Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
inference: true
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
tags:
|
| 6 |
+
- stable-diffusion
|
| 7 |
+
- text-to-image
|
| 8 |
+
license: other
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
dnditem
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
Image here:
|
| 15 |
+
|
| 16 |
+
This is a model (dnditem) for creating magic items, for the game Dungeons and Dragons! It was trained to be very similar to the official results that are available here: https://www.dndbeyond.com/magic-items
|
| 17 |
+
|
| 18 |
+
The model was trained in a pretty specific way though, and requires a specific way of prompting to get good results.
|
| 19 |
+
|
| 20 |
+
##Prompting
|
| 21 |
+
---
|
| 22 |
+
The keywork is "dnditem", and the prompts should be done in the following way:
|
| 23 |
+
|
| 24 |
+
"dnditem, [item type], [item style], [background]"
|
| 25 |
+
|
| 26 |
+
So, for example, a prompt could look like:
|
| 27 |
+
|
| 28 |
+
"dnditem, a pair of boots, spellguard style, light red circle background with white outerbackground".
|
| 29 |
+
or
|
| 30 |
+
"dnditem, a shield, shooting star style, light blue stripe background with white outerbackground".
|
| 31 |
+
|
| 32 |
+
##item type
|
| 33 |
+
---
|
| 34 |
+
Currently the model supports and was trained on the following types:
|
| 35 |
+
|
| 36 |
+
"a pair of boots", "a cloak", "a pair of gloves", "a helmet", "a necklace", "a ring", "a robe", "a rod", "a shield", "a staff", "a sword", "a wand"
|
| 37 |
+
|
| 38 |
+
|
| 39 |
+
|
| 40 |
+
---
|
| 41 |
+
|
| 42 |
+
|