Update README.md
Browse files
README.md
CHANGED
|
@@ -2,13 +2,6 @@
|
|
| 2 |
license: openrail++
|
| 3 |
---
|
| 4 |
|
| 5 |
-
---
|
| 6 |
-
license: openrail++
|
| 7 |
-
tags:
|
| 8 |
-
- stable-diffusion
|
| 9 |
-
- text-to-image
|
| 10 |
-
---
|
| 11 |
-
|
| 12 |
This is a finetuned version of [stabilityai/stable-diffusion-2-base](https://huggingface.co/stabilityai/stable-diffusion-2-base), optimised for outputting English text.
|
| 13 |
|
| 14 |
The model is finetuned for 70 epochs on [pbevan11/GPT4V-captions-from-LVIS-typography](https://huggingface.co/datasets/pbevan11/GPT4V-captions-from-LVIS-typography), a curated dataset of image-caption pairs from LVIS with detailed transcriptions of the text present in the image.
|
|
|
|
| 2 |
license: openrail++
|
| 3 |
---
|
| 4 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
This is a finetuned version of [stabilityai/stable-diffusion-2-base](https://huggingface.co/stabilityai/stable-diffusion-2-base), optimised for outputting English text.
|
| 6 |
|
| 7 |
The model is finetuned for 70 epochs on [pbevan11/GPT4V-captions-from-LVIS-typography](https://huggingface.co/datasets/pbevan11/GPT4V-captions-from-LVIS-typography), a curated dataset of image-caption pairs from LVIS with detailed transcriptions of the text present in the image.
|