Trained for 1 epochs and 38500 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: 38000
+- Training steps: 38500
 - Learning rate: 1e-06
 - Effective batch size: 192
   - Micro-batch size: 24
@@ -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: 2
+- Total number of aspect buckets: 1
 - Resolution: 1.0 megapixels
 - Cropped: False
 - Crop style: None

optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37faaeffde1777258cd3d5cffefde35179de065181065652441198aeb7940b84
+oid sha256:42ae4e84395241c9480f483adb428e2ba52e536028584290d8d58c22dee09831
 size 5451415117

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b972c7fb43d33d0bfbcf70a56ca16022a7ed2bc98719a03dfb48936c41249196
-size 16100
+oid sha256:59f5080e3fb0c67adc2b4d3ef6b67beb4850e99a29cb911b3676455db285f7b3
+size 16036

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1bcc063d5cbb02280b9100cf7684ba102286debcb071dea14a616dce5545114
+oid sha256:0129e6fd70205caea2ef9a4e572a916f4b40b146f6e301cf04eafef49def0c5f
 size 1000

training_state-dalle3.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5291f8f536529cd852caf68b34bea5fc800d9338a0ff2906b29482195aa714ec
-size 11335045
+oid sha256:21ba0a58c3117ae0dcba546a71fb6be7bbf95968c377eaa7e2f76cbe9cc6c8a6
+size 11510959

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:272340a5c8c227c25f84bde9b86db050ec4e14250c9e1520609191ab30526a31
-size 9951303
+oid sha256:ed8e8fbae6184533dd0a05880c24d5292b313253927ec5b403292e88f21da9fa
+size 10161423

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02a5cf79466f7858fa4c66eb8351732342faa1c715f8f05f23866ab61a18c48e
-size 10585651
+oid sha256:109315caebcd416992a0d3ccf989132e6042fabde2e82c5c75dabf3081e8ec49
+size 10841731

training_state-photo-concept-bucket.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3e8646e34e8f7ce44362ecf64ef5330fa7c6a877598c27c5bebf8e9c43ddcb0
-size 8060888
+oid sha256:4ed2b039a29f6832fb26aa195ddee4bacb724c92539811a281dc3bb968165260
+size 8264006

training_state.json

@@ -1 +1 @@
-{"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}}
+{"global_step": 38500, "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": 22, "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 sha256:67f88e4d9a5a214a75f2988b4a48d7956805f91aef889042a025905584727729
+oid sha256:99d48733ae27b5485f008efaa1dfc625676bf408b353aa41a771e0c313378ae3
 size 1816969728