Text-to-Image
Diffusers
stable-diffusion
PeterL1n commited on
Commit
0a5991b
1 Parent(s): b468d42

Update readme

Browse files
Files changed (1) hide show
  1. README.md +15 -2
README.md CHANGED
@@ -10,7 +10,7 @@ library_name: diffusers
10
 
11
  ![Intro Image](sdxl_lightning_samples.jpg)
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 paper: [SDXL-Lightning: Progressive Adversarial Diffusion Distillation](https://huggingface.co/ByteDance/SDXL-Lightning/resolve/main/sdxl_lightning_report.pdf). The models are released for research purposes only.
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
 
@@ -125,4 +125,17 @@ The 1-step model is only experimental and the quality is much less stable. Consi
125
  1. Download the full checkpoint (`sdxl_lightning_1step_x0.safetensors`) to `/ComfyUI/models/checkpoints`.
126
  1. Download our [ComfyUI full 1-step workflow](comfyui/sdxl_lightning_workflow_full_1step.json).
127
 
128
- ![SDXL-Lightning ComfyUI Full 1-Step Workflow](comfyui/sdxl_lightning_workflow_full_1step.jpg)
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10
 
11
  ![Intro Image](sdxl_lightning_samples.jpg)
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 paper: [SDXL-Lightning: Progressive Adversarial Diffusion Distillation](https://arxiv.org/abs/2402.13929). The models are released for research purposes only.
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
 
 
125
  1. Download the full checkpoint (`sdxl_lightning_1step_x0.safetensors`) to `/ComfyUI/models/checkpoints`.
126
  1. Download our [ComfyUI full 1-step workflow](comfyui/sdxl_lightning_workflow_full_1step.json).
127
 
128
+ ![SDXL-Lightning ComfyUI Full 1-Step Workflow](comfyui/sdxl_lightning_workflow_full_1step.jpg)
129
+
130
+
131
+ ## Cite Our Work
132
+ ```
133
+ @misc{lin2024sdxllightning,
134
+ title={SDXL-Lightning: Progressive Adversarial Diffusion Distillation},
135
+ author={Shanchuan Lin and Anran Wang and Xiao Yang},
136
+ year={2024},
137
+ eprint={2402.13929},
138
+ archivePrefix={arXiv},
139
+ primaryClass={cs.CV}
140
+ }
141
+ ```