Update README.md
Browse files
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 |
-
|
|
|
|
|
|
|
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 |
-
|
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
|
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
|