volrath50 commited on
Commit
bc5f222
1 Parent(s): fef304e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -8
README.md CHANGED
@@ -184,9 +184,9 @@ Training was done on a dataset consisting of cropped, 512x512 versions of the ar
184
 
185
  The result is a comprehensive model that has a good understanding of MTG artists, sets, planes, card types, creature types, years, colors, and more. If you had ever wondered what a Merfolk, drawn by Ron Spencer, would have looked like on Tarkir, as part of the Mardu clan, with dash, haste, and trample - this model can deliver what you want.
186
 
187
- Because the training data is literally the art from every MTG card, combined with the information for the associated card (about ~35,000 unique pieces of art and text), I won't be releasing the training data, out of concerns that would be violating WotC's IP. I have, however, included the python script that I used to generate the training data set, which should get you uncropped images and identical text (or near identical) text files, with used with the "unique artwork" json from https://scryfall.com/docs/api/bulk-data
188
 
189
- The script is simple, and could probably be improved. I hadn't done any coding for 20 years, since I was a teenager, and had never used Python prior to hacking this together with vague memories of Perl in 2000-2001, liberal use of Github co-pilot and lots of googling.
190
 
191
  Cropping was done with ImageMagick (see below, under issues).
192
 
@@ -195,12 +195,6 @@ This was intended to be a second test run on the full data set (the first did no
195
 
196
  - Cropping
197
  -- 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
198
- - Planes
199
  -- 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"
200
- - Unique Characters
201
- -- How well it knows a unique character largely depends on how many cards they show up on, and how well the AI was able to isolate the character in question
202
- -- Most Planeswalkers are fairly well known, even some that have very few cards. (It knows who Aminatou is, despite her having a single card, and even managed to separate her from Seb McKinnon's awesome artwork)
203
- -- Some other unique characters, it only has a general sense of what they look like - Emrakul, for instance, comes out more as purple version of the flying spaghetti monster, and some creature types - (like slivers), it still hasn't quite figured them out
204
- - Random issues
205
  -- 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
206
  -- 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"
 
184
 
185
  The result is a comprehensive model that has a good understanding of MTG artists, sets, planes, card types, creature types, years, colors, and more. If you had ever wondered what a Merfolk, drawn by Ron Spencer, would have looked like on Tarkir, as part of the Mardu clan, with dash, haste, and trample - this model can deliver what you want.
186
 
187
+ I have uploaded the python script that I used to generate the training data set, which should get you uncropped images and identical text (or near identical) text files, with used with the "unique artwork" json from https://scryfall.com/docs/api/bulk-data
188
 
189
+ The script is simple, and could probably be improved and cleaned up. Prior to this project, I hadn't done any coding in 20 years, when I was a teenager, and had never used Python prior to hacking this together with vague memories of Perl in 2000-2001, liberal use of Github co-pilot and lots of googling.
190
 
191
  Cropping was done with ImageMagick (see below, under issues).
192
 
 
195
 
196
  - Cropping
197
  -- 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
 
198
  -- 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"
 
 
 
 
 
199
  -- 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
200
  -- 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"