updates preview images
Browse files- README.md +1 -1
- arona/chara-arona-v1.png +2 -2
- chise/chara-chise-v2.png +2 -2
- fubuki/chara-fubuki-v1b.png +2 -2
- haruka/chara-haruka-v1b.png +2 -2
- hibiki/chara-hibiki-v3.png +2 -2
- junko/chara-junko-v1c.png +2 -2
- kazusa/chara-kazusa-v1c.png +2 -2
- kazusa/tagging methodology.md +1 -1
- koharu/chara-koharu-v3.png +2 -2
- kokona/chara-kokona.png +2 -2
- mari/chara-mari-v5b.png +2 -2
- momoka/chara-momoka-v1c.png +2 -2
- portrait controlnet input.png +3 -0
- portrait pose.png → portrait controlnet output 1.png +2 -2
- portrait controlnet output 2.png +3 -0
- reisa/chara-reisa-v3.png +2 -2
- seia/chara-seia-v1b.png +2 -2
- shizuko/chara-shizuko.png +2 -2
- sora/chara-sora-v3.png +2 -2
README.md
CHANGED
@@ -6,7 +6,7 @@ license: mit
|
|
6 |
|
7 |
Here you will find the various LoRAs I've trained, typically of Blue Archive characters.
|
8 |
|
9 |
-
Preview images are all generated with the same seed, model, and basic prompt template, to demonstrate the inherent style of the LoRA. ControlNet was used for
|
10 |
|
11 |
## Blue Archive
|
12 |
ブルーアーカイブ / 블루 아카이브 / 碧蓝档案
|
|
|
6 |
|
7 |
Here you will find the various LoRAs I've trained, typically of Blue Archive characters.
|
8 |
|
9 |
+
Preview images are all generated with the same seed, model, and basic prompt template, to demonstrate the inherent style of the LoRA. ControlNet was used for preview images, with this [OpenPose input](portrait%20controlnet%20output%201.png) (generated from [this base image](portrait%20controlnet%20input.png)).
|
10 |
|
11 |
## Blue Archive
|
12 |
ブルーアーカイブ / 블루 아카이브 / 碧蓝档案
|
arona/chara-arona-v1.png
CHANGED
Git LFS Details
|
Git LFS Details
|
chise/chara-chise-v2.png
CHANGED
Git LFS Details
|
Git LFS Details
|
fubuki/chara-fubuki-v1b.png
CHANGED
Git LFS Details
|
Git LFS Details
|
haruka/chara-haruka-v1b.png
CHANGED
Git LFS Details
|
Git LFS Details
|
hibiki/chara-hibiki-v3.png
CHANGED
Git LFS Details
|
Git LFS Details
|
junko/chara-junko-v1c.png
CHANGED
Git LFS Details
|
Git LFS Details
|
kazusa/chara-kazusa-v1c.png
CHANGED
Git LFS Details
|
Git LFS Details
|
kazusa/tagging methodology.md
CHANGED
@@ -3,7 +3,7 @@
|
|
3 |
## README / Intro
|
4 |
Since I've seen a few people share this already I'll provide this disclaimer.
|
5 |
|
6 |
-
This is not really intended to be a guide, it's just
|
7 |
|
8 |
I don't claim that any or all of these optimal, nor can I confidently put them forth as recommendations. They're literally just a record of the steps I follow while tagging, gradually developed after ~16 characters using some version of the below process.
|
9 |
|
|
|
3 |
## README / Intro
|
4 |
Since I've seen a few people share this already I'll provide this disclaimer.
|
5 |
|
6 |
+
This is not really intended to be a guide, it's just a log/checklist of my process, for my own benefit, since I repeat this for a lot of LoRAs and I got tired of winging it every single time. I've put only the slightest amount of effort into making it accessible to others.
|
7 |
|
8 |
I don't claim that any or all of these optimal, nor can I confidently put them forth as recommendations. They're literally just a record of the steps I follow while tagging, gradually developed after ~16 characters using some version of the below process.
|
9 |
|
koharu/chara-koharu-v3.png
CHANGED
Git LFS Details
|
Git LFS Details
|
kokona/chara-kokona.png
CHANGED
Git LFS Details
|
Git LFS Details
|
mari/chara-mari-v5b.png
CHANGED
Git LFS Details
|
Git LFS Details
|
momoka/chara-momoka-v1c.png
CHANGED
Git LFS Details
|
Git LFS Details
|
portrait controlnet input.png
ADDED
Git LFS Details
|
portrait pose.png → portrait controlnet output 1.png
RENAMED
File without changes
|
portrait controlnet output 2.png
ADDED
Git LFS Details
|
reisa/chara-reisa-v3.png
CHANGED
Git LFS Details
|
Git LFS Details
|
seia/chara-seia-v1b.png
CHANGED
Git LFS Details
|
Git LFS Details
|
shizuko/chara-shizuko.png
CHANGED
Git LFS Details
|
Git LFS Details
|
sora/chara-sora-v3.png
CHANGED
Git LFS Details
|
Git LFS Details
|