Trained for 0 epochs and 19500 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: 19000
+- Training steps: 19500
 - Learning rate: 1e-06
 - Effective batch size: 192
   - Micro-batch size: 24
@@ -238,8 +238,8 @@ You may reuse the base model text encoder for inference.
 - Crop aspect: square
 ### midjourney-v6-520k-raw
 - Repeats: 0
-- Total number of images: ~671104
-- Total number of aspect buckets: 1
+- Total number of images: ~513792
+- Total number of aspect buckets: 58
 - Resolution: 1.0 megapixels
 - Cropped: False
 - Crop style: None

optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50ba649d3de29393eebb6caa66dadecca8b6c257991a497e6a8b535fa11f82c9
+oid sha256:e7b56ba82dd211c8f4551b1cbec8901f6057e353ef470aebcc6d5b971abe69c5
 size 5451415117

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64d962742857fea87f6787b4a329b98603d433a0dc816a90ce3270cd0cf23f60
+oid sha256:c770b7b4e86ebc6b94b45201b429e3335d39e67d637d5c7936066e1387257e44
 size 16036

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:620514fe21717dc1201a2c8cbfc67e5580f267d3247cfb3420b1c1ba04e65099
+oid sha256:6d29c11b9621e4d2c79b1f8e5443b6bfe6fac302e83e618e899aab7f32b4bc92
 size 1000

training_state-dalle3.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6bbba34c95d9157d9cdb69b2fa7a5e09d93d8896d90032c9613fb9eaeac1804
-size 14408402
+oid sha256:a4e9706647de1d863eb8dc24c1bb83b1295c70c40b67713c82eda72aa06d6aca
+size 14595472

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a61277cb8b834c065ce19e6d5d8ca37ea2b36673feed6b66775029b0efb362d
-size 13653367
+oid sha256:278429c4f1368ba9f5b097bbdbf5ca2211176195b9c6bd12b9980bfb153c6869
+size 6230947

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03ebe5c2ae7ff755c691889bf59763c5ffef6a123893a001d8c1b598c0d66e71
-size 14543499
+oid sha256:9af1c5e19e052fe7b0ff2ccd9c27daaac8ebea923359505e3a0aa1eb39f10a1c
+size 14810139

training_state-photo-concept-bucket.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6575368d029d95c873e157b70f3124203641bb0264716fe2c9aabd4d9bb19d70
-size 10913032
+oid sha256:7083a901993af9252e6514de92e5279624be9819c18627f10bfbd58858610715
+size 11114379

training_state.json

@@ -1 +1 @@
-{"global_step": 19000, "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": 48, "shutterstock": 0, "nsfw-1024": 0, "photo-aesthetics": 0, "anatomy": 0, "bg20k-1024": 0, "sfwbooru": 0}}
+{"global_step": 19500, "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", "midjourney-v6-520k-raw"], "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": 49, "shutterstock": 0, "nsfw-1024": 0, "photo-aesthetics": 0, "anatomy": 0, "bg20k-1024": 0, "sfwbooru": 0, "midjourney-v6-520k-raw": 0}}

transformer/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a6ceeed3ae182149c26730c5bd9290fb7857a1cd7fb8149fbeb3a8e37390e32
+oid sha256:151c9389f63999b5b84207129a7fa685babc3f65bd32e049801483a148835758
 size 1816969728