Update README.md
Browse files




README.md
CHANGED
@@ -1,3 +1,37 @@
|
|
1 |
---
|
|
|
|
|
2 |
license: creativeml-openrail-m
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
license: creativeml-openrail-m
|
5 |
+
tags:
|
6 |
+
- Marvel
|
7 |
+
- stable-diffusion
|
8 |
+
- text-to-image
|
9 |
+
- diffusers
|
10 |
+
inference: true
|
11 |
---
|
12 |
+
|
13 |
+
### Marvel What_If Diffusion
|
14 |
+
This model is trained on images from the animated Marvel Disney+ show What If.
|
15 |
+
Which includes characters, background, and some objects.
|
16 |
+
|
17 |
+
To reference the art style, use the token: whatif style
|
18 |
+
|
19 |
+
Here are some samples.
|
20 |
+
|
21 |
+
**Portraits**
|
22 |
+

|
23 |
+

|
24 |
+

|
25 |
+
|
26 |
+
Prompt used:
|
27 |
+
Portrait of *name* in whatif style
|
28 |
+
Guidance: 7
|
29 |
+
Steps: 50 using DDIM
|
30 |
+
|
31 |
+
I'm not a prompt wizard so you can definitely get better results with some tuning.
|
32 |
+
|
33 |
+
**Landscapes**
|
34 |
+

|
35 |
+
|
36 |
+
**Objects**
|
37 |
+

|