Trained for 1 epochs and 37000 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: 36500
+- Training steps: 37000
 - 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: 3
+- Total number of aspect buckets: 2
 - Resolution: 1.0 megapixels
 - Cropped: False
 - Crop style: None

optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99ee1a96defb643fbdbea455632d6dd94ddac3d515e6afa1af88ef3ceb8a1883
+oid sha256:10679517ba0c9f06d0e330a1e68e53f561c8c7a9741191a0a26f70f3a14192f8
 size 5451415117

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:482be5e19b31f172160e8aeaac61f213e702ed27bf177415f6b4694c3417acd7
-size 16100
+oid sha256:e849c3fd5212d656e68b75fd57891e11c7baa3193c95518ad40c05344315de68
+size 16036

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c661fcdee20037d519c92c9fff453c9c50b8eab6819bee6a140b94fd0509d116
+oid sha256:e772a2163519612718c931d5ba9a5886d433c6c0109733ee68e094c30f142ef4
 size 1000

training_state-dalle3.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a6baa90e15b6f9f058268bb05dd6c6be281f0b72f62fce993397f3946e4351a
-size 10883736
+oid sha256:bf258618b9453c586b2845ad14a8ed6ac10b40fe27fdf93d48f09e3cbb4d5364
+size 11032697

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6eeaeaa33404c9f95e760abb3743277f48d280420a32a4b26429c3321615cad
-size 9365439
+oid sha256:23efbbcfdf00299a2b7dfa74167bdcb4c813b6abf07db211d3e7ea7f91b3f35f
+size 9528591

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73bd1aa3e8f6dbf8b58a255591bd2473c465f491b5e929d0d4671eada02ca14e
-size 9857011
+oid sha256:8819b5ffcf69ebf56314c2d38b8d50d83968e7ffd9ddabf0ab56d1b2c4256b0c
+size 10089331

training_state-photo-concept-bucket.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3502bff8d4d03ccd4cd9b4a94bc66539c598f544101ee047a08061b54affa9f3
-size 7534642
+oid sha256:8134e500b6f50825c6b20bb82ace6ee6d67cb66e2bc3f811e8245537d0378d45
+size 7710725

training_state.json

@@ -1 +1 @@
-{"global_step": 36500, "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": 16, "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": 37000, "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": 18, "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 sha256:570bd5ce1e1bf8c8f65f1466f5513d1e30b35a754f711a9eddc613ff7861e83e
+oid sha256:f7f55d15a557d86dc4f460edbc9ab6410640ffbd2bb33311672130133b235f0b
 size 1816969728