Pixel-Dust
commited on
Commit
•
9e0d279
1
Parent(s):
1ca4150
Update README.md
Browse files
README.md
CHANGED
@@ -11,6 +11,9 @@ tags:
|
|
11 |
**Version Number:** 0.1
|
12 |
|
13 |
## Summary
|
|
|
|
|
|
|
14 |
CC0_rebuild_attempt is a text-to-image model based on the Stable Diffusion 1.5 architecture. It is trained exclusively on CC0 images and other permissive content, aiming to produce high-quality artistic images from given text prompts. The goal is to create a robust and versatile model while ensuring the dataset used is entirely within the public domain, allowing for unrestricted use.
|
15 |
|
16 |
### Training Overview
|
@@ -31,13 +34,15 @@ The model is trained on images and content from the following sources:
|
|
31 |
- **Authors:** CC0
|
32 |
- **Contributors:** CC0
|
33 |
|
|
|
|
|
34 |
These datasets may not cover all possible themes or subjects comprehensively. The dataset may lack representation of certain modern or niche topics due to the limited availability of such content under these licenses. Additionally, the model was trained and developed with a focus on compliance with the Brazilian Copyright Act, which imposes stricter regulations compared to other jurisdictions due to the absence of fair use provisions.
|
35 |
|
36 |
## Associated Risks
|
37 |
* The model might struggle with generating highly detailed text within images.
|
38 |
* There may be limitations in creating complex scenes that require deep compositional understanding.
|
39 |
* The quality and diversity of generated images are dependent on the availability and variety of CC0 and permissive content.
|
40 |
-
* Potential bias towards subjects and styles that are more commonly found in CC0 and permissive content datasets.
|
41 |
|
42 |
## Intended Uses
|
43 |
* Generative art and design projects
|
|
|
11 |
**Version Number:** 0.1
|
12 |
|
13 |
## Summary
|
14 |
+
|
15 |
+
|
16 |
+
|
17 |
CC0_rebuild_attempt is a text-to-image model based on the Stable Diffusion 1.5 architecture. It is trained exclusively on CC0 images and other permissive content, aiming to produce high-quality artistic images from given text prompts. The goal is to create a robust and versatile model while ensuring the dataset used is entirely within the public domain, allowing for unrestricted use.
|
18 |
|
19 |
### Training Overview
|
|
|
34 |
- **Authors:** CC0
|
35 |
- **Contributors:** CC0
|
36 |
|
37 |
+
![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/619bb3c9b392787f0f3ead14/OP3ps7Lad71u9fOAEUyAk.jpeg)
|
38 |
+
|
39 |
These datasets may not cover all possible themes or subjects comprehensively. The dataset may lack representation of certain modern or niche topics due to the limited availability of such content under these licenses. Additionally, the model was trained and developed with a focus on compliance with the Brazilian Copyright Act, which imposes stricter regulations compared to other jurisdictions due to the absence of fair use provisions.
|
40 |
|
41 |
## Associated Risks
|
42 |
* The model might struggle with generating highly detailed text within images.
|
43 |
* There may be limitations in creating complex scenes that require deep compositional understanding.
|
44 |
* The quality and diversity of generated images are dependent on the availability and variety of CC0 and permissive content.
|
45 |
+
* Potential bias towards subjects and styles that are more commonly found in CC0 and permissive content datasets and the manual capition.
|
46 |
|
47 |
## Intended Uses
|
48 |
* Generative art and design projects
|