Trained for 1 epochs and 33000 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: 32500
+- Training steps: 33000
 - Learning rate: 1e-06
 - Effective batch size: 192
   - Micro-batch size: 24
@@ -80,7 +80,7 @@ You may reuse the base model text encoder for inference.
 ### photo-concept-bucket
 - Repeats: 0
 - Total number of images: ~564672
-- Total number of aspect buckets: 7
+- Total number of aspect buckets: 6
 - Resolution: 1.0 megapixels
 - Cropped: False
 - Crop style: None
@@ -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: 2
+- Total number of aspect buckets: 3
 - Resolution: 1.0 megapixels
 - Cropped: True
 - Crop style: random
@@ -184,7 +184,7 @@ You may reuse the base model text encoder for inference.
 ### text-1mp
 - Repeats: 125
 - Total number of images: ~12864
-- Total number of aspect buckets: 2
+- Total number of aspect buckets: 3
 - Resolution: 1.0 megapixels
 - Cropped: True
 - Crop style: random
@@ -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: 17
+- Total number of aspect buckets: 16
 - 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:f04d44d36beb990403fff076e71c0ef14390d944feb3d2816b3422c4f85bbf55
+oid sha256:8727c5da91201cd6837fe642f12b3ba6d916699354972eee2225d3fab2f520cd
 size 5451415117

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4ae756e1e5cf59b021a3e39e22773cb53b37b9026acb7212de6ed9bd20f5487
-size 16036
+oid sha256:ac6e21b55b0101de18bf9fbe42d12f3239a879eba99f5a37ab79f8c9d587a1a3
+size 16100

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b4e86989bd9547eddee325d2b5c446bb8133114d95203ed983925f9ae2190e0
+oid sha256:2691ebdf64dbb584689f1332db6ea79a42a1942721dca1e1eed8b1a44de5c706
 size 1000

training_state-dalle3.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1eba49419fe49679ab7f55a6b17ca060cc41b138180ee9f9dc7eb7a988fec4d
-size 9824892
+oid sha256:7cdd05bff9fd541fb7fcc6f1df5d6d805f6ffcbe3e57005fd70781dcf73ca39e
+size 9939151

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ced388f952b6cba98bc85f2d411e22a0f5a81077a15d52c40e56b81f10cf10f3
-size 7709199
+oid sha256:df4e2126eda414e4e78874d815d44794e363a521e2befd901fffdd152304323c
+size 7892127

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd92af75241a3397ca57cad05fa05988a094ea57e8287f56b8c11e9bb6036780
-size 8162131
+oid sha256:8347307c19310ebca0bac3108f88affabd39fa1dc00cc5ec7bf9e9d45e72b4c1
+size 8394451

training_state-photo-concept-bucket.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0fc73c00f20a9c009c976bb1ffc70de13e3265bfd23b0768239e6a64876ba99
-size 6299215
+oid sha256:7c4b3917d8c086a78b3477d0a4dbf63401a996e9c7295a395ddc106a26959637
+size 6456172

training_state.json

@@ -1 +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}}
+{"global_step": 33000, "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": 8, "shutterstock": 0, "nsfw-1024": 0, "photo-aesthetics": 0, "anatomy": 4, "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:d0565ba8c52601e71b1730999b7ce59d46921b1b0a74bec3f93055407e83677b
+oid sha256:fa7ce6d0258784297f5242dfdd931535b7f790481f2be1e87b660e0ea0dded99
 size 1816969728