Information
Browse files
README.md
CHANGED
@@ -1,3 +1,60 @@
|
|
1 |
-
---
|
2 |
-
license: cc
|
3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc
|
3 |
+
---
|
4 |
+
Brand-new checkpoints series where a model is merged and upgrade with only my resources (own LoRAs and datasets). Targeting a sweet style, colorful, pleasant and cute.
|
5 |
+
|
6 |
+
**Entrance :**
|
7 |
+
|
8 |
+
First paths, the base model is 0.7xMIX_11 + 0.15xMIX_8 + 0.15xMIX_12, 19 homemade LoRAs were added to the model with high strength, values had been tweaked to keep at the end the best output. Kind of a half-trained checkpoint.
|
9 |
+
|
10 |
+
Warning : during testing, I found that 2 of the negative embeddings I used in the past were hardly impacting the style, by getting rid of them, I could have access to a better and more colorful style.
|
11 |
+
|
12 |
+
4 Groups were made to ease the tweaking, see screenshot :
|
13 |
+
|
14 |
+
(It is like merging 19 models that are having one LoRA attached to it with high strength)
|
15 |
+
|
16 |
+
|
17 |
+
**Settings recommended :**
|
18 |
+
|
19 |
+
Sampler : Euler a + Automatic/uniform
|
20 |
+
|
21 |
+
Steps : 27-30
|
22 |
+
|
23 |
+
CFG : 7-8
|
24 |
+
|
25 |
+
Hires Fix : R-ESRGAN 4x+ Anime6B or 4x-UltraSharp + Denoising strength 0.5-0.7 and 20 Steps (upscale x1)
|
26 |
+
|
27 |
+
Upscale : img2img x1.5 - Denoising strength around 0.5 (lower if good input, higher if more corrections needed)
|
28 |
+
|
29 |
+
Edit : Controlnet, openpose, depth (midas), Krita AI diffusion -> use Alternative - Euler A Preset, live mode to add or remove things (select area with selection tools)
|
30 |
+
|
31 |
+
Enhance : after img2img and other editing, -> Extras tab, upscale x2 with R-ESRGAN 4x+ Anime6B or 4x-UltraSharp ;
|
32 |
+
|
33 |
+
R-ESRGAN 4x+ Anime6B -> Better colors and anime looking
|
34 |
+
|
35 |
+
4x-UltraSharp -> More realistic, more details
|
36 |
+
|
37 |
+
Other Working Samplers :
|
38 |
+
|
39 |
+
DPM++ 2M, DDIM, Restart, UniPC -> bad with Hires Fix
|
40 |
+
|
41 |
+
DPM++ 3M SDE (expo/polyexpo) / DPM++ 2S a / DPM++ 2M SDE -> compatible Hires Fix
|
42 |
+
|
43 |
+
|
44 |
+
**Comparison with CSA series :**
|
45 |
+
|
46 |
+
Style : **+**
|
47 |
+
|
48 |
+
Stability : **-** (removal of negative embeddings and high strength LoRAs)
|
49 |
+
|
50 |
+
Creativity : **+=** (do more easily heterochromia, gradient hair and monster girls)
|
51 |
+
|
52 |
+
Prompt listening : **+=** (trained with booru tags, better identification of some concepts like thin legs, shiny skin...)
|
53 |
+
|
54 |
+
Render time : **=**
|
55 |
+
|
56 |
+
Aging : **Younger** (could add chibi in negative prompt to avoid big heads)
|
57 |
+
|
58 |
+
Hope you will have fun with this heavenly checkpoint !
|
59 |
+
|
60 |
+
Last but not least, since there is a strong influence of WingedCloud and Blue-senpai artists, the model is kinda naughty so don't hesitate to put nsfw in negative prompt ;).
|