FredZhang7 commited on
Commit
8d38984
1 Parent(s): 7fbb07e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +15 -15
README.md CHANGED
@@ -12,15 +12,9 @@ tags:
12
  inference: true
13
  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
- Begin the prompt with **((oil painting))** to add the oil paint effect. For digital and other painting styles, enter similar prompts as you would for Midjourney (with some tweaks), Stable Diffusion v1.5 (add more styles), Open Journey V2, or Disco Diffusion.
18
-
19
- Paint Journey V2's paintings are closer to human-drawn art than Open Journey V2.
20
- Compared to models like Dreamlike Diffusion 1.0, this model tends to generate 768x768 or higher resolution images with reduced noise levels.
21
- This model is also capable of generating stunning portraits at 768x1144 resolution without duplicated faces (with [Camenduru's WebUI](https://github.com/camenduru/stable-diffusion-webui)), a difficult task to models like DreamShaper 3.3.
22
-
23
- This model crafts more stunning masterpieces with more descriptive positive and negative prompts, though it can also generate beautiful landscapes with short prompts.
24
 
25
  [![Open with Camenduru's WebUI in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/AMLA-UBC/100-Exploring-the-World-of-Modern-Machine-Learning/blob/main/assets/PaintJourneyV2.ipynb)
26
 
@@ -29,20 +23,26 @@ This model crafts more stunning masterpieces with more descriptive positive and
29
  *All examples were generated using Camenduru's WebUI (see the Colab file)*
30
 
31
  ![](./assets/characters.png)
32
-
33
- *768x1136 portraits, generated with descriptive prompts and without face restoration, [generation parameters](https://huggingface.co/FredZhang7/paint-journey-v2/raw/main/assets/character_settings.txt)*
34
 
35
  ![](./assets/nature.png)
36
-
37
- *1280x768 (mostly) natural landscapes, generated with shorter prompts, [generation parameters](https://huggingface.co/FredZhang7/paint-journey-v2/raw/main/assets/nature_settings.txt)*
38
 
39
  ![](./assets/outerspace.png)
40
-
41
- *1152x768 outerspace landscapes, generated with descriptive prompts, [generation parameters](https://huggingface.co/FredZhang7/paint-journey-v2/raw/main/assets/outerspace_settings.txt)*
42
 
43
  ![](./assets/lamborghini.png)
 
 
 
 
 
 
 
 
44
 
45
- *1152x768 lamborghini, [generation parameters](https://huggingface.co/FredZhang7/paint-journey-v2/raw/main/assets/lamborghini_settings.txt)*
 
46
 
47
 
48
  ## Training
 
12
  inference: true
13
  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 V4, Open Journey V2, and Disco Diffusion
16
 
17
+ Begin the prompt with **((oil painting))** to add the oil paint effect. For digital and other painting styles, enter similar prompts as you would for Midjourney V4 (with some tweaks), Stable Diffusion v1.5 (add more styles), Open Journey V2, or Disco Diffusion.
 
 
 
 
 
 
18
 
19
  [![Open with Camenduru's WebUI in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/AMLA-UBC/100-Exploring-the-World-of-Modern-Machine-Learning/blob/main/assets/PaintJourneyV2.ipynb)
20
 
 
23
  *All examples were generated using Camenduru's WebUI (see the Colab file)*
24
 
25
  ![](./assets/characters.png)
26
+ *⬆️ 768x1136 portraits, generated with descriptive prompts and without face restoration, [generation parameters](https://huggingface.co/FredZhang7/paint-journey-v2/raw/main/assets/character_settings.txt)*
 
27
 
28
  ![](./assets/nature.png)
29
+ *⬆️ 1280x768 (mostly) natural landscapes, generated with shorter prompts, [generation parameters](https://huggingface.co/FredZhang7/paint-journey-v2/raw/main/assets/nature_settings.txt)*
 
30
 
31
  ![](./assets/outerspace.png)
32
+ *⬆️ 1152x768 outerspace landscapes, generated with descriptive prompts, [generation parameters](https://huggingface.co/FredZhang7/paint-journey-v2/raw/main/assets/outerspace_settings.txt)*
 
33
 
34
  ![](./assets/lamborghini.png)
35
+ *⬆️ 1152x768 lamborghini, [generation parameters](https://huggingface.co/FredZhang7/paint-journey-v2/raw/main/assets/lamborghini_settings.txt)*
36
+
37
+
38
+ ## Comparisons
39
+
40
+ Paint Journey V2's paintings are closer to human-drawn art than Open Journey V2.
41
+ Compared to models like Dreamlike Diffusion 1.0, this model tends to generate 768x768 or higher resolution images with reduced noise levels.
42
+ This model is also capable of generating stunning portraits at 768x1136 resolution without duplicated faces (with [Camenduru's WebUI](https://github.com/camenduru/stable-diffusion-webui)), a difficult task to models like DreamShaper 3.3.
43
 
44
+ At lower resolutions, DreamShaper 3.3 tends to generate higher quality portraits than Paint Journey V2 in terms of noise levels, given the same (short) postive and negative prompts.
45
+ However, this model can craft more stunning masterpieces with more descriptive positive and negative prompts and can still generate beautiful landscapes with short prompts.
46
 
47
 
48
  ## Training