Trained for 0 epochs and 13500 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: 13000
+- Training steps: 13500
 - Learning rate: 1e-06
 - Effective batch size: 192
   - Micro-batch size: 24
@@ -246,8 +246,8 @@ You may reuse the base model text encoder for inference.
 - Crop aspect: None
 ### sfwbooru
 - Repeats: 0
-- Total number of images: ~423552
-- Total number of aspect buckets: 2
+- Total number of images: ~271488
+- Total number of aspect buckets: 73
 - 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:b911f913bcf165d361e6de8250b36b411620fb86efeaa7122ffcd4c080e01829
+oid sha256:caec3c74a8f2b3b775949895c54e233d47aac7d0823e97639462fd657cdb5d11
 size 5451415117

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a55d3118a8aa8fd0a4a159e0010141b96509af1a4b1a3bd06999fc34941e470e
-size 16036
+oid sha256:66c0d62badcc97a20262add5be98e768013ef7bce95243ce50dca0ec21bf0293
+size 15972

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6f8da65cee5c48fbfc575bdae9f6f54e8ba8adf0b40a831c65954e45f143edd
+oid sha256:2e2e140832ec38ad29b3c17d1cd157e00abcf4beb50417d8560201a13f0f60ac
 size 1000

training_state-dalle3.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9733dee84d2ac4d9c389e56844b4f1661609a0985fb43507dd8251340a942b57
-size 12469305
+oid sha256:b9e4082d6caed9875b441473bb0456ffed64a157180fe5aa62bad3f07a43fa66
+size 12629987

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a1f1c1f2b951ef33ffc8808126e6b70aec2950b782c3fb5d0e1d76441f8d184
-size 10649887
+oid sha256:2d36065a0bda5588f1d06e9c69847358ae00e0945d22f024e71e7d4ea8dcae6d
+size 10904503

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:240526294a21e8db8726f4c63bf25e7fb848c3178d4daf9cd67def5d17f6cbee
-size 11428299
+oid sha256:8210eb385d415076437b45ce56df4c36f561b0aee7c2c59d63555ab74eb3f5b0
+size 11652699

training_state-photo-concept-bucket.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5c8fa4ca8b1d1c8d0101de2aa22119c148f67ccfb52736484f8fc2eb22b3ef0
-size 8582269
+oid sha256:95419ecd917c80d9f11d444ca3791faadf912f949645f28a95767cc2ee4f3bde
+size 8754545

training_state.json

@@ -1 +1 @@
-{"global_step": 13000, "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": 30, "shutterstock": 0, "nsfw-1024": 0, "photo-aesthetics": 0, "anatomy": 0, "bg20k-1024": 0}}
+{"global_step": 13500, "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", "sfwbooru"], "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": 31, "shutterstock": 0, "nsfw-1024": 0, "photo-aesthetics": 0, "anatomy": 0, "bg20k-1024": 0, "sfwbooru": 0}}

transformer/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2b4fcdbf6f379a35ff4768b2e76d179205c12b0815dd26c6c3a3536c3e054ba
+oid sha256:e326372b15c8d5b0a6a43c7e1b6afa72a0978a4a8cda9d496058f2c92d9a1055
 size 1816969728