Hugging Face's logo

ByteDance
/
SDXL-Lightning

Text-to-Image
Diffusers
stable-diffusion
Model card Files
xet
Community
62
PeterL1n commited on
Commit
08f9888
·
verified ·
1 Parent(s): 8d5ebb6

Update readme

Browse files
Files changed (1) hide show
  1. README.md +5 -4
README.md CHANGED
@@ -3,6 +3,7 @@ license: openrail++
3
  tags:
4
  - text-to-image
5
  - stable-diffusion
 
6
  ---
7
 
8
  # SDXL-Lightning
@@ -11,7 +12,7 @@ tags:
11
 
12
  SDXL-Lightning is a lightning fast text-to-image generative model. It can generate high-quality 1024px images under a few steps. For more information, please refer to our paper: [SDXL-Lightning: Progressive Adversarial Diffusion Distillation](). The models are released for research purposes only.
13
 
14
- 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.
15
 
16
  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.
17
 
@@ -28,7 +29,7 @@ from diffusers import StableDiffusionXLPipeline, EulerDiscreteScheduler
28
  from huggingface_hub import hf_hub_download
29
 
30
  base = "stabilityai/stable-diffusion-xl-base-1.0"
31
- repo = "bytedance/sdxl-lightning"
32
  ckpt = "sdxl_lightning_4step_unet.pth" # Use the correct ckpt for your step setting!
33
 
34
  # Load model.
@@ -50,7 +51,7 @@ from diffusers import StableDiffusionXLPipeline, EulerDiscreteScheduler
50
  from huggingface_hub import hf_hub_download
51
 
52
  base = "stabilityai/stable-diffusion-xl-base-1.0"
53
- repo = "bytedance/sdxl-lightning"
54
  ckpt = "sdxl_lightning_4step_lora.pth" # Use the correct ckpt for your step setting!
55
 
56
  # Load model.
@@ -73,7 +74,7 @@ from diffusers import StableDiffusionXLPipeline, EulerDiscreteScheduler
73
  from huggingface_hub import hf_hub_download
74
 
75
  base = "stabilityai/stable-diffusion-xl-base-1.0"
76
- repo = "bytedance/sdxl-lightning"
77
  ckpt = "sdxl_lightning_1step_unet.pth" # Use the correct ckpt for your step setting!
78
 
79
  # Load model.
 
3
  tags:
4
  - text-to-image
5
  - stable-diffusion
6
+ library_name: diffusers
7
  ---
8
 
9
  # SDXL-Lightning
 
12
 
13
  SDXL-Lightning is a lightning fast text-to-image generative model. It can generate high-quality 1024px images under a few steps. For more information, please refer to our paper: [SDXL-Lightning: Progressive Adversarial Diffusion Distillation](). 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) (coming soon). This repository contains checkpoints for 1-step, 2-step, 4-step, and 8-step distilled models.
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
 
 
29
  from huggingface_hub import hf_hub_download
30
 
31
  base = "stabilityai/stable-diffusion-xl-base-1.0"
32
+ repo = "ByteDance/sdxl-lightning"
33
  ckpt = "sdxl_lightning_4step_unet.pth" # Use the correct ckpt for your step setting!
34
 
35
  # Load model.
 
51
  from huggingface_hub import hf_hub_download
52
 
53
  base = "stabilityai/stable-diffusion-xl-base-1.0"
54
+ repo = "ByteDance/sdxl-lightning"
55
  ckpt = "sdxl_lightning_4step_lora.pth" # Use the correct ckpt for your step setting!
56
 
57
  # Load model.
 
74
  from huggingface_hub import hf_hub_download
75
 
76
  base = "stabilityai/stable-diffusion-xl-base-1.0"
77
+ repo = "ByteDance/sdxl-lightning"
78
  ckpt = "sdxl_lightning_1step_unet.pth" # Use the correct ckpt for your step setting!
79
 
80
  # Load model.