PseudoTerminal X
commited on
Trained for 1 epochs and 35250 steps.
Browse filesTrained with datasets ['text-embeds-sd2x', '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']
Learning rate 4e-07, batch size 4, 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: stabilityai/stable-diffusion-2-1
VAE: None
- README.md +9 -9
- optimizer.bin +1 -1
- random_states_0.pkl +1 -1
- scheduler.bin +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 +2 -2
- 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-gay.json +2 -2
- training_state-guys.json +1 -1
- training_state-moviecollection.json +2 -2
- training_state-movieposters.json +2 -2
- training_state-nijijourney.json +1 -1
- training_state-normalnudes.json +1 -1
- training_state-nsfw-1024.json +2 -2
- training_state-pixel-art.json +1 -1
- training_state-propagandaposters.json +1 -1
- training_state-shutterstock.json +2 -2
- training_state-signs.json +1 -1
- training_state-sports.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
@@ -28,7 +28,7 @@ a cinematic scene from the film Rogue One, a woman stares off into the distance,
|
|
28 |
- Steps: `30`
|
29 |
- Sampler: `euler`
|
30 |
- Seed: `420420420`
|
31 |
-
- Resolutions: `
|
32 |
|
33 |
Note: The validation settings are not necessarily the same as the [training settings](#training-settings).
|
34 |
|
@@ -44,7 +44,7 @@ You may reuse the base model text encoder for inference.
|
|
44 |
## Training settings
|
45 |
|
46 |
- Training epochs: 1
|
47 |
-
- Training steps:
|
48 |
- Learning rate: 4e-07
|
49 |
- Effective batch size: 4
|
50 |
- Micro-batch size: 4
|
@@ -60,7 +60,7 @@ You may reuse the base model text encoder for inference.
|
|
60 |
|
61 |
### celebrities
|
62 |
- Repeats: 0
|
63 |
-
- Total number of images:
|
64 |
- Total number of aspect buckets: 3
|
65 |
- Resolution: 1.0 megapixels
|
66 |
- Cropped: True
|
@@ -68,7 +68,7 @@ You may reuse the base model text encoder for inference.
|
|
68 |
- Crop aspect: random
|
69 |
### movieposters
|
70 |
- Repeats: 0
|
71 |
-
- Total number of images:
|
72 |
- Total number of aspect buckets: 3
|
73 |
- Resolution: 1.0 megapixels
|
74 |
- Cropped: True
|
@@ -116,7 +116,7 @@ You may reuse the base model text encoder for inference.
|
|
116 |
- Crop aspect: random
|
117 |
### moviecollection
|
118 |
- Repeats: 0
|
119 |
-
- Total number of images:
|
120 |
- Total number of aspect buckets: 3
|
121 |
- Resolution: 1.0 megapixels
|
122 |
- Cropped: True
|
@@ -124,7 +124,7 @@ You may reuse the base model text encoder for inference.
|
|
124 |
- Crop aspect: random
|
125 |
### bookcovers
|
126 |
- Repeats: 0
|
127 |
-
- Total number of images:
|
128 |
- Total number of aspect buckets: 3
|
129 |
- Resolution: 1.0 megapixels
|
130 |
- Cropped: True
|
@@ -164,7 +164,7 @@ You may reuse the base model text encoder for inference.
|
|
164 |
- Crop aspect: random
|
165 |
### gay
|
166 |
- Repeats: 0
|
167 |
-
- Total number of images:
|
168 |
- Total number of aspect buckets: 3
|
169 |
- Resolution: 1.0 megapixels
|
170 |
- Cropped: True
|
@@ -204,7 +204,7 @@ You may reuse the base model text encoder for inference.
|
|
204 |
- Crop aspect: random
|
205 |
### anatomy
|
206 |
- Repeats: 5
|
207 |
-
- Total number of images:
|
208 |
- Total number of aspect buckets: 3
|
209 |
- Resolution: 1.0 megapixels
|
210 |
- Cropped: True
|
@@ -212,7 +212,7 @@ You may reuse the base model text encoder for inference.
|
|
212 |
- Crop aspect: random
|
213 |
### bg20k-1024
|
214 |
- Repeats: 0
|
215 |
-
- Total number of images:
|
216 |
- Total number of aspect buckets: 3
|
217 |
- Resolution: 1.0 megapixels
|
218 |
- Cropped: True
|
|
|
28 |
- Steps: `30`
|
29 |
- Sampler: `euler`
|
30 |
- Seed: `420420420`
|
31 |
+
- Resolutions: `1024x1024,1152x960,896x1152`
|
32 |
|
33 |
Note: The validation settings are not necessarily the same as the [training settings](#training-settings).
