Update readme
Browse files
README.md
CHANGED
|
@@ -12,12 +12,12 @@ library_name: diffusers
|
|
| 12 |
|
| 13 |
SDXL-Lightning is a lightning-fast text-to-image generation model. It can generate high-quality 1024px images in a few steps. For more information, please refer to our research paper: [SDXL-Lightning: Progressive Adversarial Diffusion Distillation](https://arxiv.org/abs/2402.13929). We open-source the model as part of the research.
|
| 14 |
|
|
|
|
|
|
|
| 15 |
Our models are distilled from [stabilityai/stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0). This repository contains checkpoints for 1-step, 2-step, 4-step, and 8-step distilled models. The generation quality of our 2-step, 4-step, and 8-step model is amazing. Our 1-step model is more experimental.
|
| 16 |
|
| 17 |
We provide both full UNet and LoRA checkpoints. The full UNet models have the best quality while the LoRA models can be applied to other base models.
|
| 18 |
|
| 19 |
-
[Demo](https://huggingface.co/spaces/AP123/SDXL-Lightning) (made by the community)
|
| 20 |
-
|
| 21 |
## Diffusers Usage
|
| 22 |
|
| 23 |
Please always use the correct checkpoint for the corresponding inference steps.
|
|
|
|
| 12 |
|
| 13 |
SDXL-Lightning is a lightning-fast text-to-image generation model. It can generate high-quality 1024px images in a few steps. For more information, please refer to our research paper: [SDXL-Lightning: Progressive Adversarial Diffusion Distillation](https://arxiv.org/abs/2402.13929). We open-source the model as part of the research.
|
| 14 |
|
| 15 |
+
Try it out with our [demo](https://huggingface.co/spaces/ByteDance/SDXL-Lightning)!
|
| 16 |
+
|
| 17 |
Our models are distilled from [stabilityai/stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0). This repository contains checkpoints for 1-step, 2-step, 4-step, and 8-step distilled models. The generation quality of our 2-step, 4-step, and 8-step model is amazing. Our 1-step model is more experimental.
|
| 18 |
|
| 19 |
We provide both full UNet and LoRA checkpoints. The full UNet models have the best quality while the LoRA models can be applied to other base models.
|
| 20 |
|
|
|
|
|
|
|
| 21 |
## Diffusers Usage
|
| 22 |
|
| 23 |
Please always use the correct checkpoint for the corresponding inference steps.
|