Hugging Face's logo

ptx0
/
pseudo-flex-v2

Text-to-Image
Diffusers
Safetensors
stable-diffusion
stable-diffusion-diffusers
full
Model card Files Community
ptx0 commited on
Commit
620ea65
•
1 Parent(s): 317f9a8

Trained for 1 epochs and 5750 steps.

Browse files

Trained 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

Files changed (16) hide show
  1. README.md +6 -6
  2. optimizer.bin +1 -1
  3. random_states_0.pkl +2 -2
  4. training_state-anatomy.json +2 -2
  5. training_state-architecture.json +2 -2
  6. training_state-bg20k-1024.json +2 -2
  7. training_state-cinemamix-1mp.json +2 -2
  8. training_state-ethnic.json +2 -2
  9. training_state-experimental.json +2 -2
  10. training_state-gay.json +2 -2
  11. training_state-moviecollection.json +2 -2
  12. training_state-nsfw-1024.json +2 -2
  13. training_state-shutterstock.json +2 -2
  14. training_state-yoga.json +2 -2
  15. training_state.json +2 -2
  16. 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: 1
47
- - Training steps: 5500
48
  - Learning rate: 4e-07
49
  - Effective batch size: 4
50
  - Micro-batch size: 4
@@ -116,7 +116,7 @@ You may reuse the base model text encoder for inference.
116
  - Crop aspect: None
117
  ### moviecollection
118
  - Repeats: 0
119
- - Total number of images: 1861
120
  - Total number of aspect buckets: 29
121
  - Resolution: 1.0 megapixels
122
  - Cropped: False
@@ -141,7 +141,7 @@ You may reuse the base model text encoder for inference.
141
  ### experimental
142
  - Repeats: 0
143
  - Total number of images: 3000
144
- - Total number of aspect buckets: 17
145
  - Resolution: 1.0 megapixels
146
  - Cropped: False
147
  - Crop style: None
@@ -173,7 +173,7 @@ You may reuse the base model text encoder for inference.
173
  ### architecture
174
  - Repeats: 0
175
  - Total number of images: 4320
176
- - Total number of aspect buckets: 21
177
  - Resolution: 1.0 megapixels
178
  - Cropped: False
179
  - Crop style: None
@@ -189,7 +189,7 @@ You may reuse the base model text encoder for inference.
189
  ### cinemamix-1mp
190
  - Repeats: 0
191
  - Total number of images: 9024
192
- - Total number of aspect buckets: 6
193
  - Resolution: 1.0 megapixels
194
  - Cropped: False
195
  - Crop style: None
@@ -205,7 +205,7 @@ You may reuse the base model text encoder for inference.
205
  ### anatomy
206
  - Repeats: 5
207
  - Total number of images: 16381
208
- - Total number of aspect buckets: 25
209
  - Resolution: 1.0 megapixels
210
  - Cropped: False
211
  - Crop style: None
 
44
  ## Training settings
45
 
46
  - Training epochs: 1
47
+ - Training steps: 5750
48
  - Learning rate: 4e-07
49
  - Effective batch size: 4
50
  - Micro-batch size: 4
 
116
  - Crop aspect: None
117
  ### moviecollection
118
  - Repeats: 0
119
+ - Total number of images: 1856
120
  - Total number of aspect buckets: 29
121
  - Resolution: 1.0 megapixels
122
  - Cropped: False
 
141
  ### experimental
142
  - Repeats: 0
143
  - Total number of images: 3000
144
+ - Total number of aspect buckets: 16
145
  - Resolution: 1.0 megapixels
146
  - Cropped: False
147
  - Crop style: None
 
173
  ### architecture
174
  - Repeats: 0
175
  - Total number of images: 4320
176
+ - Total number of aspect buckets: 20
177
  - Resolution: 1.0 megapixels
178
  - Cropped: False
179
  - Crop style: None
 
189
  ### cinemamix-1mp
190
  - Repeats: 0
191
  - Total number of images: 9024
192
+ - Total number of aspect buckets: 5
193
  - Resolution: 1.0 megapixels
194
  - Cropped: False
195
  - Crop style: None
 
