Trained for 0 epochs and 11500 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

.gitattributes

@@ -227,3 +227,4 @@ assets/image_173_2.png filter=lfs diff=lfs merge=lfs -text
 assets/image_190_1.png filter=lfs diff=lfs merge=lfs -text
 assets/image_86_2.png filter=lfs diff=lfs merge=lfs -text
 training_state-dalle3.json filter=lfs diff=lfs merge=lfs -text
+training_state-nijijourney-v6-520k-raw.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -77,7 +77,7 @@ You may reuse the base model text encoder for inference.
 ## Training settings
 
 - Training epochs: 0
-- Training steps: 10500
+- Training steps: 11500
 - Learning rate: 1e-06
 - Effective batch size: 192
   - Micro-batch size: 24
@@ -239,7 +239,7 @@ You may reuse the base model text encoder for inference.
 ### midjourney-v6-520k-raw
 - Repeats: 0
 - Total number of images: ~671104
-- Total number of aspect buckets: 4
+- Total number of aspect buckets: 2
 - Resolution: 1.0 megapixels
 - Cropped: False
 - Crop style: None
@@ -255,7 +255,7 @@ You may reuse the base model text encoder for inference.
 ### nijijourney-v6-520k-raw
 - Repeats: 0
 - Total number of images: ~670976
-- 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:ea3e043dbde26e119155dac829c1a9faf3e2ee6f9e7d1987d6d4b2eaf4ab5771
+oid sha256:e34bd6b1f0ad360a4e64ef84b1e395e66153caa402cf97f8fd3cbd0182e1cb79
 size 5451415117

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e9115327c37c2d869128ff3c510e478e337919cf27399c8c3e9c5995a07cd0d
+oid sha256:ab72ccdbac782f51d0bb647f5334c951879bc523e3593bec20e97458f8438601
 size 16100

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5fc9084ba1cb32889ec2c18cd863242c0de390f9228bd73c5a1722bc76b9cb7
+oid sha256:73ce7cf35830ccfbdd3263602f24ca7d30369fad63895589732d389cb293467e
 size 1000

training_state-dalle3.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:665ac4cef86d970737190724c632a471a55f1be678aa6d263014427446869058
-size 11736372
+oid sha256:49da03982825c68af6de05717f21d34059a43ca0635074107f12cc36e10130d9
+size 11979691

training_state-photo-concept-bucket.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fabfa3d59c1d20504757073195d56622e40e3c21538b7a3ac84b4ac22a77271
-size 7744014
+oid sha256:ab0a8fea763459a9ad2ca7f884ba3beaaf70a5a3402806057b5e2cee2810426c
+size 8117638

training_state.json

@@ -1 +1 @@
-{"global_step": 10500, "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"], "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": 24, "shutterstock": 0, "nsfw-1024": 0, "photo-aesthetics": 0, "anatomy": 0, "bg20k-1024": 0}}
+{"global_step": 11500, "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"], "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": 26, "shutterstock": 0, "nsfw-1024": 0, "photo-aesthetics": 0, "anatomy": 0, "bg20k-1024": 0}}

transformer/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ded5384b2b0141e12a012c69dc7503cddb23d673ed4faaea4a5c0c6261db45ce
+oid sha256:9fa482bb0fddd8743a7fb83eac7a50968718bf8516074419ebf91b8f66e3e029
 size 1816969728