Trained for 1 epochs and 34500 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: 34000
+- Training steps: 34500
 - 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: 5
+- Total number of aspect buckets: 4
 - 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: 13
+- Total number of aspect buckets: 9
 - Resolution: 1.0 megapixels
 - Cropped: False
 - Crop style: None

optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50b3d45bd029df0ade2c6c33bbcd22228f7963db0eee71a203b0ba08820b1132
+oid sha256:f687eeaf935cdc59542dbe6055d5b7db2fb0991e320cb4e38e3f8d0eefdea6a2
 size 5451415117

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02dcc3508692cdcb0dfce21c08530c616dfe1405f5700bfe3b88b0cc9915ac98
-size 16036
+oid sha256:14194aa4acad3ed40905837a242ad97bd7ab32d0a012e0d6018ce9ab7a955fd8
+size 16100

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfca25df8324541ee71f939b94cd9eec33004cf0d01f8cb6e29c8e907e0be0f8
+oid sha256:0034e017275c221ecd11edb6edcd7b25247e38c9ef37110ad0b805bb8be314b7
 size 1000

training_state-dalle3.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4483a05d2b406ace7a9325613070be3c7749371e3141982fbc798badabcded6
-size 10196383
+oid sha256:fa80fc388b49db53b38e0c499ab2b5d5e02fe8d352f1903291c40d40ae4b3ba6
+size 10327184

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8d756024349a5285cf3d4a166abe98fe79c6524a87006531345295b72efd960
-size 8322255
+oid sha256:92efb7e8dc9d61ff74585e9ff3b48e74f6f89c41339cb0c141a5ea14cdbb152f
+size 8537319

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c5abe6d517ef692abe6b559911eb793398a427ace2055e920e5cef287569ebf
-size 8779891
+oid sha256:77c2155c9fd0f0ba4254c77197870fe2f369e2d8476029800cf5c0c81bec1f8c
+size 8985811

training_state-photo-concept-bucket.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d311f4cfe599fd1659caf63c0d8de90aa22c4227e2e549d7124f354d059f1d1
-size 6766125
+oid sha256:cb90d320fd126021e00c337be91fc4ef4c2c2210728dc004e65cd474f8d3571b
+size 6930713

training_state.json

@@ -1 +1 @@
-{"global_step": 34000, "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"], "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": 11, "shutterstock": 0, "nsfw-1024": 0, "photo-aesthetics": 0, "anatomy": 5, "bg20k-1024": 0, "sfwbooru": 0, "midjourney-v6-520k-raw": 0, "nijijourney-v6-520k-raw": 0, "photo-concept-bucket": 0, "dalle3": 0}}
+{"global_step": 34500, "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"], "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": 12, "shutterstock": 0, "nsfw-1024": 0, "photo-aesthetics": 0, "anatomy": 5, "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 sha256:6fcc29c31b1a5fff2bf5fb68a868caa098c962a4b5d423d2ce99344339d265c3
+oid sha256:de41e493e14186d332e98bf30de94bd8bd79f620644945a3ec8c7e0e0a28b1d9
 size 1816969728