Update README.md
Browse files
README.md
CHANGED
|
@@ -1,5 +1,7 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
|
|
|
| 3 |
---
|
| 4 |
|
| 5 |
# Introduction
|
|
@@ -7,6 +9,9 @@ license: apache-2.0
|
|
| 7 |
This is the example model of [Distill SDXL](https://github.com/okotaku/diffengine/tree/main/configs/distill_sd).
|
| 8 |
The training is based on [DiffEngine](https://github.com/okotaku/diffengine), the open-source toolbox for training state-of-the-art Diffusion Models with diffusers and mmengine.
|
| 9 |
|
|
|
|
|
|
|
|
|
|
| 10 |
# Training
|
| 11 |
|
| 12 |
```
|
|
@@ -53,4 +58,4 @@ image.save('demo.png')
|
|
| 53 |
|
| 54 |
prompt = 'a picture of a pink and yellow pokemon with a sword'
|
| 55 |
|
| 56 |
-
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
datasets:
|
| 4 |
+
- lambdalabs/pokemon-blip-captions
|
| 5 |
---
|
| 6 |
|
| 7 |
# Introduction
|
|
|
|
| 9 |
This is the example model of [Distill SDXL](https://github.com/okotaku/diffengine/tree/main/configs/distill_sd).
|
| 10 |
The training is based on [DiffEngine](https://github.com/okotaku/diffengine), the open-source toolbox for training state-of-the-art Diffusion Models with diffusers and mmengine.
|
| 11 |
|
| 12 |
+
Paper: [On Architectural Compression of Text-to-Image Diffusion Models](https://arxiv.org/abs/2305.15798)
|
| 13 |
+
Unofficial implementation: https://github.com/segmind/distill-sd
|
| 14 |
+
|
| 15 |
# Training
|
| 16 |
|
| 17 |
```
|
|
|
|
| 58 |
|
| 59 |
prompt = 'a picture of a pink and yellow pokemon with a sword'
|
| 60 |
|
| 61 |
+
|