Guizmus commited on
Commit
2fddadb
1 Parent(s): ea587c1

Delete README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -121
README.md DELETED
@@ -1,121 +0,0 @@
1
- ---
2
- language:
3
- - en
4
- license: creativeml-openrail-m
5
- thumbnail: "https://huggingface.co/Guizmus/SD_PoW_Collection/resolve/main/showcase.jpg"
6
- tags:
7
- - stable-diffusion
8
- - text-to-image
9
- - image-to-image
10
- library_name: "EveryDream"
11
- inference: false
12
- ---
13
-
14
- ![PoW](https://huggingface.co/Guizmus/SD_PoW_Collection/resolve/main/showcase.jpg)
15
-
16
- # Intro
17
-
18
- This is a collection of models related to the "Picture of the Week" contest on Stable Diffusion discord.
19
-
20
- I try to make a model out of all the submission for people to continue enjoy the theme after the even, and see a little of their designs in other people's creations. The token stays "PoW Style" and I balance the learning on the low side, so that it doesn't just replicate creations.
21
-
22
- I also make smaller quality models to help make pictures for the contest itself, based on the theme.
23
-
24
- ## 14 novembre 2022, "The Never-Ending Loop"
25
-
26
- ### Theme : The Never-Ending Loop
27
-
28
- It is a passed-down proverb that lines represent the flow of time itself. They converge and take shape. They twist, tangle, sometimes unravel, break, and then connect again.
29
-
30
- * Without words, how are we able to accurately represent this flow of time with only lines? geometrically, intricately, asymmetricaly, seamlessly, ornately...
31
- * Think of a never-ending pattern, texture, or shape– looping on and on for what feels infinite.
32
- * Just how detailed are you able to get with your patterns?
33
-
34
- Our prompt for this event was created by @Asukii !
35
-
36
- "the fractal flow of time stretches towards the horizon, surreal fractal intertwined looping pathways, dramatic cinematic perspective, detailed delicate intricate ornate linework, geometric abstract masterwork digital art, quantum wavetracing, ink drawing, optical illusion"
37
-
38
-
39
- ![PoW](https://huggingface.co/Guizmus/SD_PoW_Collection/resolve/main/141122/images/theme1.png)
40
-
41
- ![PoW](https://huggingface.co/Guizmus/SD_PoW_Collection/resolve/main/141122/images/theme2.png)
42
-
43
- ### Models
44
-
45
- ![PoW Style](https://huggingface.co/Guizmus/SD_PoW_Collection/resolve/main/141122/images/showcase_FractimeStyle.jpg)
46
- * based on the suggested prompt and theme
47
- * training: 50 pictures, 1750 steps on batch 6, 1e-6 polynomial LR.
48
- * balance to be tested
49
- * **Activation token :** `Fractime Style`
50
- * Other noticable tokens : intricate, nebula, illusion, person, road, tree, boat
51
- * [CKPT link](https://huggingface.co/Guizmus/SD_PoW_Collection/resolve/main/141122/ckpts/FractimeStyle.ckpt)
52
- * [Dataset](https://huggingface.co/Guizmus/SD_PoW_Collection/resolve/main/141122/PoW_141122_1_dataset.zip)
53
-
54
-
55
- ## 09 novembre 2022, "Abstralities"
56
-
57
- ### Theme : Abstract Realities
58
-
59
- Glitch, warp, static, shape, flicker, break, bend, mend
60
-
61
- Have you ever felt your reality shift out from under your feet? Our perception falters and repairs itself in the blink of an eye. Just how much do our brains influence what we perceive? How much control do we have over molding these realities?
62
-
63
- With the introduction of AI and its rapid pace taking the world by storm, we are seeing single-handedly just how these realities can bring worlds into fruition.
64
-
65
- * Can you show us your altered reality?
66
- * Are these realities truly broken, or only bent?
67
-
68
- Our example prompt for this event was created by @Aether !
69
-
70
- "household objects floating in space, bedroom, furniture, home living, warped reality, cosmic horror, nightmare, retrofuturism, surrealism, abstract, illustrations by alan nasmith"
71
-
72
-
73
- ![PoW](https://huggingface.co/Guizmus/SD_PoW_Collection/resolve/main/091122/images/AETHER.png)
74
-
75
- ![PoW](https://huggingface.co/Guizmus/SD_PoW_Collection/resolve/main/091122/images/aether2.png)
76
-
77
- ### Models
78
-
79
- ![PoW Style](https://huggingface.co/Guizmus/SD_PoW_Collection/resolve/main/091122/images/showcase_pow_final.jpg)
80
- * Main model based on all the results from the PoW
81
- * training: 51 pictures, 3000 steps on 1e-6 polynomial LR.
82
- * balanced on the light side, add attention/weight on the activation token
83
- * **Activation token :** `PoW Style`
84
- * [CKPT link](https://huggingface.co/Guizmus/SD_PoW_Collection/resolve/main/091122/ckpts/PoWStyle_Abstralities.ckpt)
85
- * [Diffusers : Guizmus/SD_PoW_Collection/091122/diffusers](https://huggingface.co/Guizmus/SD_PoW_Collection/tree/main/091122/diffusers/)
86
- * [Dataset](https://huggingface.co/Guizmus/SD_PoW_Collection/resolve/main/091122/dataset.zip)
87
-
88
- ---
89
-
90
- ![Bendstract Style](https://huggingface.co/Guizmus/SD_PoW_Collection/resolve/main/091122/images/showcase_bendstract.jpg)
91
- * based on the suggested prompt
92
- * training: 100 pictures, 7500 steps on 1e-6 polynomial LR. overtrained
93
- * **Activation token :** `Bendstract Style`
94
- * [CKPT link](https://huggingface.co/Guizmus/SD_PoW_Collection/resolve/main/091122/ckpts/Bendstract-v1.ckpt)
95
-
96
- ---
97
-
98
- ![BendingReality Style](https://huggingface.co/Guizmus/SD_PoW_Collection/resolve/main/091122/images/showcase_bendingreality.jpg)
99
- * based on the suggested prompt
100
- * training: 68 pictures, 6000 steps on 1e-6 polynomial LR. overtrained
101
- * **Activation token :** `BendingReality Style`
102
- * [CKPT link](https://huggingface.co/Guizmus/SD_PoW_Collection/resolve/main/091122/ckpts/BendingReality_Style-v1.ckpt)
103
-
104
- ---
105
-
106
- ![PoW Style](https://huggingface.co/Guizmus/SD_PoW_Collection/resolve/main/091122/images/showcase_pow_midrun.jpg)
107
- * based on the first few submissions
108
- * training: 24 pictures, 2400 steps on 1e-6 polynomial LR. a little too trained
109
- * **Activation token :** `PoW Style`
110
- * [CKPT link](https://huggingface.co/Guizmus/SD_PoW_Collection/resolve/main/091122/ckpts/PoWStyle_midrun.ckpt)
111
-
112
-
113
- ## License
114
-
115
- These models are open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage.
116
- The CreativeML OpenRAIL License specifies:
117
-
118
- 1. You can't use the model to deliberately produce nor share illegal or harmful outputs or content
119
- 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
120
- 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)
121
- [Please read the full license here](https://huggingface.co/spaces/CompVis/stable-diffusion-license)