PseudoTerminal X commited on
Commit
846e82a
1 Parent(s): 3c484e2

Trained for 0 epochs and 6500 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

.gitattributes CHANGED
@@ -226,3 +226,4 @@ training_state-photo-concept-bucket.json filter=lfs diff=lfs merge=lfs -text
226
  assets/image_173_2.png filter=lfs diff=lfs merge=lfs -text
227
  assets/image_190_1.png filter=lfs diff=lfs merge=lfs -text
228
  assets/image_86_2.png filter=lfs diff=lfs merge=lfs -text
 
 
226
  assets/image_173_2.png filter=lfs diff=lfs merge=lfs -text
227
  assets/image_190_1.png filter=lfs diff=lfs merge=lfs -text
228
  assets/image_86_2.png filter=lfs diff=lfs merge=lfs -text
229
+ training_state-dalle3.json filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -77,7 +77,7 @@ You may reuse the base model text encoder for inference.
77
  ## Training settings
78
 
79
  - Training epochs: 0
80
- - Training steps: 6000
81
  - Learning rate: 1e-06
82
  - Effective batch size: 192
83
  - Micro-batch size: 24
@@ -167,7 +167,7 @@ You may reuse the base model text encoder for inference.
167
  ### anatomy
168
  - Repeats: 5
169
  - Total number of images: ~15168
170
- - Total number of aspect buckets: 3
171
  - Resolution: 1.0 megapixels
172
  - Cropped: True
173
  - Crop style: random
@@ -247,7 +247,7 @@ You may reuse the base model text encoder for inference.
247
  ### sfwbooru
248
  - Repeats: 0
249
  - Total number of images: ~423552
250
- - Total number of aspect buckets: 25
251
  - Resolution: 1.0 megapixels
252
  - Cropped: False
253
  - Crop style: None
@@ -255,7 +255,7 @@ You may reuse the base model text encoder for inference.
255
  ### nijijourney-v6-520k-raw
256
  - Repeats: 0
257
  - Total number of images: ~670976
258
- - Total number of aspect buckets: 9
259
  - Resolution: 1.0 megapixels
260
  - Cropped: False
261
  - Crop style: None
 
77
  ## Training settings
78
 
79
  - Training epochs: 0
80
+ - Training steps: 6500
81
  - Learning rate: 1e-06
82
  - Effective batch size: 192
83
  - Micro-batch size: 24
 
167
  ### anatomy
168
  - Repeats: 5
169
  - Total number of images: ~15168
170
+ - Total number of aspect buckets: 2
171
  - Resolution: 1.0 megapixels
172
  - Cropped: True
173
  - Crop style: random
 
247
  ### sfwbooru
248
  - Repeats: 0
249
  - Total number of images: ~423552
250
+ - Total number of aspect buckets: 22
251
  - Resolution: 1.0 megapixels
252
  - Cropped: False
253
  - Crop style: None
 
255
  ### nijijourney-v6-520k-raw
256
  - Repeats: 0
257
  - Total number of images: ~670976
258
+ - Total number of aspect buckets: 8
259
  - Resolution: 1.0 megapixels
260
  - Cropped: False
261
  - Crop style: None
optimizer.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:628f076f19a3e7d4a4802a5550c04db94e8e406729a29176d4e340749e82039f
3
  size 5451415117
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcff4c17312d745b136c8190f9727d3fc2c2edd25ee230c282d74cec68b3e4e1
3
  size 5451415117
random_states_0.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed8c07b13bbaf98c98e6f43a5e88e51be1853d173e9127e879ba372ee4eed54b
3
  size 16036
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02d96097f72f30354fa85e73245707b2e4359c7a4eb6cee9b2ff3a53a7722036
3
  size 16036
scheduler.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa90d1596151fc982c9df01c65a1b9accaa596352fb73dd2d76f53176687cc0d
3
  size 1000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2857172e458093a6b00728a13ba73b13ad03ca2bba97709c461c686e18e69d52
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
The diff for this file is too large to render. See raw diff
 
training_state-midjourney-v6-520k-raw.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_state-nijijourney-v6-520k-raw.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_state-photo-concept-bucket.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cfc8fd93b0098850c4aeb5709e40838c5588c8b2e2bf75ccfc0e2552a2af1c01
3
- size 6317385
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f81049a4be735eff10f1cf3f2c65602186f3f40a32a7744c5b8e5cecb67f1b3c
3
+ size 6454827
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": 6000, "epoch_step": 1, "epoch": 1, "exhausted_backends": ["signs", "nijijourney", "pixel-art", "propagandaposters", "sports", "gay", "experimental", "yoga", "ethnic", "cinemamix-1mp", "architecture", "mj-60", "normalnudes", "bookcovers", "celebrities", "movieposters", "shutterstock", "nsfw-1024", "photo-aesthetics", "moviecollection", "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": 13, "shutterstock": 0, "nsfw-1024": 0, "photo-aesthetics": 0, "anatomy": 5, "bg20k-1024": 0}}
 
1
+ {"global_step": 6500, "epoch_step": 1, "epoch": 1, "exhausted_backends": ["signs", "nijijourney", "pixel-art", "propagandaposters", "sports", "gay", "experimental", "yoga", "ethnic", "cinemamix-1mp", "architecture", "mj-60", "normalnudes", "bookcovers", "celebrities", "movieposters", "shutterstock", "nsfw-1024", "photo-aesthetics", "moviecollection", "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": 14, "shutterstock": 0, "nsfw-1024": 0, "photo-aesthetics": 0, "anatomy": 5, "bg20k-1024": 0}}
transformer/diffusion_pytorch_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:adfcfa6afa55315cd426029676bda667d7bf44d2a2ef92eeb58f27437eee187e
3
  size 1816969728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34b5f18a661013502c57468cb3ad67ed59955081630f044bf5dfd6b566007d41
3
  size 1816969728