Bootloader
commited on
Commit
β’
e6589c0
1
Parent(s):
cfa7334
Update README.md
Browse files
README.md
CHANGED
@@ -2,44 +2,48 @@
|
|
2 |
license: unknown
|
3 |
---
|
4 |
|
5 |
-
|
|
|
|
|
6 |
|
7 |
-
## Model Details
|
8 |
|
9 |
- **Model Name:** Ai2Ai_v1
|
10 |
-
- **Description:**
|
11 |
- **Version:** v1
|
12 |
-
- **Date
|
13 |
-
- **Framework
|
14 |
|
15 |
-
## Intended Use
|
16 |
|
17 |
-
This
|
18 |
|
19 |
-
## Performance
|
20 |
|
21 |
-
- **Accuracy:**
|
22 |
-
- **Precision:**
|
23 |
|
24 |
-
## Limitations and Bias
|
25 |
|
26 |
-
- **Limitations:**
|
27 |
-
- **Bias Considerations:** jpt artifacts, cheek bulge,
|
28 |
-
## Training Data
|
29 |
|
30 |
-
|
31 |
-
- **Data Size:** 82 images, around 12 Mb
|
32 |
|
|
|
|
|
|
|
33 |
|
34 |
-
## Examples
|
35 |
|
36 |
Example 1:
|
37 |
![Example 1](image_url_for_example_1)
|
38 |
|
39 |
-
Caption: [Description of the example]
|
40 |
|
41 |
Example 2:
|
42 |
![Example 2](image_url_for_example_2)
|
43 |
|
44 |
-
Caption: [Description of the example]
|
45 |
|
|
|
|
2 |
license: unknown
|
3 |
---
|
4 |
|
5 |
+
<div align="center">
|
6 |
+
<h1>π Model Card: Ai2Ai_v1 π</h1>
|
7 |
+
</div>
|
8 |
|
9 |
+
## π Model Details
|
10 |
|
11 |
- **Model Name:** Ai2Ai_v1
|
12 |
+
- **Description:** A cutting-edge LoRA trained on AI-generated images sourced from Pinterest.
|
13 |
- **Version:** v1
|
14 |
+
- **Release Date:** [Release date - Insert Date]
|
15 |
+
- **Framework:** Kohya Trainer Colab
|
16 |
|
17 |
+
## π Intended Use
|
18 |
|
19 |
+
This revolutionary LoRA (Limitless Realm AI) is designed for generating stunning anime girls with incredible creativity. It excels in generating detailed facial features and captivating hats. However, it's not optimized for rendering full body and clothing designs.
|
20 |
|
21 |
+
## π Performance
|
22 |
|
23 |
+
- **Accuracy:** High on face and hat generation, lower on body details
|
24 |
+
- **Precision:** High on face and hat generation, lower on body details
|
25 |
|
26 |
+
## β‘ Limitations and Bias
|
27 |
|
28 |
+
- **Limitations:** This LoRA model is relatively small, resulting in the generation of somewhat identical faces.
|
29 |
+
- **Bias Considerations:** Beware of potential artifacts such as "jpt artifacts," "cheek bulge," and the model's potential to be overly powerful in certain aspects.
|
|
|
30 |
|
31 |
+
## π― Training Data
|
|
|
32 |
|
33 |
+
- **Data Sources:** Images from Pinterest
|
34 |
+
- **Data Size:** 82 images, approximately 12 MB
|
35 |
+
- **Data Preprocessing:** AI-generated images carefully curated for training quality
|
36 |
|
37 |
+
## π Examples
|
38 |
|
39 |
Example 1:
|
40 |
![Example 1](image_url_for_example_1)
|
41 |
|
42 |
+
*Caption: [Description of the example]*
|
43 |
|
44 |
Example 2:
|
45 |
![Example 2](image_url_for_example_2)
|
46 |
|
47 |
+
*Caption: [Description of the example]*
|
48 |
|
49 |
+
---
|