PseudoTerminal X
commited on
Trained for 0 epochs and 4400 steps.
Browse filesTrained with datasets ['text-embeds-sdxl', 'photocb-clip-embeds', 'celebrities', 'movieposters', 'normalnudes', 'propagandaposters', 'guys', 'pixel-art', 'signs', 'moviecollection', 'bookcovers', 'nijijourney', 'experimental', 'ethnic', 'sports', 'gay', 'architecture', 'shutterstock', 'cinemamix-1mp', 'nsfw-1024', 'anatomy', 'bg20k-1024', 'yoga', 'photo-aesthetics', 'text-1mp', 'photo-concept-bucket']
Learning rate 4e-07, batch size 8, and 1 gradient accumulation steps.
Used DDPM noise scheduler for training with v_prediction prediction type and rescaled_betas_zero_snr=True
Using 'trailing' timestep spacing.
Base model: ptx0/terminus-xl-velocity-v1
VAE: madebyollin/sdxl-vae-fp16-fix
- README.md +75 -11
- optimizer.bin +1 -1
- random_states_0.pkl +1 -1
- training_state-anatomy.json +2 -2
- training_state-architecture.json +2 -2
- training_state-bg20k-1024.json +2 -2
- training_state-bookcovers.json +3 -0
- training_state-celebrities.json +2 -2
- training_state-cinemamix-1mp.json +2 -2
- training_state-ethnic.json +2 -2
- training_state-experimental.json +2 -2
- training_state-guys.json +3 -0
- training_state-moviecollection.json +3 -0
- training_state-movieposters.json +3 -0
- training_state-nijijourney.json +3 -0
- training_state-normalnudes.json +3 -0
- training_state-nsfw-1024.json +2 -2
- training_state-photo-aesthetics.json +2 -2
- training_state-photo-concept-bucket.json +2 -2
- training_state-pixel-art.json +3 -0
- training_state-propagandaposters.json +3 -0
- training_state-shutterstock.json +2 -2
- training_state-signs.json +3 -0
- training_state-text-1mp.json +2 -2
- training_state-yoga.json +2 -2
- training_state.json +1 -1
- unet/config.json +1 -1
- unet/diffusion_pytorch_model.safetensors +1 -1
README.md
CHANGED
@@ -44,7 +44,7 @@ You may reuse the base model text encoder for inference.
|
|
44 |
## Training settings
|
45 |
|
46 |
- Training epochs: 0
|
47 |
-
- Training steps:
|
48 |
- Learning rate: 4e-07
|
49 |
- Effective batch size: 8
|
50 |
- Micro-batch size: 8
|
@@ -58,26 +58,90 @@ You may reuse the base model text encoder for inference.
|
|
58 |
|
59 |
## Datasets
|
60 |
|
61 |
-
###
|
62 |
- Repeats: 0
|
63 |
-
- Total number of images:
|
64 |
-
- Total number of aspect buckets:
|
65 |
- Resolution: 1.0 megapixels
|
66 |
- Cropped: False
|
67 |
- Crop style: None
|
68 |
- Crop aspect: None
|
69 |
-
###
|
70 |
- Repeats: 0
|
71 |
-
- Total number of images:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
72 |
- Total number of aspect buckets: 20
|
73 |
- Resolution: 1.0 megapixels
|
74 |
- Cropped: False
|
75 |
- Crop style: None
|
76 |
- Crop aspect: None
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
77 |
### experimental
|
78 |
- Repeats: 0
|
79 |
- Total number of images: 2970
|
80 |
-
- Total number of aspect buckets:
|
81 |
- Resolution: 1.0 megapixels
|
82 |
- Cropped: False
|
83 |
- Crop style: None
|
@@ -85,7 +149,7 @@ You may reuse the base model text encoder for inference.
|
|
85 |
### ethnic
|
86 |
- Repeats: 0
|
87 |
- Total number of images: 3009
|
88 |
-
- Total number of aspect buckets:
|
89 |
- Resolution: 1.0 megapixels
|
90 |
- Cropped: False
|
91 |
- Crop style: None
|
@@ -109,7 +173,7 @@ You may reuse the base model text encoder for inference.
|
|
109 |
### architecture
|
110 |
- Repeats: 0
|
111 |
- Total number of images: 4258
|
112 |
-
- Total number of aspect buckets:
|
113 |
- Resolution: 1.0 megapixels
|
114 |
- Cropped: False
|
115 |
- Crop style: None
|
@@ -141,7 +205,7 @@ You may reuse the base model text encoder for inference.
|
|
141 |
### anatomy
|
142 |
- Repeats: 5
|
143 |
- Total number of images: 16329
|
144 |
-
- Total number of aspect buckets:
|
145 |
- Resolution: 1.0 megapixels
|
146 |
- Cropped: False
|
147 |
- Crop style: None
|
@@ -165,7 +229,7 @@ You may reuse the base model text encoder for inference.