205
  ### anatomy
206
  - Repeats: 5
207
  - Total number of images: 16381
208
+ - Total number of aspect buckets: 24
209
  - Resolution: 1.0 megapixels
210
  - Cropped: False
211
  - Crop style: None
optimizer.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6896a4fd8f513878f60992c4e4b6bb2f974095794633316be6306cc37b78c39e
3
  size 5196082660
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f46eb4c95d6a85e5dc18dec0d8ec7385d0021f14968d1821242c72504967da2
3
  size 5196082660
random_states_0.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c3ce3387429a78dfbed6daa721a3794977edbc138f27ca1a01b18260fbcab7d8
3
- size 14408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adff84220313660f59fafcac029bddc6419efc85f71974bccd0b1cf53e135634
3
+ size 14344
training_state-anatomy.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:64ec3f13525b7181d504a6da9f0c67949c2ca896f7cf0004b91f56bd35e04ec5
3
- size 2325477
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:700e81b82fbdd00179e244bb8ce2435e0868135ce4627a2d9f0030564905f8c7
3
+ size 2338088
training_state-architecture.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b99d384693304464e1c0704fd8636345a796fc0467e767849bee146fb8c75324
3
- size 271901
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d61f50fb49450193b68dbe732d112603702127340cffd30a31b1bc1a60068a54
3
+ size 275248
training_state-bg20k-1024.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:431912791f964839ca3c6506a524d400e1e063a7cacd5665839b47aead0903db
3
- size 14891923
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afce56608d9b65b55d71523c5a34086361e2971e2a5d06e32fb1a947dbed1450
3
+ size 14913074
training_state-cinemamix-1mp.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:18cf585ea446365ee379d89e3c897d9ec816cd5be0a61b4fdd9c667e7f4d6f5b
3
- size 1308303
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6878505ff4d4d9514eb5d041200cc8f6bd62442bf6e67f180a9a93b2b073651
3
+ size 1322534
training_state-ethnic.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc41f537b7d8737b96f566e040e9340086974b6487fc73b1a13f6f44a6eda6df
3
- size 928788
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:654edc0e13b4f498c6bf2d08828349d43858932801f6fda1cff39f28d6bf7032
3
+ size 942442
training_state-experimental.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc2c0334be829d2fa3c2a60554a8a93815c2176e8caf6a573985747bbfa9425b
3
- size 486568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13ecb08faf5a71abd380d5464a6be1785b0f3954bd75669c0dcedb96fe3b3f87
3
+ size 501261
training_state-gay.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:269238decb5473316aaef4fe16aa0a4c2c5b9cf7471528ab81f3669e42598883
3
- size 378413
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8b6dd3a6fe9ede0b278882073553e540df34c7cc53bca9947d9b25871c769eb
3
+ size 393665
training_state-moviecollection.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1463d8dfc13c2b4fcda286f4dae8b4b5a48e7baed148485d714f2fea2441814c
3
- size 87167
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bb2a9c84789d7a31319e2f2c0f44bf53e3d78a63fdebd5269c842f8cd08e0c5
3
+ size 39645
training_state-nsfw-1024.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:211012e5c78c0ebdce84bcc40dcc330dc839ed730b8dd064d8e7565b6173038a
3
- size 851173
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43addcbab1b5460ad37178c460421e3c5b4ecab9dabce06f457734468c548bf0
3
+ size 856168
training_state-shutterstock.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c9cc24730438e834d1ae4ad0a09116a5af98db0efedf0f33af86ad20b865e77
3
- size 4781023
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d878a87b56e8ebcbc4e6339a602ffc781683c623b4488553265e48c0301250c
3
+ size 4810421
training_state-yoga.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b824cdd2061230b1eef757642d3b98a99732b3678d835c659ad5a72fe3b428c
3
- size 784169
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23a7f0e2fdd7375ddc9cfdfc52ae483292ba1404f2f2222bd0e4dc5be6ae4c3e
3
+ size 797608
training_state.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:720680f84265fbd7f77c55c2d1c2cc108a03ef9d8e7ac6bd749bc357be800211
3
- size 392
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a1c9f66956f9af40e88f62072b7e33b988d0ac680038d1110ec5d0d071bb342
3
+ size 433
unet/diffusion_pytorch_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a55bd3d7076e7d9e15ffe782e579cd0a8be27ddf4f246518acd74e4c05cb385c
3
  size 1731905416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3fe5a7698eefd91f290d20b15cfb5b7fdb62b6aaa3336d3528818e2e8dae091
3
  size 1731905416