FredZhang7
commited on
Commit
•
93ad14d
1
Parent(s):
35aac19
Update README.md
Browse files
README.md
CHANGED
@@ -1,8 +1,19 @@
|
|
1 |
---
|
2 |
license: creativeml-openrail-m
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
4 |
## Paint Journey V2 is [Paint Journey V1](https://huggingface.co/FredZhang7/paint-journey-v1) fine-tuned on 768x768 oil paintings by Midjourney, Open Journey, and Disco Diffusion
|
5 |
-
|
|
|
|
|
6 |
|
7 |
## Portrait Examples
|
8 |
|
@@ -74,4 +85,31 @@ Steps: 20, Sampler: Euler, CFG scale: 7.5, Seed: 432451301, Size: 768x768, Model
|
|
74 |
((oil painting)), a futuristic space station, lighting, sci-fi, dry paint, high resolution, uhd wallpaper
|
75 |
Negative prompt: low-res blurry ((fog)) watermark
|
76 |
Steps: 20, Sampler: Euler, CFG scale: 7.5, Seed: 4009095562, Size: 1056x768, Model hash: 26fd2f6f, Batch size: 4, Batch pos: 0
|
77 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: creativeml-openrail-m
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
tags:
|
6 |
+
- text-to-image
|
7 |
+
- stable-diffusion
|
8 |
+
- disco-diffusion
|
9 |
+
- painting
|
10 |
+
- art
|
11 |
+
inference: true
|
12 |
---
|
13 |
## Paint Journey V2 is [Paint Journey V1](https://huggingface.co/FredZhang7/paint-journey-v1) fine-tuned on 768x768 oil paintings by Midjourney, Open Journey, and Disco Diffusion
|
14 |
+
|
15 |
+
Put **((oil painting))** at the start of the prompt for the style effect. For starters, try a dimension of 768x768 for anything, 512x768 for portraits, and 1056x768 for landscapes.
|
16 |
+
|
17 |
|
18 |
## Portrait Examples
|
19 |
|
|
|
85 |
((oil painting)), a futuristic space station, lighting, sci-fi, dry paint, high resolution, uhd wallpaper
|
86 |
Negative prompt: low-res blurry ((fog)) watermark
|
87 |
Steps: 20, Sampler: Euler, CFG scale: 7.5, Seed: 4009095562, Size: 1056x768, Model hash: 26fd2f6f, Batch size: 4, Batch pos: 0
|
88 |
+
```
|
89 |
+
|
90 |
+
## WebUI Usage
|
91 |
+
```
|
92 |
+
git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui.git
|
93 |
+
```
|
94 |
+
Download [paint_journey_v2.ckpt](./paint_journey_v2.ckpt) to the `./stable-diffusion-webui/models/Stable-diffusion` folder. Run `webui-user.bat`.
|
95 |
+
|
96 |
+
## Diffusers Usage
|
97 |
+
```bash
|
98 |
+
pip install --upgrade diffusers
|
99 |
+
```
|
100 |
+
```python
|
101 |
+
from diffusers import StableDiffusionPipeline
|
102 |
+
import torch
|
103 |
+
|
104 |
+
pipe = StableDiffusionPipeline.from_pretrained("FredZhang7/paint-journey-v2")
|
105 |
+
pipe = pipe.to("cuda")
|
106 |
+
|
107 |
+
prompt = "((oil painting)) lighthouse near the sea, oil painting, high resolution wallpaper"
|
108 |
+
image = pipe(prompt).images[0]
|
109 |
+
|
110 |
+
image.save("./result.png")
|
111 |
+
```
|
112 |
+
|
113 |
+
## Safety Checker
|
114 |
+
|
115 |
+
The official [stable diffusion safety checker](https://huggingface.co/CompVis/stable-diffusion-safety-checker) uses up 1.22GB VRAM. Recommend using [Google Safesearch Mini](https://huggingface.co/FredZhang7/google-safesearch-mini) (99MB) to save 1.12GB VRAM.
|