project links added
Browse files
README.md
CHANGED
|
@@ -15,7 +15,12 @@ tags:
|
|
| 15 |
|
| 16 |
This ECLIPSE model weight is a tiny (33M parameter) non-diffusion text-to-image prior model trained on 5M LAION-HighRes subset data.
|
| 17 |
|
| 18 |
-
Despite being so small and trained on limited amount of data, ECLIPSE priors
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
|
| 20 |
## Installation
|
| 21 |
```bash
|
|
|
|
| 15 |
|
| 16 |
This ECLIPSE model weight is a tiny (33M parameter) non-diffusion text-to-image prior model trained on 5M LAION-HighRes subset data.
|
| 17 |
|
| 18 |
+
Despite being so small and trained on a limited amount of data, ECLIPSE priors achieve results that of 1 Billion parameter T2I prior models trained on millions of image-text pairs.
|
| 19 |
+
|
| 20 |
+
Project Page: [https://eclipse-t2i.vercel.app](https://eclipse-t2i.vercel.app)
|
| 21 |
+
|
| 22 |
+
GitHub: [https://github.com/eclipse-t2i/eclipse-inference](https://github.com/eclipse-t2i/eclipse-inference)
|
| 23 |
+
|
| 24 |
|
| 25 |
## Installation
|
| 26 |
```bash
|