---
license: creativeml-openrail-m
thumbnail: >-
    ./images/thumbnail.webp
tags:
    - stable-diffusion
    - text-to-image
    - safetensors
    - diffusers
inference: true
language:
    - en
widget:
    - text: >-
          1girl, solo, bangs, (pink hair, gradient hair, very long hair:1.1), (purple eyes:1.05), (cat ears, animal ear fluff:1.2), sidelocks, white shirt, collared shirt, buttons, 
          night, looking at viewer, table, pizza on table, pov, restaurant, medium breasts, smiling, (blush:0.7), colored inner hair, (symmetric), (masterpiece, exceptional, extremely detailed:1.1)
      example_title: example
library_name: diffusers
---

<center>
<img src="Andromeda/resolve/main/images/AndromedaCover.png" width="80%"/>
<h1 style="font-size:1.6rem;">
  <b>AndromedaDX (and friends)</b>
</h1>
<h2>Stable Diffusion models for (neko enthusiast) weebs</h2>
</center>

<div style="display: flex; flex-direction: row; width: 100%">
  <div style="margin: 0; padding: 0; width:25%;">
    <figure style="margin: 2px;">
      <img src="Andromeda/resolve/main/images/AndromedaDX-v1-CS2-01367-3105139270.png" />
      <figcaption style="text-align: center; font-size: 1.2rem;"><a href="Andromeda/resolve/main/AndromedaDX-v1.safetensors">Andromeda<b>DX</b></a></figcaption>
    </figure>
  </div>
  <div style="margin: 0; padding: 0; width:25%;">
    <figure style="margin: 2px;">
      <img src="Andromeda/resolve/main/images/AndromedaSX-v1-CS2-01365-3105139270.png" />
      <figcaption style="text-align: center; font-size: 1.2rem;"><a href="Andromeda/resolve/main/AndromedaSX-v1.safetensors">Andromeda<b>SX</b></a></figcaption>
    </figure>
  </div>
  <div style="margin: 0; padding: 0; width:25%;">
    <figure style="margin: 2px;">
      <img src="Andromeda/resolve/main/images/AndromedaSV-v1-CS2-01366-3105139270.png" />
      <figcaption style="text-align: center; font-size: 1.2rem;"><a href="Andromeda/resolve/main/AndromedaSV-v1.safetensors">Andromeda<b>SV</b></a></figcaption>
    </figure>
  </div>
  <div style="margin: 0; padding: 0; width:25%;">
    <figure style="margin: 2px;">
      <img src="Andromeda/resolve/main/images/AndromedaUnreal-v1-CS2-01368-3105139270.png" />
      <figcaption style="text-align: center; font-size: 1.2rem;"><a href="Andromeda/resolve/main/AndromedaUnreal-v1.safetensors">Andromeda<b>Unreal</b></a></figcaption>
    </figure>
  </div>
</div>

## Model Variants

<p>I'm not sure there's actually enough difference between these four to merit posting all of them, but nevertheless, here they are.</p>

<h3><a href="Andromeda/resolve/main/AndromedaDX-v1.safetensors">Andromeda<b>DX</b></a></h3>
<p>
  This is probably the one you want. Out of all of these it's the one I'm happiest with; it produces high-detail backgrounds (and IMO can achieve a fairly high overall level of detail). Bonus special feature (_definitely_ not a bug, shhh): it likes to add cats to things. Just regular cats. Sometimes several cats!
</p>

<h3><a href="Andromeda/resolve/main/AndromedaSX-v1.safetensors">Andromeda<b>SX</b></a> and <a href="Andromeda/resolve/main/AndromedaSV-v1.safetensors">Andromeda<b>SV</b></a></h3>
<p>
  These are more suited to foxgirls than catgirls. If you're a Fubuki or Kawakaze enthusiast, these are for you :)
</p>

<h3><a href="Andromeda/resolve/main/AndromedaUnreal-v1.safetensors">Andromeda<b>Unreal</b></a></h3>
<p>
  This one has a (slightly) more realistic style thanks to the addition of some MeinaUnreal (not currently posted on HF).
</p>

## Notes/info

I made DX for a chatbot of mine who can "take selfies" via SD, and it behaves nicely enough that I felt like it was worth sharing.
It's especially good with natural language prompts at high CLIP skip, e.g.:

<div style="display: flex; flex-direction: row; width: 100%">
  <div style="margin: 0; padding: 0; width: 50%;">
    <figure style="margin: 2px;">
      <img src="Andromeda/resolve/main/images/DX/AndromedaDX-v1-CS5-01285-3762015382.png"/>
      <figcaption style="text-align: center; font-size: 1.2rem;">CLIP Skip 5</b></figcaption>
    </figure>
  </div>
  <div style="margin: 0; padding: 0; width: 50%;">
    <figure style="margin: 2px;">
      <img src="Andromeda/resolve/main/images/DX/AndromedaDX-v1-CS7-00812-3866181234.png"/>
      <figcaption style="text-align: center; font-size: 1.2rem;">CLIP Skip 7</b></figcaption>
    </figure>
  </div>
</div>

<details>
  <summary><big><b>Prompts</b></big></summary>

OK, I lied, it's just the one prompt for now.

```yaml
1girl, solo, bangs, red hair, (pink hair:1.1), long hair, very long hair, (purple eyes:1.1), (cat ears, animal ear fluff:1.1), , evening, gradient eyes, colored inner hair, medium breasts, (smile:0.6), (masterpiece, best quality, exceptional, extremely detailed:1.1)
Negative prompt: (nsfw:1.05), (EasyNegative:0.7), simple5.5, simple5.6, bad-hands-5, (short hair:1.1), loli, child
Steps: 25, Sampler: Euler a, CFG scale: 8.25, Seed: 3105139270, Size: 864x608, Model hash: 9e0b7d3259, Model: AndromedaSX-v1, Denoising strength: 0.5, Clip skip: 2, ENSD: 31337, Hires upscale: 1.5, Hires steps: 8, Hires upscaler: Latent, Discard penultimate sigma: True
```

</details>

## Recommended settings

Some educated guesses based on what playing around I've done:

-   VAE: [kl-f8-anime2](https://huggingface.co/hakurei/waifu-diffusion-v1-4/blob/main/vae/kl-f8-anime2.ckpt)) is baked in and recommended, blessed2 works as well but is a little softer on the colours.
-   Clip Skip: 2, 5, or 7 - DX and Unreal do quite well in the 5-7 range
-   Sampler: DPM++ 2M Karras, the usual 20-35 steps, or Euler A at 40-50 steps with CLIP skip 5-7
-   CFG Scale: 7.5 ± 1 (much below 6 is a bad move, much above 9 will get... fun)
-   Recommended Positive Prompt:  
    Add `(masterpiece, best quality, exceptional, extremely detailed:1.1)` at the **end** of your prompt. Otherwise, nothing particularly special. YMMV, of course.
-   Recommended Negative Prompt:  
    [EasyNegative](https://huggingface.co/datasets/gsdf/EasyNegative), `(nsfw:1.05), (EasyNegative:0.7), simple5.5, simple5.6, bad-hands-5, (short hair:1.1), loli, child`
-   For better results, using hires fix is a must.
-   Hires upscaler: Latent (any variant, such as nearest-exact), 12-18 steps at 0.5-0.6 denoising (7-10 actual steps)

## Recipe

To be filled in later... I honestly don't remember half of what I did here.

### Credits

A big thankyou to [ShussarSDFA](https://huggingface.co/ShussarSDFA) for their [Sathariel](https://huggingface.co/ShussarSDFA/Sathariel) model series, which are a key component of this