|
|
165 |
### photo-aesthetics
|
166 |
- Repeats: 0
|
167 |
- Total number of images: 33031
|
168 |
-
- Total number of aspect buckets:
|
169 |
- Resolution: 1.0 megapixels
|
170 |
- Cropped: False
|
171 |
- Crop style: None
|
|
|
44 |
## Training settings
|
45 |
|
46 |
- Training epochs: 0
|
47 |
+
- Training steps: 4400
|
48 |
- Learning rate: 4e-07
|
49 |
- Effective batch size: 8
|
50 |
- Micro-batch size: 8
|
|
|
58 |
|
59 |
## Datasets
|
60 |
|
61 |
+
### celebrities
|
62 |
- Repeats: 0
|
63 |
+
- Total number of images: 1160
|
64 |
+
- Total number of aspect buckets: 17
|
65 |
- Resolution: 1.0 megapixels
|
66 |
- Cropped: False
|
67 |
- Crop style: None
|
68 |
- Crop aspect: None
|
69 |
+
### movieposters
|
70 |
- Repeats: 0
|
71 |
+
- Total number of images: 1624
|
72 |
+
- Total number of aspect buckets: 12
|
73 |
+
- Resolution: 1.0 megapixels
|
74 |
+
- Cropped: False
|
75 |
+
- Crop style: None
|
76 |
+
- Crop aspect: None
|
77 |
+
### normalnudes
|
78 |
+
- Repeats: 0
|
79 |
+
- Total number of images: 1000
|
80 |
- Total number of aspect buckets: 20
|
81 |
- Resolution: 1.0 megapixels
|
82 |
- Cropped: False
|
83 |
- Crop style: None
|
84 |
- Crop aspect: None
|
85 |
+
### propagandaposters
|
86 |
+
- Repeats: 0
|
87 |
+
- Total number of images: 576
|
88 |
+
- Total number of aspect buckets: 18
|
89 |
+
- Resolution: 1.0 megapixels
|
90 |
+
- Cropped: False
|
91 |
+
- Crop style: None
|
92 |
+
- Crop aspect: None
|
93 |
+
### guys
|
94 |
+
- Repeats: 0
|
95 |
+
- Total number of images: 312
|
96 |
+
- Total number of aspect buckets: 2
|
97 |
+
- Resolution: 1.0 megapixels
|
98 |
+
- Cropped: False
|
99 |
+
- Crop style: None
|
100 |
+
- Crop aspect: None
|
101 |
+
### pixel-art
|
102 |
+
- Repeats: 0
|
103 |
+
- Total number of images: 1248
|
104 |
+
- Total number of aspect buckets: 17
|
105 |
+
- Resolution: 0.5 megapixels
|
106 |
+
- Cropped: False
|
107 |
+
- Crop style: None
|
108 |
+
- Crop aspect: None
|
109 |
+
### signs
|
110 |
+
- Repeats: 0
|
111 |
+
- Total number of images: 624
|
112 |
+
- Total number of aspect buckets: 16
|
113 |
+
- Resolution: 0.5 megapixels
|
114 |
+
- Cropped: False
|
115 |
+
- Crop style: None
|
116 |
+
- Crop aspect: None
|
117 |
+
### moviecollection
|
118 |
+
- Repeats: 0
|
119 |
+
- Total number of images: 1784
|
120 |
+
- Total number of aspect buckets: 22
|
121 |
+
- Resolution: 1.0 megapixels
|
122 |
+
- Cropped: False
|
123 |
+
- Crop style: None
|
124 |
+
- Crop aspect: None
|
125 |
+
### bookcovers
|
126 |
+
- Repeats: 0
|
127 |
+
- Total number of images: 728
|
128 |
+
- Total number of aspect buckets: 12
|
129 |
+
- Resolution: 1.0 megapixels
|
130 |
+
- Cropped: False
|
131 |
+
- Crop style: None
|
132 |
+
- Crop aspect: None
|
133 |
+
### nijijourney
|
134 |
+
- Repeats: 0
|
135 |
+
- Total number of images: 576
|
136 |
+
- Total number of aspect buckets: 18
|
137 |
+
- Resolution: 1.0 megapixels
|
138 |
+
- Cropped: False
|
139 |
+
- Crop style: None
|
140 |
+
- Crop aspect: None
|
141 |
### experimental
|
142 |
- Repeats: 0
|
143 |
- Total number of images: 2970
|
144 |
+
- Total number of aspect buckets: 16
|
145 |
- Resolution: 1.0 megapixels
|
146 |
- Cropped: False
|
147 |
- Crop style: None
|
|
|
149 |
### ethnic
|
150 |
- Repeats: 0
|
151 |
- Total number of images: 3009
|
152 |
+
- Total number of aspect buckets: 18
|
153 |
- Resolution: 1.0 megapixels
|
154 |
- Cropped: False
|
155 |
- Crop style: None
|
|
|
173 |
### architecture
|
174 |
- Repeats: 0
|
175 |
- Total number of images: 4258
|
176 |
+
- Total number of aspect buckets: 18
|
177 |
- Resolution: 1.0 megapixels
|
178 |
- Cropped: False
|
179 |
- Crop style: None
|
|
|
205 |
### anatomy
|
206 |
- Repeats: 5
|
207 |
- Total number of images: 16329
|
208 |
+
- Total number of aspect buckets: 22
|
209 |
- Resolution: 1.0 megapixels
|
210 |
- Cropped: False
|
211 |
- Crop style: None
|
|
|
229 |
### photo-aesthetics
|
230 |
- Repeats: 0
|
231 |
- Total number of images: 33031
|
232 |
+
- Total number of aspect buckets: 25
|
233 |
- Resolution: 1.0 megapixels
|
234 |
- Cropped: False
|
235 |
- Crop style: None
|
optimizer.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15406336826
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c32bcd235c178bb8aef7d3c15bbd258750178e954b7a32a1e413b23f1d776040
|
3 |
size 15406336826
|
random_states_0.pkl
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14344
