Update README.md
Browse files
README.md
CHANGED
@@ -10,7 +10,7 @@ tags:
|
|
10 |
---
|
11 |
#fantasy-card-diffusion
|
12 |
|
13 |
-
### A comprehensive Stable Diffusion model for generating fantasy trading card style art, trained on all currently available Magic: the Gathering card art (~35k unique pieces of art) to 140,000 steps, using Stable Diffusion v1.5 as a base model. Has a strong understanding of MTG Artists, planes, sets, colors, card types, creature types and much more.
|
14 |
|
15 |
<b>Prompts:</b> For best results, prompt the model with card information, <i><b>like you were writing out a custom MtG card</b></i>, with the phrase "MTG card art" and an art description
|
16 |
|
@@ -211,10 +211,8 @@ The script is simple, and could probably be improved and cleaned up. Prior to th
|
|
211 |
Cropping was done with ImageMagick (see below, under issues).
|
212 |
|
213 |
## Issues
|
214 |
-
This was intended to be a second test run on the full data set (the first did not go well), so some corners were cut for the purpose of starting my "testing." The model turned out far better than I had expected, so I've decided to release it as is, and hope other people enjoy it as much as I have. But there are some issues that I am aware of and intend to work on fixing for future releases
|
215 |
-
|
216 |
-
-
|
217 |
-
|
218 |
-
|
219 |
-
-- Some artists use special characters in their name. I tried to take away all accents, but I missed at least one, Tom Wänerstrand, who is trained as Tom Wänerstrand, with the umlaut
|
220 |
-
-- Greg Rutkowski: Not an issue, but the poster boy for AI art, Greg Rutkowski, is an MTG artist. He uses the Polish form of his name on MTG cards, Grzegorz Rutkowski, and that is what this model was trained with. So you'll get different results using "by Greg Rutkowski" vs "by Grzegorz Rutkowski"
|
|
|
10 |
---
|
11 |
#fantasy-card-diffusion
|
12 |
|
13 |
+
### A comprehensive fine-tuned Stable Diffusion model for generating fantasy trading card style art, trained on all currently available Magic: the Gathering card art (~35k unique pieces of art) to 140,000 steps, using Stable Diffusion v1.5 as a base model. Trained on thousands of concepts, using tags from card data. Has a strong understanding of MTG Artists, planes, sets, colors, card types, creature types and much more.
|
14 |
|
15 |
<b>Prompts:</b> For best results, prompt the model with card information, <i><b>like you were writing out a custom MtG card</b></i>, with the phrase "MTG card art" and an art description
|
16 |
|
|
|
211 |
Cropping was done with ImageMagick (see below, under issues).
|
212 |
|
213 |
## Issues
|
214 |
+
- This was intended to be a second test run on the full data set (the first did not go well), so some corners were cut for the purpose of starting my "testing." The model turned out far better than I had expected, so I've decided to release it as is, and hope other people enjoy it as much as I have. But there are some issues that I am aware of and intend to work on fixing for future releases
|
215 |
+
- Cropping: MTG art is rectangular. I initially tried to use a trainer that could handle different aspect ratios, but after a couple failed tries, I just did a quick mass cropping job with ImageMagick, resizing and cropping everything to 512x512, so I could get training running. I forget what exactly I did, but it appears it focused on the left side of the card, universally cutting off the right side. You'll see this in lots of images, that tend to have everything on the right as a result
|
216 |
+
- Plane information was only added around step 70,000, so it may be less trained than other information - basically, I wanted a way to group sets together by plane, as I was finding how well it knew the look of a set depended on whether WotC had incorporated the name of the plane into the set itself - ie: using "Theros" would only get you "Theros" and "Theros: Beyond Death" and not "Born of the Gods" or "Journey into Nyx"
|
217 |
+
- Some artists use special characters in their name. I tried to take away all accents, but I missed at least one, Tom Wänerstrand, who is trained as Tom Wänerstrand, with the umlaut
|
218 |
+
- Greg Rutkowski: Not an issue, but the poster boy for AI art, Greg Rutkowski, is an MTG artist. He uses the Polish form of his name on MTG cards, Grzegorz Rutkowski, and that is what this model was trained with. So you'll get different results using "by Greg Rutkowski" vs "by Grzegorz Rutkowski"
|
|
|
|