|
34 |
|
|
|
44 |
## Training settings
|
45 |
|
46 |
- Training epochs: 1
|
47 |
+
- Training steps: 35250
|
48 |
- Learning rate: 4e-07
|
49 |
- Effective batch size: 4
|
50 |
- Micro-batch size: 4
|
|
|
60 |
|
61 |
### celebrities
|
62 |
- Repeats: 0
|
63 |
+
- Total number of images: 1240
|
64 |
- Total number of aspect buckets: 3
|
65 |
- Resolution: 1.0 megapixels
|
66 |
- Cropped: True
|
|
|
68 |
- Crop aspect: random
|
69 |
### movieposters
|
70 |
- Repeats: 0
|
71 |
+
- Total number of images: 1736
|
72 |
- Total number of aspect buckets: 3
|
73 |
- Resolution: 1.0 megapixels
|
74 |
- Cropped: True
|
|
|
116 |
- Crop aspect: random
|
117 |
### moviecollection
|
118 |
- Repeats: 0
|
119 |
+
- Total number of images: 1912
|
120 |
- Total number of aspect buckets: 3
|
121 |
- Resolution: 1.0 megapixels
|
122 |
- Cropped: True
|
|
|
124 |
- Crop aspect: random
|
125 |
### bookcovers
|
126 |
- Repeats: 0
|
127 |
+
- Total number of images: 812
|
128 |
- Total number of aspect buckets: 3
|
129 |
- Resolution: 1.0 megapixels
|
130 |
- Cropped: True
|
|
|
164 |
- Crop aspect: random
|
165 |
### gay
|
166 |
- Repeats: 0
|
167 |
+
- Total number of images: 1104
|
168 |
- Total number of aspect buckets: 3
|
169 |
- Resolution: 1.0 megapixels
|
170 |
- Cropped: True
|
|
|
204 |
- Crop aspect: random
|
205 |
### anatomy
|
206 |
- Repeats: 5
|
207 |
+
- Total number of images: 16424
|
208 |
- Total number of aspect buckets: 3
|
209 |
- Resolution: 1.0 megapixels
|
210 |
- Cropped: True
|
|
|
212 |
- Crop aspect: random
|
213 |
### bg20k-1024
|
214 |
- Repeats: 0
|
215 |
+
- Total number of images: 89301
|
216 |
- Total number of aspect buckets: 3
|
217 |
- Resolution: 1.0 megapixels
|
218 |
- Cropped: True
|
optimizer.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5196082660
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:13c00753b06127b27902f52efb8f99e7ad0f1c8af757d0e4fa4759470c4a4c78
|
3 |
size 5196082660
|
random_states_0.pkl
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14408
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38c38f9252930d347181bc229ec0c539e81aadc21a6045cb7c73cd0e3231a6af
|
3 |
size 14408
|
scheduler.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1000
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d9c38f423266a7828e85f94e967999ccf4b3bcb49e4ebe2cbbcf503e08133fa9
|
3 |
size 1000
|
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 sha256:60c0acb47e60673d1de6ed127f19d1c2bcf64582a951f250bab857f2bd729c8b
|
3 |
+
size 2204677
|
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:d3ec480f575b0ef148a585ae31a72bc7db63adf42eb8e735ab055ca27df94459
|
3 |
+
size 217874
|
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 sha256:543f91f808e12884dfee0128ff8e196e14d2da8db4811f168b62a999ae1bd676
|
3 |
+
size 23049704
|
training_state-bookcovers.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:c5f4dbd2426cceb5711ff99965684da3b368d9696ff3d5570187f42ee552eb34
|
3 |
+
size 17305
|
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 sha256:3d07fe15041bcf8bd0f01c7705da26818d35535ae71dc089c48b5f0cf86ea3db
|
3 |
+
size 26312
|
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 sha256:357293c5b1c392789e23ed6963cf22eff3e61eab231005a434875294c2725dfe
|
3 |
+
size 1082692
|
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 sha256:96c66df278a40048c5911b03c2457a902dfa7af3260e30a33d8e874848f1d7d3
|
3 |
+
size 724000
|
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:bd370c5cd05bd965624512b2c2d0cef2f0122075f9de392f13af74c9da7db18d
|
3 |
+
size 376726
|
training_state-gay.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:bebe3e5cd6dab69c4d9b6282ac77ed11489b80394e2c9a61180afcfb3130e38b
|
3 |
+
size 216648
|
training_state-guys.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 8349
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f013c0ae4df7bb3b54b514402ed7849754dd5e2b3aa3c2079f604f535177092d
|
3 |
size 8349
|
training_state-moviecollection.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 sha256:4b05df9f512c5865f7592085047fb3117e69714e2038f754c06359ea4aaee956
|
3 |
+
size 40361
|
training_state-movieposters.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 sha256:0f1c1f2b7541fb541609f03cb774f3872f6a16699487c1186bcafa0f353533af
|
3 |
+
size 36756
|
training_state-nijijourney.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 13994
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf85c50dd0a7e03b699f15736cfd29d434db9e0043cbd46954836e608416d411
|
3 |
size 13994
|
training_state-normalnudes.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 23721
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:802544bfe80b5f24096fad69245e7d851d80e78ded905a078691cc475fddc674
|
3 |
size 23721
|
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:dd205f9623ab68f4445f37399791784ffd5c9dbe1ceff21ea7bbf862583c6dca
|
3 |
+
size 785499
|
training_state-pixel-art.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 22514
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b4fea37c092f69d9b5af1f78954a3b17929e91cd17315cb189370722bbc217f
|
3 |
size 22514
|
training_state-propagandaposters.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 13994
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf85c50dd0a7e03b699f15736cfd29d434db9e0043cbd46954836e608416d411
|
3 |
size 13994
|
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 sha256:460567be99b2c88bdafc4536f70abe27d985532ab30dc243f608af36f97763d0
|
3 |
+
size 4433120
|
training_state-signs.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 8517
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1cb90471b19fe5da2bef1229830017c8adddc87b343f281f131df5e192afcd17
|
3 |
size 8517
|
training_state-sports.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 sha256:3439919a5f30cf732368ad303f55d4e45252090a9b2c9604d3aa67a7ea7240dc
|
3 |
+
size 143022
|
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 sha256:40057d3799542992145cb36d1c623a93e52c7671ae7291d027fc8149148bfa47
|
3 |
+
size 652375
|
training_state.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 679
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e282f43a27155da79246543361b0e346e0191804407d12868dce9fec97fe822c
|
3 |
size 679
|
unet/config.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1878
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a518104276d6a778f9e3661c7af0b2d913fbc8bc59e30074d434c7fb39925838
|
3 |
size 1878
|
unet/diffusion_pytorch_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1731905416
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0753268c98477492b87704eecb3b62110763cd31f9e4e6fa02e73cf283e93cf2
|
3 |
size 1731905416
|