Add readme
Browse files
README.md
CHANGED
|
@@ -1,3 +1,30 @@
|
|
| 1 |
---
|
| 2 |
license: openrail++
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: openrail++
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
tags:
|
| 6 |
+
- anime
|
| 7 |
+
- image generation
|
| 8 |
+
- PonyXL
|
| 9 |
+
- Stable Diffusion
|
| 10 |
+
- SDXL
|
| 11 |
---
|
| 12 |
+
|
| 13 |
+
## MikuFactorXL
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
## About
|
| 18 |
+
|
| 19 |
+
This is my first PonyXL merge, it is just based off random models I picked off CivitAI. The results are amazing to me at least, best PonyXL model avaible I think personally! However I am very biased. I tried to select models for following
|
| 20 |
+
|
| 21 |
+
## Model selection criteria
|
| 22 |
+
- Good small details
|
| 23 |
+
- Ones that look least like AI slop, more solv
|
| 24 |
+
- Ones with least artifacts in example images
|
| 25 |
+
- Ones that I find personally appealing
|
| 26 |
+
- Bright colors
|
| 27 |
+
|
| 28 |
+
## Model merge techique
|
| 29 |
+
|
| 30 |
+
Idk I just merged bunch of models in ComfyUI, they are all listed in `mega-merge.json` to look at good luck finding them all on CivitAI. My PC almost crapped itself and had to make 200GB swap file, so like would be nice
|