PseudoTerminal X commited on
Commit
bae33b9
·
verified ·
1 Parent(s): 370e037

Trained for 1 epochs and 32500 steps.

Browse files

Trained with datasets ['text-embeds-pixart-filter', 'photo-concept-bucket', 'moviecollection', 'experimental', 'ethnic', 'sports', 'architecture', 'shutterstock', 'cinemamix-1mp', 'nsfw-1024', 'anatomy', 'bg20k-1024', 'yoga', 'photo-aesthetics', 'text-1mp', 'movieposters', 'normalnudes', 'pixel-art', 'signs', 'midjourney-v6-520k-raw', 'sfwbooru', 'nijijourney-v6-520k-raw', 'dalle3']
Learning rate 1e-06, batch size 24, and 1 gradient accumulation steps.
Used DDPM noise scheduler for training with epsilon prediction type and rescaled_betas_zero_snr=False
Using 'linspace' timestep spacing.
Base model: ptx0/pixart-900m-1024-ft-large
VAE: madebyollin/sdxl-vae-fp16-fix

README.md CHANGED
@@ -62,7 +62,7 @@ You may reuse the base model text encoder for inference.
62
  ## Training settings
63
 
64
  - Training epochs: 1
65
- - Training steps: 32000
66
  - Learning rate: 1e-06
67
  - Effective batch size: 192
68
  - Micro-batch size: 24
@@ -152,7 +152,7 @@ You may reuse the base model text encoder for inference.
152
  ### anatomy
153
  - Repeats: 5
154
  - Total number of images: ~15168
155
- - Total number of aspect buckets: 3
156
  - Resolution: 1.0 megapixels
157
  - Cropped: True
158
  - Crop style: random
@@ -184,7 +184,7 @@ You may reuse the base model text encoder for inference.
184
  ### text-1mp
185
  - Repeats: 125
186
  - Total number of images: ~12864
187
- - Total number of aspect buckets: 3
188
  - Resolution: 1.0 megapixels
189
  - Cropped: True
190
  - Crop style: random
@@ -232,7 +232,7 @@ You may reuse the base model text encoder for inference.
232
  ### sfwbooru
233
  - Repeats: 0
234
  - Total number of images: ~271488
235
- - Total number of aspect buckets: 19
236
  - Resolution: 1.0 megapixels
237
  - Cropped: False
238
  - Crop style: None
@@ -240,7 +240,7 @@ You may reuse the base model text encoder for inference.
240
  ### nijijourney-v6-520k-raw
241
  - Repeats: 0
242
  - Total number of images: ~516288
243
- - Total number of aspect buckets: 7
244
  - Resolution: 1.0 megapixels
245
  - Cropped: False
246
  - Crop style: None
@@ -248,7 +248,7 @@ You may reuse the base model text encoder for inference.
248
  ### dalle3
249
  - Repeats: 0
250
  - Total number of images: ~1119168
251
- - Total number of aspect buckets: 2
252
  - Resolution: 1.0 megapixels
253
  - Cropped: False
254
  - Crop style: None
 
62
  ## Training settings
63
 
64
  - Training epochs: 1
65
+ - Training steps: 32500
66
  - Learning rate: 1e-06
67
  - Effective batch size: 192
68
  - Micro-batch size: 24
 
152
  ### anatomy
153
  - Repeats: 5
154
  - Total number of images: ~15168
155
+ - Total number of aspect buckets: 2
156
  - Resolution: 1.0 megapixels
157
  - Cropped: True
158
  - Crop style: random
 
184
  ### text-1mp
185
  - Repeats: 125
186
  - Total number of images: ~12864
187
+ - Total number of aspect buckets: 2
188
  - Resolution: 1.0 megapixels
189
  - Cropped: True
190
  - Crop style: random
 
232
  ### sfwbooru
233
  - Repeats: 0
234
  - Total number of images: ~271488
235
+ - Total number of aspect buckets: 17
236
  - Resolution: 1.0 megapixels
237
  - Cropped: False
238
  - Crop style: None
 
240
  ### nijijourney-v6-520k-raw
241
  - Repeats: 0
242
  - Total number of images: ~516288
243
+ - Total number of aspect buckets: 5
244
  - Resolution: 1.0 megapixels
245
  - Cropped: False
246
  - Crop style: None
 
