Hugging Face's logo

Guizmus
/
SD_DreamerCommunities_Collection

Text-to-Image
Diffusers
English
EveryDream
stable-diffusion
image-to-image
Model card Files
xet
Community
11

CharacterChan and CreatureChan

#6
by Guizmus - opened
base: refs/heads/main
←
from: refs/pr/6
Discussion Files changed
+81
-0
Files changed (10) hide show
  1. README.md +63 -0
  2. ckpt/CharacterChanStyle-v1.ckpt +3 -0
  3. ckpt/CharacterChanStyle-v1_with_optimizers.ckpt +3 -0
  4. ckpt/CreatureChanStyle-v1.ckpt +3 -0
  5. ckpt/CreatureChanStyle-v1_with_optimizers.ckpt +3 -0
  6. datasets/CharacterChanStyle-v1.zip +3 -0
  7. datasets/CreatureChanStyle-v1.zip +3 -0
  8. images/showcase_CharacterChanStyle-v1.jpg +0 -0
  9. images/showcase_CreatureChanStyle-v1.jpg +0 -0
  10. images/showcase_main.jpg +0 -0
README.md CHANGED
@@ -7,6 +7,7 @@ tags:
7
  - stable-diffusion
8
  - text-to-image
9
  - image-to-image
 
10
  library_name: "EveryDream"
11
  inference: false
12
  ---
@@ -19,6 +20,67 @@ Those are mainly done through the use of EveryDream, and should result in a Mega
19
 
20
 
21
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
22
  # 3DChan Style
23
 
24
 
@@ -50,6 +112,7 @@ Other significant tokens : rick roll, fullbody shot, bad cosplay man
50
 
51
 
52
 
 
53
  # AnimeChan Style
54
 
55
  ## Dataset & training
 
7
  - stable-diffusion
8
  - text-to-image
9
  - image-to-image
10
+ - diffusers
11
  library_name: "EveryDream"
12
  inference: false
13
  ---
 
20
 
21
 
22
 
23
+
24
+ # CharacterChan Style
25
+
26
+
27
+ ## Dataset & training
28
+
29
+ This model was based on [RunwayML SD 1.5](https://huggingface.co/runwayml/stable-diffusion-v1-5) model with updated VAE.
30
+
31
+ The dataset was a collaborative effort of the Stable Diffusion #CharacterChan channel, made of pictures from the users themselves using their different techniques.
32
+
33
+ 50 total pictures in the dataset, 160 repeats total each, over 4 Epoch on LR1e-6.
34
+
35
+ This was trained using EveryDream with a full caption of all training pictures.
36
+
37
+ The style will be called by the use of the token **CharacterChan Style**.
38
+
39
+ ## Showcase & Downloads v1
40
+
41
+ ![Showcase](https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/resolve/main/images/showcase_CharacterChanStyle-v1.jpg)
42
+
43
+ [CKPT (2GB)](https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/resolve/main/ckpt/CharacterChanStyle-v1.ckpt)
44
+
45
+ [CKPT with training optimizers (11GB)](https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/resolve/main/ckpt/CharacterChanStyle-v1_with_optimizers.ckpt)
46
+
47
+ [Diffusers](https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/tree/main/diffusers/CharacterChan)
48
+
49
+ [Dataset](https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/resolve/main/datasets/CharacterChan-v1.zip)
50
+
51
+
52
+
53
+
54
+ # CreatureChan Style
55
+
56
+
57
+ ## Dataset & training
58
+
59
+ This model was based on [RunwayML SD 1.5](https://huggingface.co/runwayml/stable-diffusion-v1-5) model with updated VAE.
60
+
61
+ The dataset was a collaborative effort of the Stable Diffusion #CreatureChan channel, made of pictures from the users themselves using their different techniques.
62
+
63
+ 50 total pictures in the dataset, 160 repeats total each, over 4 Epoch on LR1e-6.
64
+
65
+ This was trained using EveryDream with a full caption of all training pictures.
66
+
67
+ The style will be called by the use of the token **CreatureChan Style**.
68
+
69
+ ## Showcase & Downloads v1
70
+
71
+ ![Showcase](https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/resolve/main/images/showcase_CreatureChanStyle-v1.jpg)
72
+
73
+ [CKPT (2GB)](https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/resolve/main/ckpt/CreatureChanStyle-v1.ckpt)
74
+
75
+ [CKPT with training optimizers (11GB)](https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/resolve/main/ckpt/CreatureChanStyle-v1_with_optimizers.ckpt)
76
+
77
+ [Diffusers](https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/tree/main/diffusers/CreatureChanStyle)
78
+
79
+ [Dataset](https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/resolve/main/datasets/CreatureChanStyle-v1.zip)
80
+
81
+
82
+
83
+
84
  # 3DChan Style
85
 
86
 
 
112
 
113
 
114
 
115
+
116
  # AnimeChan Style
117
 
118
  ## Dataset & training
ckpt/CharacterChanStyle-v1.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0e7dd65a9c41c8930a0464c68f4a71336f76413daa4e1254a126a6027d20a99
3
+ size 2132889372
ckpt/CharacterChanStyle-v1_with_optimizers.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dabe2850f6d8c3debeca77f7964259c5bb349bcc37f8c6dddfa1e979966c188c
3
+ size 12126931034
ckpt/CreatureChanStyle-v1.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c3eae484d059fdaefa34bf223d1105fd43c4ab110314e467ee8fa0d2eceebcd
3
+ size 2132889372
ckpt/CreatureChanStyle-v1_with_optimizers.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f455ea7c0431d2b2d492334ae903942519556465cc9302c51a6518dc0d30318
3
+ size 12126931034
datasets/CharacterChanStyle-v1.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ac66c60693df173c0a971eec1556eb0869c1e323b58c8458fd2a72a570cbfd0
3
+ size 20564921
datasets/CreatureChanStyle-v1.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b5edc1d01f07ad73ed5adc5d77a7fea0bb7d84eef103f5d3a90aa9265aa7345
3
+ size 20905642
images/showcase_CharacterChanStyle-v1.jpg ADDED
images/showcase_CreatureChanStyle-v1.jpg ADDED
images/showcase_main.jpg CHANGED