Trained for 0 epochs and 8000 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

@@ -77,7 +77,7 @@ You may reuse the base model text encoder for inference.
 ## Training settings
 
 - Training epochs: 0
-- Training steps: 7500
+- Training steps: 8000
 - Learning rate: 1e-06
 - Effective batch size: 192
   - Micro-batch size: 24
@@ -247,7 +247,7 @@ You may reuse the base model text encoder for inference.
 ### sfwbooru
 - Repeats: 0
 - Total number of images: ~423552
-- Total number of aspect buckets: 19
+- Total number of aspect buckets: 18
 - Resolution: 1.0 megapixels
 - Cropped: False
 - Crop style: None
@@ -255,7 +255,7 @@ You may reuse the base model text encoder for inference.
 ### nijijourney-v6-520k-raw
 - Repeats: 0
 - Total number of images: ~670976
-- Total number of aspect buckets: 7
+- Total number of aspect buckets: 5
 - Resolution: 1.0 megapixels
 - Cropped: False
 - Crop style: None
@@ -263,7 +263,7 @@ You may reuse the base model text encoder for inference.
 ### dalle3
 - Repeats: 0
 - Total number of images: ~1242072
-- Total number of aspect buckets: 2
+- Total number of aspect buckets: 1
 - Resolution: 1.0 megapixels
 - Cropped: False
 - Crop style: None

optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2401b666a0393b1e72b36519fd1262a643afd740ad4e90660520212a10f3d002
+oid sha256:474034d08289f1cb67f32456bebfbe6179065655125680503ed1874c6f783897
 size 5451415117

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3eb8e7f519726186ee677a404cf21e9594275bf265b288abd329086fa515f61f
+oid sha256:6c2a0221fe1d55129dd44f8733cd0216d6a8eb8122bcd91bf170f59072d6dd5a
 size 16036

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:527e4c2bb09c536660123568a9500fdbcf6bdafd4a3a1224fb94a5fa9584df2d
+oid sha256:dbd56ac68ba3b8763227c7d94f5939ee50822f12eda29b2e9914934807520f04
 size 1000

training_state-dalle3.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce8ce03c9cf1296fbda408b52efa976221d14a7dd274dd0db10c650ce5dbac1d
-size 10906881
+oid sha256:f9e13ea2b646aa7553d382dba976d29e6593f52dcb5403f4511f88aa38a7ef84
+size 11050845

training_state-photo-concept-bucket.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:942627841d63120d7881bf29808a215fef031a29d3c35c7be9332442a52b629f
-size 6822574
+oid sha256:a39f65211942f4d37c95543435fc05d557fa315bf5d568f028d01926b987adf2
+size 6979379

training_state.json

@@ -1 +1 @@
-{"global_step": 7500, "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", "anatomy"], "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": 16, "shutterstock": 0, "nsfw-1024": 0, "photo-aesthetics": 0, "anatomy": 0, "bg20k-1024": 0}}
+{"global_step": 8000, "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", "anatomy"], "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": 17, "shutterstock": 0, "nsfw-1024": 0, "photo-aesthetics": 0, "anatomy": 0, "bg20k-1024": 0}}

transformer/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6997d9da879ac3ee386d7833105cbcb9e279cc98b2fe3d15a09ae4cd48af8ff
+oid sha256:ae8d5638b24164c0dcbd42c66b6a766addb985af275aac5909b5221648f7b852
 size 1816969728