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:06ab63b051f35e84408c4a49406233d1f46ae878708af6cecc183f3cdb6db411
|
3 |
size 14344
|
training_state-anatomy.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:89fc46dafd34d49c94d32360edaddbc435b4fd479394aaa5fe96dc8769d1fc6a
|
3 |
+
size 2435108
|
training_state-architecture.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ee179e10824a120b6076c06c29c5794f31f8de03974f789874496efe71b3e11
|
3 |
+
size 300955
|
training_state-bg20k-1024.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d2151ffedc0e72e276e99e725f7801b12a5340d413b31984adcd0f3fa565665
|
3 |
+
size 15158291
|
training_state-bookcovers.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:91c8dcd86d566088c671912dca66e8cb352c66c718a9b24d5aaa4b2387631c7f
|
3 |
+
size 18725
|
training_state-celebrities.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39a16a17793b665e782bf82091908f248418c7dedf71e669de072101aa72ac0d
|
3 |
+
size 32102
|
training_state-cinemamix-1mp.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b53aad32977802a3f8b6d00911a3631a04c6832a25ab11248b7ea2728118d4ea
|
3 |
+
size 1509904
|
training_state-ethnic.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bf591d9afb0ee4b097ddd5a959c3f72fc60122be6a8d13546db0c0b580af3ed7
|
3 |
+
size 1058202
|
training_state-experimental.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:612f91052594082f33d44915ccde4ec2c779eb144f39574685a5100bc058747a
|
3 |
+
size 583234
|
training_state-guys.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c08baf3d87e0db66e37de3bae0543823578e7b7e47c0783eadc0052882a3e52
|
3 |
+
size 10980
|
training_state-moviecollection.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce67ac92f8d9a82fff9748bc2854756fc0e89e757e847bc445284f328ff300db
|
3 |
+
size 39953
|
training_state-movieposters.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b5f541882174dcbea6cdbd0f13b43ce0501ede673d6fc5fb3e506120c78012d5
|
3 |
+
size 36519
|
training_state-nijijourney.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4aed65cd0909fd2981abf59e770fce8e691a497c5ff124fe1eafdda180ed7a9
|
3 |
+
size 14397
|
training_state-normalnudes.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da6bbfa1e23548974a2f89db62ce5d07293e98e1ee51c64f2e24ab6f0b9e153d
|
3 |
+
size 22582
|
training_state-nsfw-1024.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb5e5a577a43fe83a032bd33152242faf7d29edd40ef7e94af1787b413e8f0b1
|
3 |
+
size 908683
|
training_state-photo-aesthetics.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e253d2fc53f9708b068894b0c92985a9eccc4a619660699ed64b41dc5ce51548
|
3 |
+
size 5047312
|
training_state-photo-concept-bucket.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:07855f4900617b59ede6c5bdae343e6e43ff7880ef95f5d9f4bf3ed6cfbea906
|
3 |
+
size 15233207
|
training_state-pixel-art.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4de286b9840b4c5ffcc6cb3ababd4ebf3db50d13a8beb71e1107f25602e5cd92
|
3 |
+
size 28349
|
training_state-propagandaposters.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69e9a0019ffcfdf33c7d551459062e3bfa8080fab7ad7a67338fc532512c9596
|
3 |
+
size 14181
|
training_state-shutterstock.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c0506d7466da09d0afac7c4012451adade4c058b936bc5efebf8eae901728c49
|
3 |
+
size 5105262
|
training_state-signs.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08dafa5deefd3cb9644dddddec161f870708652209f8ed682113b224b70054f0
|
3 |
+
size 15690
|
training_state-text-1mp.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6145d145c2ea7156cbeecd7a283972f29c966c1dca90f02b258ce59e6b897e22
|
3 |
+
size 2042807
|
training_state-yoga.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:230ba3c56349293722c0422808e35596682479d91c68c3895f38265b934ae750
|
3 |
+
size 914403
|
training_state.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 130
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c56024dcc404364c6321d8ed9ba7cb1de7d691ea30592cf516c6523ba76bc6d0
|
3 |
size 130
|
unet/config.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1837
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d754e51d0062bdd794c3a5d4d9729db4e2861ae5e662fcfebffddedf82990a7e
|
3 |
size 1837
|
unet/diffusion_pytorch_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5135151440
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:213035e86713beb8f098ffd9f17696cbc369e5952892c5db42340468c6982106
|
3 |
size 5135151440
|