<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/AndromedaMV-v1-CS2-01368-3105139270.png" /> <figcaption style="text-align: center; font-size: 1.2rem;"><a href="Andromeda/resolve/main/AndromedaMV-v1.safetensors">Andromeda<b>MV</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/AndromedaMV-v1.safetensors">Andromeda<b>MV</b></a></h3> <p> This one has a much more realistic style thanks to the addition of some models made by a 2ho discord poster who (AFAIK) hasn't made them public yet. </p>
C-tier Variants
<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). It's honestly not super great and it's barely different to DX. </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.
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) 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,(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 for their Sathariel model series, which are a key component of this
