README.md

---
license: cc-by-nc-4.0
language:
- en
---
MergeStove2.5D

A merge stable diffusion model, which improves anatomy of anime characters, especially with eyes and hands, without losing anime objects.

No commercial usage!

![12848-2569952539-miku, ruby eyes, face to viewer, solo, medium breasts, soft light, outdoors, garden, seaside, beauty.png](https://s3.amazonaws.com/moonup/production/uploads/1674739809930-6384c33038f4aec99c4a7483.png)


Bias

Sometimes long necks appear. Still hazy a bit. Under some theme will produce wrong skin gloss. Sometimes overfitting.


Formula

Round1 animefull-latest(NovelAI)+64in1(Private, from a Chinese AI community NovelAI 中文频道) sum rate0.4

Round2 ()+AbyssOrangemix2_nsfw(WarriorMama777) sum rate0.2

After baked in vae-ft-mse-840000-ema-pruned(StabilityAI) VAE, pruned ema, compressed to FP16, get MergeStove2.5D_mk1.

Round3 MergeStove2.5D_mk1+Anmokomergetest1(Private, from a Chinese AI community NovelAI 中文频道) sum rate0.4

After baked in vae-ft-mse-840000-ema-pruned(StabilityAI) VAE, pruned ema, compressed to FP16, get MergeStove2.5D_mk2.