Trained for 1 epochs and 38000 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: 37500
+- Training steps: 38000
 - Learning rate: 1e-06
 - Effective batch size: 192
   - Micro-batch size: 24
@@ -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: 1
+- 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 sha256:7f754a41b2f44f3f69a8da87a86cfa00a7bbf45e0e6525f4cb511528b713932c
+oid sha256:37faaeffde1777258cd3d5cffefde35179de065181065652441198aeb7940b84
 size 5451415117

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0ca4e816a1635569adca5d7cb5aeb91a89754b754cc69719e116a5a788bb3a9
-size 16036
+oid sha256:b972c7fb43d33d0bfbcf70a56ca16022a7ed2bc98719a03dfb48936c41249196
+size 16100

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:547c2c8c1f6ee7a3dd109c3cc7fa08b55ec05e1b7550f677c876dbd8810ac921
+oid sha256:c1bcc063d5cbb02280b9100cf7684ba102286debcb071dea14a616dce5545114
 size 1000

training_state-dalle3.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e637dbae30c18e453a826a6a454bd2b880dd34e5f5605ccafeb8bec9808a021a
-size 11175367
+oid sha256:5291f8f536529cd852caf68b34bea5fc800d9338a0ff2906b29482195aa714ec
+size 11335045

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb67ef4a9387d71071b9b4cfbe777e2df80f97c715861a2f26b41086112a41c3
-size 9721407
+oid sha256:272340a5c8c227c25f84bde9b86db050ec4e14250c9e1520609191ab30526a31
+size 9951303

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ab95d50908ea28d91492d21d2dcdbcb01f67dbc0e39df78f8da3ea88579c6aa
-size 10308451
+oid sha256:02a5cf79466f7858fa4c66eb8351732342faa1c715f8f05f23866ab61a18c48e
+size 10585651

training_state-photo-concept-bucket.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d9187155c12e4512ab53b4abafc1ee3145df92938da25d43deabaacd9e9b3b1
-size 7873216
+oid sha256:a3e8646e34e8f7ce44362ecf64ef5330fa7c6a877598c27c5bebf8e9c43ddcb0
+size 8060888

training_state.json

@@ -1 +1 @@
-{"global_step": 37500, "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", "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": 19, "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": 38000, "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", "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": 20, "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}}

transformer/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6482b8794488daa2d72d8356e9f466770e17be15f7652540f264f17daa22d3c
+oid sha256:67f88e4d9a5a214a75f2988b4a48d7956805f91aef889042a025905584727729
 size 1816969728