ming-yang commited on
Commit
889745d
1 Parent(s): 90b5738

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -11
README.md CHANGED
@@ -37,9 +37,14 @@ base_model: stabilityai/stable-diffusion-xl-base-1.0
37
  instance_prompt: Chinese Ink
38
  license: creativeml-openrail-m
39
  pipeline_tag: text-to-image
 
40
  ---
41
- ## Introduction
 
 
 
42
 
 
43
  The [**Stable Diffusion XL**](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0) model is finetuned on comtemporatory Chinese ink paintings.
44
 
45
  ## Usage
@@ -48,10 +53,7 @@ Our inference process is speed up using [**LCM-LORA**](https://huggingface.co/la
48
  pip install --upgrade pip
49
  pip install --upgrade diffusers transformers accelerate peft
50
  ```
51
- # Text to Image
52
-
53
- Text-to-Image
54
-
55
  Here, we should load two adapters, **LCM-LORA** for sample accleration and **Chinese_Ink_LORA** for styled rendering with it's base model stabilityai/stable-diffusion-xl-base-1.0.
56
  Next, the scheduler needs to be changed to LCMScheduler and we can reduce the number of inference steps to just 2 to 8 steps(8 used in my experiment).
57
 
@@ -86,15 +88,10 @@ axs[1].imshow(images[1])
86
  axs[1].axis('off')
87
  plt.show()
88
  ```
89
- ![plt](images/Comparison.png)
90
- # Chinese_Ink_Painting
91
-
92
- <Gallery />
93
-
94
 
95
  ## Trigger words
96
 
97
- You should use `Chinese Ink` to trigger the image generation.
98
 
99
 
100
  ## Download model
 
37
  instance_prompt: Chinese Ink
38
  license: creativeml-openrail-m
39
  pipeline_tag: text-to-image
40
+ library_name: diffusers
41
  ---
42
+ # Chinese Ink Painting
43
+
44
+ ## Examples
45
+ <Gallery />
46
 
47
+ ## Introduction
48
  The [**Stable Diffusion XL**](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0) model is finetuned on comtemporatory Chinese ink paintings.
49
 
50
  ## Usage
 
53
  pip install --upgrade pip
54
  pip install --upgrade diffusers transformers accelerate peft
55
  ```
56
+ ## Text to Image
 
 
 
57
  Here, we should load two adapters, **LCM-LORA** for sample accleration and **Chinese_Ink_LORA** for styled rendering with it's base model stabilityai/stable-diffusion-xl-base-1.0.
58
  Next, the scheduler needs to be changed to LCMScheduler and we can reduce the number of inference steps to just 2 to 8 steps(8 used in my experiment).
59
 
 
88
  axs[1].axis('off')
89
  plt.show()
90
  ```
 
 
 
 
 
91
 
92
  ## Trigger words
93
 
94
+ You should use **`Chinese Ink`** to trigger the image generation.
95
 
96
 
97
  ## Download model