Trained for 1 epochs and 31500 steps.

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

@@ -62,7 +62,7 @@ You may reuse the base model text encoder for inference.
 ## Training settings
 
 - Training epochs: 1
-- Training steps: 31000
+- Training steps: 31500
 - Learning rate: 1e-06
 - Effective batch size: 192
   - Micro-batch size: 24
@@ -152,7 +152,7 @@ You may reuse the base model text encoder for inference.
 ### anatomy
 - Repeats: 5
 - Total number of images: ~15168
-- Total number of aspect buckets: 3
+- Total number of aspect buckets: 2
 - Resolution: 1.0 megapixels
 - Cropped: True
 - Crop style: random
@@ -224,7 +224,7 @@ You may reuse the base model text encoder for inference.
 ### midjourney-v6-520k-raw
 - Repeats: 0
 - Total number of images: ~513792
-- Total number of aspect buckets: 9
+- Total number of aspect buckets: 7
 - Resolution: 1.0 megapixels
 - Cropped: False
 - Crop style: None
@@ -232,7 +232,7 @@ You may reuse the base model text encoder for inference.
 ### sfwbooru
 - Repeats: 0
 - Total number of images: ~271488
-- Total number of aspect buckets: 20
+- Total number of aspect buckets: 19
 - Resolution: 1.0 megapixels
 - Cropped: False
 - Crop style: None

optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03b9be4c2a3c8636ca491e90254b28ce779d9a47672f79f12103acd781627912
+oid sha256:6a58fd4d292f728e09b7fc8b1f13d99526fa19749b0520f0f5f2478a0108b511
 size 5451415117

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b84649c102e44f1d75bea64e89138712bad0e9795dc1664ea2867358c03c8e78
-size 16036
+oid sha256:eefb07561d681e1f10e9ddc194312a71784689f194f637383ce8b160724d190f
+size 16100

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:848fca831655e283b7d6b1850a72f4357950642db44279410f174a1c56b2a903
+oid sha256:064acec7018bfb3b53d575594c3395db946d92b017d70e3077018412027181f9
 size 1000

training_state-dalle3.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbb0d564c0f2a8aa3b256c7365f4de38ff2f5ea1fdb4276027f249cabff946de
-size 9452108
+oid sha256:c5584cad5eec26dd2cb9b9f19ac05525839b73d3d967ce57fab2a352c0052fa8
+size 9578444

training_state-midjourney-v6-520k-raw.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4b38053fe0a6ee9f6ec99bb71edf9e6d3f4e1de54c5568696dbe79ca7f00b61
-size 7130751
+oid sha256:52a6a51fd6088d3c8dd49616e420f171879330691e72aaa84cd35b6b1d4ee2c7
+size 7321095

training_state-nijijourney-v6-520k-raw.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5166f281282bcdecf5b893fb47f23d5884d670c16ba7f01cc0e94c90711c62b8
-size 7636771
+oid sha256:e1ba8579275b5be64e3432f429f6efea56ac2b1294c2c17ecb4f447d18fd5c49
+size 7795171

training_state-photo-concept-bucket.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c32bf35104a4368c07723e4d899932e7caf9067749bb72f68d7851887a04050e
-size 5911706
+oid sha256:da1873dde2801df1b3488cf372e416491f2b6e7834a5958574af25cd24710906
+size 6020196

training_state.json

@@ -1 +1 @@
-{"global_step": 31000, "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"], "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": 5, "shutterstock": 0, "nsfw-1024": 0, "photo-aesthetics": 0, "anatomy": 2, "bg20k-1024": 0, "sfwbooru": 0, "midjourney-v6-520k-raw": 0, "nijijourney-v6-520k-raw": 0, "photo-concept-bucket": 0, "dalle3": 0}}
+{"global_step": 31500, "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"], "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": 6, "shutterstock": 0, "nsfw-1024": 0, "photo-aesthetics": 0, "anatomy": 2, "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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:136147de23e23bfd8aa9fd455c9229d25c76dbdc7389447fac9ee24c44e9fc37
+oid sha256:5e13e1dcf8be431518a4ee86aa82eb258c1955c938c10bccdc4900f839868e1f
 size 1816969728