Trained for 1 epochs and 29500 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: 29000
+- Training steps: 29500
 - 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: 19
+- Total number of aspect buckets: 13
 - Resolution: 1.0 megapixels
 - Cropped: False
 - Crop style: None
@@ -176,7 +176,7 @@ You may reuse the base model text encoder for inference.
 ### photo-aesthetics
 - Repeats: 0
 - Total number of images: ~28608
-- Total number of aspect buckets: 2
+- Total number of aspect buckets: 17
 - 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: 23
+- Total number of aspect buckets: 15
 - 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: 39
+- Total number of aspect buckets: 35
 - Resolution: 1.0 megapixels
 - Cropped: False
 - Crop style: None
@@ -240,7 +240,7 @@ You may reuse the base model text encoder for inference.
 ### nijijourney-v6-520k-raw
 - Repeats: 0
 - Total number of images: ~516288
-- Total number of aspect buckets: 20
+- Total number of aspect buckets: 11
 - Resolution: 1.0 megapixels
 - Cropped: False
 - Crop style: None
@@ -248,7 +248,7 @@ You may reuse the base model text encoder for inference.
 ### dalle3
 - Repeats: 0
 - Total number of images: ~1119168
-- Total number of aspect buckets: 8
+- Total number of aspect buckets: 3
 - Resolution: 1.0 megapixels
 - Cropped: False
 - Crop style: None

optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b5c2830cc97acd304d4492fa73d2822ea53afb351b4bed0a98989d48d92059a
+oid sha256:ae0eb6b041a0028b3a24d48874d631286d19e8b33e968ed0643a9b4659d2dd51
 size 5451415117

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e57acd91d4349c0165387a5728e319d246817450d0cf39862279371281aa8d1
+oid sha256:360f68542b7351a488cde608cb684f61ba4d5fe6a08f52fa2651ae63d26f2604
 size 16100

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:612a0e6300b750e80d0128bc030c2183392f4eccffbbdbd0e39e50c74d82ab17
+oid sha256:b1a9b5b20185dcbb5340513578a6ce11f5f1d73ebc0940e7fb0827717d4e77b4
 size 1000

training_state-dalle3.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:957f50ae20363a3be06bf9b35bdabdb4e1475503e2bab521346a54770de6d42d
-size 8965147
+oid sha256:73319ac6942a41bd35538d940e32414caf4afcc958bc6755ab2c031db7e2b1f4
+size 9073645

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cd960852a4edc1b73d081e380475b373f8bd8d72bf04ae308e7447533d9dbf8
-size 6468255
+oid sha256:82e5d11c71fa63ce38b568d6f1c2056f3ba4236e9547b631c35576169e7eb1f7
+size 6623991

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b7d8bd01164530786ee44825ca235adeebff215fca603a1814a5f5d24f01b0b
-size 6942451
+oid sha256:66ee4d1c0ce8716bc3e907d2072ff1ad8a33017cf3625622343f92242a24e88a
+size 7119331

training_state-photo-concept-bucket.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edb15cbe7259517a600254a4424eb866df40f6629cbf58a87d2cb11abdb822c8
-size 5442772
+oid sha256:b1878fde59c5028a4d28030c43b7c04a4f7d1ba9d099779a8c408f47afc80932
+size 5541572

training_state.json

@@ -1 +1 @@
-{"global_step": 29000, "epoch_step": 1, "epoch": 2, "exhausted_backends": ["pixel-art", "signs", "sports", "ethnic", "experimental", "movieposters", "normalnudes", "yoga", "cinemamix-1mp", "architecture", "moviecollection", "shutterstock"], "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": 1, "shutterstock": 0, "nsfw-1024": 0, "photo-aesthetics": 0, "anatomy": 0, "bg20k-1024": 0, "sfwbooru": 0, "midjourney-v6-520k-raw": 0, "nijijourney-v6-520k-raw": 0, "photo-concept-bucket": 0, "dalle3": 0}}
+{"global_step": 29500, "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": 2, "shutterstock": 0, "nsfw-1024": 0, "photo-aesthetics": 0, "anatomy": 1, "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:ecb6ca837f0f97edae96e95c56d12543444d5b4143601e2096ee203385a8cbdc
+oid sha256:d7d059800121590ddd35a4824a1a6734045ebd62667a773eef9ae94a8f0e6b0a
 size 1816969728