FredZhang7
commited on
Commit
•
250fcaf
1
Parent(s):
7d4eaf4
Update README.md
Browse files
README.md
CHANGED
@@ -14,7 +14,7 @@ library_name: diffusers
|
|
14 |
---
|
15 |
## Paint Journey V2 is [Paint Journey V1](https://huggingface.co/FredZhang7/paint-journey-v1) fine-tuned on 768x768 oil paintings by Midjourney, Open Journey V2, and Disco Diffusion
|
16 |
|
17 |
-
*
|
18 |
Paint Journey V2 tends to output masterpieces of beauty and finesse with descriptive positive and negative prompts.*
|
19 |
|
20 |
Begin the prompt with **((oil painting))** for the oil paint effect. For digital paintings, enter similar prompts as you would for Open Journey V2 or Disco Diffusion.
|
@@ -26,88 +26,17 @@ compared to models like Dreamlike Diffusion 1.0, this model tends to generate 76
|
|
26 |
Instead of solely fine-tuning its Unet, Paint Journey V2 focuses on fine-tuning its text encoder with a diverse range of prompts.
|
27 |
This allows for a seamless blend of the digital and oil painting styles into various other types of prompts, resulting in a more natural and dynamic output.
|
28 |
|
|
|
|
|
|
|
29 |
To further improve the resolution and reduce noise in generated images, especially when using the model for img2img, use [Paint Journey VAE](./paint_journey_v2.vae.pt) in combination with [Checkpoint](./paint_journey_v2.ckpt).
|
30 |
As an example, a Automatic1111's WebUI user can add both of these files to the `./stable-diffusion-webui/models/Stable-diffusion` folder.
|
31 |
|
32 |
|
33 |
-
##
|
34 |
-
|
35 |
-
![](./example_opmodel.png)
|
36 |
-
|
37 |
-
![](./example_opathlete.png)
|
38 |
-
|
39 |
-
## Landscape Examples
|
40 |
-
|
41 |
-
![](./example_oplighthouse.png)
|
42 |
-
|
43 |
-
![](./example_lushvalley.png)
|
44 |
-
|
45 |
-
![](./example_nighttime.png)
|
46 |
-
|
47 |
-
![](./example_opalienworld.png)
|
48 |
-
|
49 |
-
## Outerspace Examples
|
50 |
-
|
51 |
-
![](./example_opmilkyway.png)
|
52 |
-
|
53 |
-
![](./example_opuniverse.png)
|
54 |
-
|
55 |
-
![](./example_opspacestation.png)
|
56 |
-
|
57 |
-
Prompts from top to bottom:
|
58 |
-
|
59 |
-
<details>
|
60 |
-
<summary> Click to expand </summary>
|
61 |
-
|
62 |
-
```
|
63 |
-
((oil painting)), portrait of a cute attractive model, ((round pupil)), smirk, ((beautiful eyes)), high resolution, uhd wallpaper
|
64 |
-
Negative prompt: low-res blurry fog mutated body ((duplicate)) ((double head)) ((long neck)) ((extra eyes)) error ((extra fingers)) long face long body ((watermark)) signature
|
65 |
-
Steps: 20, Sampler: Euler a, CFG scale: 7.5, Seed: 874776980, Size: 512x768, Model hash: 26fd2f6f, Batch size: 4, Batch pos: 0
|
66 |
-
```
|
67 |
-
```
|
68 |
-
((oil painting)), portrait of a handsome young man, small smile, athlete, ((beautiful eyes)), high resolution, uhd wallpaper
|
69 |
-
Negative prompt: low-res blurry fog mutated body naked ((duplicate)) ((double head)) ((long neck)) ((extra eyes)) error ((extra fingers)) long face long body ((watermark)) signature
|
70 |
-
Steps: 20, Sampler: Euler a, CFG scale: 7.5, Seed: 2389251230, Size: 512x768, Model hash: 26fd2f6f, Batch size: 4, Batch pos: 0
|
71 |
-
```
|
72 |
-
```
|
73 |
-
((oil painting)), lighthouse near the sea, high resolution wallpaper
|
74 |
-
Negative prompt: low-res blurry fog watermark
|
75 |
-
Steps: 20, Sampler: Euler, CFG scale: 7.5, Seed: 353450032, Size: 768x768, Model hash: 26fd2f6f, Batch size: 4, Batch pos: 0
|
76 |
-
```
|
77 |
-
```
|
78 |
-
((oil painting)), a lush valley with mountains in the background, high resolution, uhd wallpaper
|
79 |
-
Negative prompt: low-res blurry fog watermark