248
  ### dalle3
249
  - Repeats: 0
250
  - Total number of images: ~1119168
251
+ - Total number of aspect buckets: 1
252
  - Resolution: 1.0 megapixels
253
  - Cropped: False
254
  - Crop style: None
optimizer.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b26e89cf7c5bf30683b62e3f3dbe6ae5ca374596fa0d9f32c34b9a2508fc7353
3
  size 5451415117
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f04d44d36beb990403fff076e71c0ef14390d944feb3d2816b3422c4f85bbf55
3
  size 5451415117
random_states_0.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e042327144872bf5c2eac3f3ee6caac9d6b4e8510717aec903c2d0c0b77806be
3
- size 16100
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4ae756e1e5cf59b021a3e39e22773cb53b37b9026acb7212de6ed9bd20f5487
3
+ size 16036
scheduler.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4cb70fd226b713f887d06091e6e1b1235e485cff839e044caf29c71266df6b36
3
  size 1000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b4e86989bd9547eddee325d2b5c446bb8133114d95203ed983925f9ae2190e0
3
  size 1000
training_state-anatomy.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_state-dalle3.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b056132b2d30f580155feb834cf009dc813f67df0e77b08d1cc2b88a5fae74eb
3
- size 9694482
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1eba49419fe49679ab7f55a6b17ca060cc41b138180ee9f9dc7eb7a988fec4d
3
+ size 9824892
training_state-midjourney-v6-520k-raw.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:95f96ea79085b0e1d98090be7cb0507687b5732ad96d3da567d1218ad398cc94
3
- size 7501551
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ced388f952b6cba98bc85f2d411e22a0f5a81077a15d52c40e56b81f10cf10f3
3
+ size 7709199
training_state-nijijourney-v6-520k-raw.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:041abfe0c94192dacfa7274840e44cebeeb945b4046fd64d591b7a74b1c24a10
3
- size 7964131
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd92af75241a3397ca57cad05fa05988a094ea57e8287f56b8c11e9bb6036780
3
+ size 8162131
training_state-photo-concept-bucket.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d043e6834fc6f505dcb52414deede20d21eea4a97f29aea59bae95570dc902c
3
- size 6151948
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0fc73c00f20a9c009c976bb1ffc70de13e3265bfd23b0768239e6a64876ba99
3
+ size 6299215
training_state-sfwbooru.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_state-text-1mp.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_state.json CHANGED
@@ -1 +1 @@
1
- {"global_step": 32000, "epoch_step": 1, "epoch": 2, "exhausted_backends": ["pixel-art", "signs", "sports", "ethnic", "experimental", "movieposters", "normalnudes", "yoga", "cinemamix-1mp", "architecture", "moviecollection", "shutterstock", "nsfw-1024", "photo-aesthetics", "bg20k-1024"], "repeats": {"bookcovers": 0, "signs": 0, "normalnudes": 0, "nijijourney": 0, "movieposters": 0, "celebrities": 0, "pixel-art": 0, "propagandaposters": 0, "sports": 0, "moviecollection": 0, "gay": 0, "experimental": 0, "yoga": 0, "ethnic": 0, "cinemamix-1mp": 0, "architecture": 0, "mj-60": 0, "text-1mp": 7, "shutterstock": 0, "nsfw-1024": 0, "photo-aesthetics": 0, "anatomy": 3, "bg20k-1024": 0, "sfwbooru": 0, "midjourney-v6-520k-raw": 0, "nijijourney-v6-520k-raw": 0, "photo-concept-bucket": 0, "dalle3": 0}}
 
1
+ {"global_step": 32500, "epoch_step": 1, "epoch": 2, "exhausted_backends": ["pixel-art", "signs", "sports", "ethnic", "experimental", "movieposters", "normalnudes", "yoga", "cinemamix-1mp", "architecture", "moviecollection", "shutterstock", "nsfw-1024", "photo-aesthetics", "bg20k-1024"], "repeats": {"bookcovers": 0, "signs": 0, "normalnudes": 0, "nijijourney": 0, "movieposters": 0, "celebrities": 0, "pixel-art": 0, "propagandaposters": 0, "sports": 0, "moviecollection": 0, "gay": 0, "experimental": 0, "yoga": 0, "ethnic": 0, "cinemamix-1mp": 0, "architecture": 0, "mj-60": 0, "text-1mp": 7, "shutterstock": 0, "nsfw-1024": 0, "photo-aesthetics": 0, "anatomy": 3, "bg20k-1024": 0, "sfwbooru": 0, "midjourney-v6-520k-raw": 0, "nijijourney-v6-520k-raw": 0, "photo-concept-bucket": 0, "dalle3": 0}}
transformer/diffusion_pytorch_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f43cff97a8a9b93c08334997247983eab5115d5748fc0853d814a6703723d3bd
3
  size 1816969728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0565ba8c52601e71b1730999b7ce59d46921b1b0a74bec3f93055407e83677b
3
  size 1816969728