.com/models/14479) by Korakoe
  - [**DetailedProjectV5**](https://huggingface.co/closertodeath/detailedproject/blob/main/experimental/detailedprojectv5-000012.safetensors) by closertodeath
  - **ALunarDream 2.0** by Luna Chan
  - [**ExpMixLine**](https://civitai.com/models/44150/expmixline) by Mods13
  - [**Gishiki**](https://huggingface.co/Aotsuyu/Gishiki) by Aotsuyu
  - [**Counterfeit v3.0**](https://civitai.com/models/4468)
  - [**OrangeMixs AOM3B2**](https://huggingface.co/WarriorMama777/OrangeMixs#aom3b2)
- LoRA/lyCORIS
  - [**Jordan_3**](https://cdn.discordapp.com/attachments/1066614732099964989/1071484257962315816/Jordan_3.safetensors) by deleted user
  - [**LoraEyes**](https://civitai.com/models/5529/eye-lora) by Kokoboy
  - [**Niji Style**](https://civitai.com/models/96441/niji-style-was-asked-to-do) by KoRo_
  - [**Silicon-landscape-isolation**](https://huggingface.co/ashen-sensored/lora-isolation-collection/blob/main/Silicon-landscape-isolation.safetensors) by ashen-sensored
  - [**lighting-locon**](https://huggingface.co/closertodeath/ctdlora/blob/main/locon/lighting-locon.safetensors) by closertodeath
  - [**SSAMBAtea style locon**](https://huggingface.co/AshtakaOOf/ssambatea-locon/blob/main/ssambateaLoconStyleV2.safetensors) by AshtakaOOf
  - [**Mocha Style**](https://civitai.com/models/102128) by Tonade
  - [**PastelMix LoRA**](https://civitai.com/models/5414?modelVersionId=7397) by andite
  - [**Little Gray Style**](https://civitai.com/models/102685) by Cinsdia
  - [**Dense Light**](https://civitai.com/models/77957) by L_A_X
  - [**more Detail**](https://civitai.com/models/82098) by Lykon
  - [**Youko**](https://civitai.com/models/36140) by ayyyy22002