Upload 2 files
Browse files- README.md +123 -0
- dataset.zip +3 -0
README.md
CHANGED
@@ -1,3 +1,126 @@
|
|
1 |
---
|
|
|
|
|
2 |
license: creativeml-openrail-m
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
license: creativeml-openrail-m
|
5 |
+
thumbnail: "https://huggingface.co/Guizmus/SDArt_cosmichorrors768/resolve/main/showcase.jpg"
|
6 |
+
tags:
|
7 |
+
- stable-diffusion
|
8 |
+
- text-to-image
|
9 |
+
- image-to-image
|
10 |
---
|
11 |
+
# SDArt : Cosmic Horrors (version based on 2.1 768px)
|
12 |
+
|
13 |
+
![Showcase](https://huggingface.co/Guizmus/SDArt_cosmichorrors768/resolve/main/showcase.jpg)
|
14 |
+
|
15 |
+
## Theme
|
16 |
+
|
17 |
+
> It was a stupid idea, I know that now. I thought I was brave, daring, that I could handle anything. But nothing could have prepared me for what I found on the other side of the veil. I had always been fascinated by the unknown and the supernatural, and finally, found a ritual that would grant me passage.
|
18 |
+
>
|
19 |
+
> As I recited the incantation, my mind was wrenched apart, tearing at the senses as I felt an indescribable sense of disorientation. The world was drained of color, shrouded in a thick, eerie mist that clung to my skin. I couldn't see anything moving but there was a strange silence that hung in the air. It was eerie.. unsettling.. like walking through a graveyard.
|
20 |
+
>
|
21 |
+
> And then, I saw it.
|
22 |
+
>
|
23 |
+
> Beyond the veil was a terror beyond anything I had ever imagined. A mass of writhing tendrils, some thick and muscular, others thin and sinuous that moved with a strange, fluid grace. Its eyes were pure black within a world of gray - drawing me in like a magnet.
|
24 |
+
>
|
25 |
+
> I tried to flee, but my feet seemed to be rooted to the spot. It was like the entity had some kind of hold over me. I could feel its presence in my mind, trying to rend it apart. It whispered to me the secrets of the universe, knowledge meant for no human to possess.
|
26 |
+
>
|
27 |
+
> And then, I saw black.
|
28 |
+
>
|
29 |
+
> When I opened my eyes again, I was back in my own world. But the memory of the gray world and the creature haunted me. I had looked into the abyss of the unknown, and it had looked back.
|
30 |
+
|
31 |
+
**COW #2 - Cosmic Horrors**
|
32 |
+
|
33 |
+
The veil between worlds is wearing thin.. and the monsters await.
|
34 |
+
|
35 |
+
Prepare yourself for an encounter with a terrifying monster that is beyond human comprehension. Beware, for these eldritch entities exist outside the realms of your reality, and to face them is to stare into the abyss of the unknown.
|
36 |
+
|
37 |
+
**Challenges:**
|
38 |
+
|
39 |
+
* Your image must be mostly grayscale.
|
40 |
+
* Your artwork must feature an eldritch entity or monster.
|
41 |
+
* Create mist/fog within the composition to add an element of suspense and mystery.
|
42 |
+
|
43 |
+
|
44 |
+
## Model description
|
45 |
+
|
46 |
+
This is a model related to the "Challenge of the WeekEnd" contest on Stable Diffusion discord..
|
47 |
+
|
48 |
+
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 "SDArt" and I balance the learning on the low side, so that it doesn't just replicate creations.
|
49 |
+
|
50 |
+
The total dataset is made of 39 pictures. It was trained on [Stable diffusion 2.1 768px](https://huggingface.co/stabilityai/stable-diffusion-2-1). I used [EveryDream](https://github.com/victorchall/EveryDream2trainer) to do the training, 100 total repeat per picture. The pictures were tagged using the token "SDArt", and an arbitrary token I choose. The dataset is provided below, as well as a list of usernames and their corresponding token.
|
51 |
+
|
52 |
+
The recommended sampling is k_Euler_a or DPM++ 2M Karras on 20 steps, CFGS 7.5 .
|
53 |
+
|
54 |
+
## Trained tokens
|
55 |
+
|
56 |
+
* SDArt
|
57 |
+
* dyce
|
58 |
+
* bnp
|
59 |
+
* keel
|
60 |
+
* fcu
|
61 |
+
* cous
|
62 |
+
* aved
|
63 |
+
* pfa
|
64 |
+
* kprc
|
65 |
+
* kuro
|
66 |
+
* elis
|
67 |
+
* ndi
|
68 |
+
* asot
|
69 |
+
* loeb
|
70 |
+
* bsp
|
71 |
+
* psst
|
72 |
+
* irgc
|
73 |
+
* mds
|
74 |
+
* kts
|
75 |
+
* byes
|
76 |
+
* dany
|
77 |
+
* mss
|
78 |
+
* guin
|
79 |
+
* mgt
|
80 |
+
* mwf
|
81 |
+
* crit
|
82 |
+
* mlas
|
83 |
+
* isch
|
84 |
+
* phol
|
85 |
+
* vedi
|
86 |
+
* dds
|
87 |
+
* httr
|
88 |
+
* pte
|
89 |
+
* oxi
|
90 |
+
* nery
|
91 |
+
* nips
|
92 |
+
* nlwx
|
93 |
+
* nrg
|
94 |
+
* ofi
|
95 |
+
* olis
|
96 |
+
|
97 |
+
## Download links
|
98 |
+
|
99 |
+
[SafeTensors](https://huggingface.co/Guizmus/SDArt_cosmichorrors768/resolve/main/SDArt_cosmichorrors768.safetensors)
|
100 |
+
|
101 |
+
[CKPT](https://huggingface.co/Guizmus/SDArt_cosmichorrors768/resolve/main/SDArt_cosmichorrors768.ckpt)
|
102 |
+
|
103 |
+
[Config (yaml)](https://huggingface.co/Guizmus/SDArt_cosmichorrors768/resolve/main/SDArt_cosmichorrors768.yaml)
|
104 |
+
|
105 |
+
[Dataset](https://huggingface.co/Guizmus/SDArt_cosmichorrors768/resolve/main/dataset.zip)
|
106 |
+
|
107 |
+
## 🧨 Diffusers
|
108 |
+
|
109 |
+
This model can be used just like any other Stable Diffusion model. For more information,
|
110 |
+
please have a look at the [Stable Diffusion](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion).
|
111 |
+
|
112 |
+
You can also export the model to [ONNX](https://huggingface.co/docs/diffusers/optimization/onnx), [MPS](https://huggingface.co/docs/diffusers/optimization/mps) and/or [FLAX/JAX]().
|
113 |
+
|
114 |
+
```python
|
115 |
+
from diffusers import StableDiffusionPipeline
|
116 |
+
import torch
|
117 |
+
|
118 |
+
model_id = "Guizmus/SDArt_cosmichorrors768"
|
119 |
+
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
|
120 |
+
pipe = pipe.to("cuda")
|
121 |
+
|
122 |
+
prompt = "SDArt httr"
|
123 |
+
image = pipe(prompt).images[0]
|
124 |
+
|
125 |
+
image.save("./SDArt.png")
|
126 |
+
```
|
dataset.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0c652812ae6b48c45414e870f7c6906339d1bf496173054989464d06947ab00
|
3 |
+
size 4737000
|