Text-to-Image
Diffusers
Safetensors
quickjkee commited on
Commit
ef68ca4
·
verified ·
1 Parent(s): 6c1e673

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +42 -3
README.md CHANGED
@@ -3,7 +3,6 @@ license: apache-2.0
3
  library_name: diffusers
4
  pipeline_tag: text-to-image
5
  ---
6
-
7
  # Scale-wise Distillation 3.5 Medium
8
  Scale-wise Distillation (SwD) is a novel framework for accelerating diffusion models (DMs)
9
  by progressively increasing spatial resolution during the generation process.
@@ -11,9 +10,49 @@ by progressively increasing spatial resolution during the generation process.
11
  while maintaining or even improving image quality.
12
  ![3.5 Medium Demo Image](swd.png)
13
 
 
 
 
 
14
  ## Usage
15
- To generate images using SwD, go to <a href="https://github.com/yandex-research/swd ">GitHub</a>
16
- or <a href="https://huggingface.co/spaces/dbaranchuk/Scale-wise-Distillation">Hugging Face's demo </a>.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
17
 
18
  ## Citation
19
 
 
3
  library_name: diffusers
4
  pipeline_tag: text-to-image
5
  ---
 
6
  # Scale-wise Distillation 3.5 Medium
7
  Scale-wise Distillation (SwD) is a novel framework for accelerating diffusion models (DMs)
8
  by progressively increasing spatial resolution during the generation process.
 
10
  while maintaining or even improving image quality.
11
  ![3.5 Medium Demo Image](swd.png)
12
 
13
+ Project page: https://yandex-research.github.io/swd <br>
14
+ GitHub: https://github.com/yandex-research/swd <br>
15
+ Demo: https://huggingface.co/spaces/dbaranchuk/Scale-wise-Distillation
16
+
17
  ## Usage
18
+ Upgrade to the latest version of the [🧨 diffusers library](https://github.com/huggingface/diffusers)
19
+ ```
20
+ pip install -U diffusers
21
+ ```
22
+
23
+ and then you can run
24
+ ```py
25
+ import torch
26
+ from diffusers import StableDiffusion3Pipeline
27
+ from peft import PeftModel
28
+ pipe = StableDiffusion3Pipeline.from_pretrained("stabilityai/stable-diffusion-3.5-medium",
29
+ torch_dtype=torch.float16,
30
+ custom_pipeline='quickjkee/swd_pipeline')
31
+ pipe = pipe.to("cuda")
32
+ lora_path = 'yresearch/swd-medium-4-steps'
33
+ pipe.transformer = PeftModel.from_pretrained(
34
+ pipe.transformer,
35
+ lora_path,
36
+ )
37
+ generator = torch.Generator().manual_seed(1)
38
+ prompt = 'A dog holding a sign that reads Sample Faster'
39
+ sigmas = [1.0000, 0.9454, 0.7904, 0.6022, 0.0000]
40
+ scales = [32, 64, 96, 128]
41
+
42
+ images = pipe(
43
+ prompt,
44
+ sigmas=torch.tensor(sigmas).to('cuda'),
45
+ timesteps=torch.tensor(sigmas[:-1]).to('cuda') * 1000,
46
+ scales=scales,
47
+ guidance_scale=0.0,
48
+ height=int(scales[0] * 8),
49
+ width=int(scales[0] * 8),
50
+ generator=generator,
51
+ ).images
52
+ ```
53
+ <p align="center">
54
+ <img src="medium.jpg" width="512px"/>
55
+ </p>
56
 
57
  ## Citation
58