TheRafal commited on
Commit
d35b321
1 Parent(s): f24ad95

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +122 -0
README.md CHANGED
@@ -1,3 +1,125 @@
1
  ---
2
  license: creativeml-openrail-m
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: creativeml-openrail-m
3
+ language:
4
+ - en
5
+ thumbnail: >-
6
+ https://huggingface.co/TheRafal/everything-v1/resolve/main/img/thumbnail.png
7
+ pipeline_tag: text-to-image
8
+ tags:
9
+ - stable-diffusion
10
+ - stable-diffusion-diffusers
11
+ - text-to-image
12
+ - image-to-image
13
+ - diffusers
14
+ - aiart
15
+ - anime
16
  ---
17
+
18
+ <center><img src="https://huggingface.co/TheRafal/everything-v1/resolve/main/img/1.png" width="768" height="768" alt="Girl on cherry blossom background" /></center>
19
+
20
+ ![visitors](https://visitor-badge.glitch.me/badge?page_id=everything-v1&left_color=red)
21
+
22
+ ----
23
+
24
+ # Everything V1
25
+ Everything V1 is a fine-tuned model based on Anything V3. It was trained using Dreambooth and merged using Merge Block Weighted. Like other anime-style Stable Diffusion models, it also supports danbooru tags to generate images.
26
+
27
+ e.g. **_1girl, white hair, blue eyes, cat ears, outdoors, city_**
28
+
29
+ <details>
30
+ <summary>SHOW IMAGE</summary>
31
+
32
+ <center><img src="https://huggingface.co/TheRafal/everything-v1/resolve/main/img/example.png" width="512" height="512" alt="Example prompt" /></center>
33
+
34
+ </details>
35
+
36
+ ----
37
+
38
+ # How to download
39
+
40
+ ## Batch download
41
+
42
+ 1. Install Git
43
+ 2. Create a folder of your choice and right click → "Git bash here" and open a gitbash on the folder's directory.
44
+ 3. Run the following commands in order.
45
+
46
+ ```
47
+ git lfs install
48
+ git clone https://huggingface.co/TheRafal/everything-v1
49
+ ```
50
+
51
+ 4. Complete
52
+
53
+ ## Select and download
54
+
55
+ 1. Go to the [Files and versions](https://huggingface.co/TheRafal/everything-v1/tree/main) tab
56
+ 2. Select the model you want to download
57
+ 3. Download
58
+ 4. Complete
59
+
60
+ ----
61
+
62
+ # Diffusers
63
+
64
+ This model can be used just like any other Stable Diffusion model.
65
+
66
+ You can also export the model to [ONNX](https://huggingface.co/docs/diffusers/optimization/onnx) or [MPS](https://huggingface.co/docs/diffusers/optimization/mps).
67
+
68
+ ```python
69
+ import torch
70
+ from torch import autocast
71
+ from diffusers import StableDiffusionPipeline
72
+
73
+ pipe = StableDiffusionPipeline.from_pretrained('TheRafal/everything-v1', torch_dtype=torch.float32).to('cuda')
74
+
75
+ prompt = "masterpiece, 1girl, blonde hair, blue eyes, colorful, cumulonimbus clouds, lighting, short hair, city, hoodie, night"
76
+ with autocast("cuda"):
77
+ image = pipe(prompt, num_inference_steps=50, guidance_scale=7.5)["images"][0]
78
+
79
+ image.save(prompt.replace(" ", "_") + ".png")
80
+ ```
81
+
82
+ <details>
83
+ <summary>SHOW IMAGE</summary>
84
+
85
+ **Anime Girl:**
86
+ ![Anime Girl](https://huggingface.co/TheRafal/everything-v1/resolve/main/img/test.png)
87
+
88
+ </details>
89
+
90
+ ----
91
+
92
+ # Examples
93
+
94
+ Below are some examples of images generated using this model:
95
+
96
+ <details>
97
+ <summary>SHOW IMAGES</summary>
98
+
99
+ **Anime Girl:**
100
+ ![Anime Girl](https://huggingface.co/TheRafal/everything-v1/resolve/main/img/1girl.png)
101
+ ```
102
+ 1girl, red hair, blue eyes, short hair, jacket, winter clothes, scarf, outdoors, tokyo \(city\), snow, snowing, gloves, pants, looking at viewer, cowboy shot
103
+ Steps: 50, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 2436148258, Size: 768x768
104
+ ```
105
+
106
+ **Anime Boy:**
107
+ ![Anime Boy](https://huggingface.co/TheRafal/everything-v1/resolve/main/img/1boy.png)
108
+ ```
109
+ 1boy, black hair, green eyes, bishounen, casual, indoors, sitting, coffee shop, sitting, bokeh
110
+ Steps: 50, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 4225599226, Size: 768x768
111
+ ```
112
+
113
+ </details>
114
+
115
+ ----
116
+
117
+ # License
118
+
119
+ This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage.
120
+ The CreativeML OpenRAIL License specifies:
121
+
122
+ 1. You can't use the model to deliberately produce nor share illegal or harmful outputs or content
123
+ 2. The authors claims no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in the license
124
+ 3. You may re-distribute the weights and use the model commercially and/or as a service. If you do, please be aware you have to include the same use restrictions as the ones in the license and share a copy of the CreativeML OpenRAIL-M to all your users (please read the license entirely and carefully)
125
+ [Please read the full license here](https://huggingface.co/spaces/CompVis/stable-diffusion-license)