|
80 |
-
Steps: 20, Sampler: Euler, CFG scale: 7.5, Seed: 65984537, Size: 1056x768, Model hash: 26fd2f6f, Batch size: 4, Batch pos: 0
|
81 |
-
```
|
82 |
-
```
|
83 |
-
((oil painting)), a forest, moon, dark, night, high resolution, uhd wallpaper
|
84 |
-
Negative prompt: low-res blurry fog watermark
|
85 |
-
Steps: 20, Sampler: Euler, CFG scale: 7.5, Seed: 4247689747, Size: 1056x768, Model hash: 26fd2f6f, Batch size: 4, Batch pos: 0
|
86 |
-
```
|
87 |
-
```
|
88 |
-
((oil painting)), stunning landscape in an alien world, high resolution, uhd wallpaper
|
89 |
-
Negative prompt: low-res blurry fog watermark
|
90 |
-
Steps: 20, Sampler: Euler, CFG scale: 7.5, Seed: 3693048118, Size: 1056x768, Model hash: 26fd2f6f, Batch size: 4, Batch pos: 0
|
91 |
-
```
|
92 |
-
```
|
93 |
-
((oil painting)), the milky way, high resolution, uhd wallpaper
|
94 |
-
Negative prompt: low-res blurry fog watermark
|
95 |
-
Steps: 20, Sampler: Euler, CFG scale: 7.5, Seed: 3904195208, Size: 1056x768, Model hash: 26fd2f6f, Batch size: 4, Batch pos: 0
|
96 |
-
```
|
97 |
-
```
|
98 |
-
((oil painting)), the universe, high resolution wallpaper
|
99 |
-
Negative prompt: low-res blurry fog watermark
|
100 |
-
Steps: 20, Sampler: Euler, CFG scale: 7.5, Seed: 432451301, Size: 768x768, Model hash: 26fd2f6f, Batch size: 4, Batch pos: 0
|
101 |
-
```
|
102 |
-
```
|
103 |
-
((oil painting)), a futuristic space station, lighting, sci-fi, dry paint, high resolution, uhd wallpaper
|
104 |
-
Negative prompt: low-res blurry ((fog)) watermark
|
105 |
-
Steps: 20, Sampler: Euler, CFG scale: 7.5, Seed: 4009095562, Size: 1056x768, Model hash: 26fd2f6f, Batch size: 4, Batch pos: 0
|
106 |
-
```
|
107 |
|
108 |
-
|
109 |
|
110 |
-
<br>
|
111 |
|
112 |
## Automatic1111's WebUI
|
113 |
```
|
|
|
14 |
---
|
15 |
## Paint Journey V2 is [Paint Journey V1](https://huggingface.co/FredZhang7/paint-journey-v1) fine-tuned on 768x768 oil paintings by Midjourney, Open Journey V2, and Disco Diffusion
|
16 |
|
17 |
+
*Redoing the examples because I recently discovered the endless possibilities with Paint Journey V2.
|
18 |
Paint Journey V2 tends to output masterpieces of beauty and finesse with descriptive positive and negative prompts.*
|
19 |
|
20 |
Begin the prompt with **((oil painting))** for the oil paint effect. For digital paintings, enter similar prompts as you would for Open Journey V2 or Disco Diffusion.
|
|
|
26 |
Instead of solely fine-tuning its Unet, Paint Journey V2 focuses on fine-tuning its text encoder with a diverse range of prompts.
|
27 |
This allows for a seamless blend of the digital and oil painting styles into various other types of prompts, resulting in a more natural and dynamic output.
|
28 |
|
29 |
+
This model was trained on a curated dataset of roughly 300 images hand-picked from Midjourney, [Prompt Hero](https://prompthero.com/), Open Journey V2, and Google Images.
|
30 |
+
Before training, I used R-ESRGAN 4x on many images to increase their resolution and reduce noise.
|
31 |
+
|
32 |
To further improve the resolution and reduce noise in generated images, especially when using the model for img2img, use [Paint Journey VAE](./paint_journey_v2.vae.pt) in combination with [Checkpoint](./paint_journey_v2.ckpt).
|
33 |
As an example, a Automatic1111's WebUI user can add both of these files to the `./stable-diffusion-webui/models/Stable-diffusion` folder.
|
34 |
|
35 |
|
36 |
+
## Examples
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
37 |
|
38 |
+
*Releasing soon*
|
39 |
|
|
|
40 |
|
41 |
## Automatic1111's WebUI
|
42 |
```
|