Commit
·
2b69367
1
Parent(s):
fa9cfad
Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
<h1>CharTurner</h1>
|
| 2 |
+
Hey there! I'm a working artist, and I loathe doing character turnarounds, I find it the least fun part of character design. I've been working on an embedding that helps with this process, and, though it's not where I want it to be, I was encouraged to release it under the Minimum Viable Product principle.
|
| 3 |
+
|
| 4 |
+
I'm also working on a few more character embeddings, including a head turn around and an expression sheet. They're still way too raw to release tho.
|
| 5 |
+
|
| 6 |
+
Is there some type of embedding that would be useful for you? Let me know, i'm having fun making tools to fix all the stuff I hate doing by hand.
|
| 7 |
+
|
| 8 |
+
|
| 9 |
+
<h2>v1 is still a little bit... fiddly.</h2>
|
| 10 |
+
|
| 11 |
+
**Sampler: I use DPM++ 2m Karras or DDIM most often.
|
| 12 |
+
|
| 13 |
+
**Highres. fix ON for best results
|
| 14 |
+
|
| 15 |
+
**landscape orientation will get you more 'turns'; square images tend toward just front and back.
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
I like https://civitai.com/models/2540/elldreths-stolendreams-mix to make characters in.
|
| 19 |
+
|
| 20 |
+
I use an embedding trained on my own art (smoose) that I will release if people want it? But it's an aesthetic thing, just my own vibe.
|
| 21 |
+
|
| 22 |
+
I didn't really test this in any of the waifu/NAI type models, as I don't usually use them. Looks like it works but it probably has its own special dance.
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
<h1>Things I'm working on for v2:</h1>
|
| 26 |
+
|
| 27 |
+
It fights you on style sometimes. I'm adding more various types of art styles to the dataset to combat this.
|
| 28 |
+
|
| 29 |
+
Open front coats and such tend to be open 'back' on the back view. Adding more types of clothing to the dataset to combat this.
|
| 30 |
+
|
| 31 |
+
Tends toward white and 'fit' characters, which isn't useful. Adding more diversity in body and skin tone to the dataset to combat this.
|
| 32 |
+
|
| 33 |
+
Helps create multiple full body views of a character. The intention is to get at least a front and back, and ideally, a front, 3/4, profile, 1/4 and back versions, in the same outfit.
|