text_to_img
#30
by
dattatreya11
- opened
README.md
CHANGED
|
@@ -20,6 +20,7 @@ We provide both full UNet and LoRA checkpoints. The full UNet models have the be
|
|
| 20 |
## Demos
|
| 21 |
|
| 22 |
* Generate with all configurations, best quality: [Demo](https://huggingface.co/spaces/ByteDance/SDXL-Lightning)
|
|
|
|
| 23 |
|
| 24 |
## Checkpoints
|
| 25 |
|
|
@@ -129,7 +130,7 @@ Use LoRA only if you are using non-SDXL base models. Otherwise use our full chec
|
|
| 129 |
|
| 130 |
|
| 131 |
|
| 132 |
-
### 1-Step
|
| 133 |
|
| 134 |
The 1-step model is only experimental and the quality is much less stable. Consider using the 2-step model for much better quality.
|
| 135 |
|
|
|
|
| 20 |
## Demos
|
| 21 |
|
| 22 |
* Generate with all configurations, best quality: [Demo](https://huggingface.co/spaces/ByteDance/SDXL-Lightning)
|
| 23 |
+
* Real-time generation as you type, lightning-fast: [Demo from fastsdxl.ai](https://fastsdxl.ai/)
|
| 24 |
|
| 25 |
## Checkpoints
|
| 26 |
|
|
|
|
| 130 |
|
| 131 |
|
| 132 |
|
| 133 |
+
### 1-Step UNet
|
| 134 |
|
| 135 |
The 1-step model is only experimental and the quality is much less stable. Consider using the 2-step model for much better quality.
|
| 136 |
|