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 |
![SDXL-Lightning ComfyUI LoRA Workflow](comfyui/sdxl_lightning_workflow_lora.jpg)
|
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 |
![SDXL-Lightning ComfyUI LoRA Workflow](comfyui/sdxl_lightning_workflow_lora.jpg)
|
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 |
|