Trained for 0 epochs and 10500 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

@@ -77,7 +77,7 @@ You may reuse the base model text encoder for inference.
 ## Training settings
 
 - Training epochs: 0
-- Training steps: 10000
+- Training steps: 10500
 - 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: 5
+- Total number of aspect buckets: 4
 - Resolution: 1.0 megapixels
 - Cropped: False
 - Crop style: None
@@ -247,7 +247,7 @@ You may reuse the base model text encoder for inference.
 ### sfwbooru
 - Repeats: 0
 - Total number of images: ~423552
-- Total number of aspect buckets: 9
+- Total number of aspect buckets: 6
 - 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: 5
+- Total number of aspect buckets: 3
 - 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:dd974cc4ba54d8c387c3e6b6df3e69f29789af9522718e3531a569843b28dc13
+oid sha256:ea3e043dbde26e119155dac829c1a9faf3e2ee6f9e7d1987d6d4b2eaf4ab5771
 size 5451415117

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39ae2d0427acf40510bbff37fac8f1dab907b5320dab625b8883b39072163ec2
-size 16036
+oid sha256:3e9115327c37c2d869128ff3c510e478e337919cf27399c8c3e9c5995a07cd0d
+size 16100

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec3386c1a1e3165e95e087cc5fed219f9a936cfdaf927dc9d05a2255eb24e135
+oid sha256:e5fc9084ba1cb32889ec2c18cd863242c0de390f9228bd73c5a1722bc76b9cb7
 size 1000

training_state-dalle3.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9937cc1d2376d9f2d0926a89bc485705ec8c7d770dd933f794ba1384a9b3ea82
-size 11608750
+oid sha256:665ac4cef86d970737190724c632a471a55f1be678aa6d263014427446869058
+size 11736372

training_state-photo-concept-bucket.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3ce663d5460bf37733d096d06a82a095ae4cb4ddc6c10a78cfbeb44040b57f6
-size 7567838
+oid sha256:9fabfa3d59c1d20504757073195d56622e40e3c21538b7a3ac84b4ac22a77271
+size 7744014

training_state.json

@@ -1 +1 @@
-{"global_step": 10000, "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": 23, "shutterstock": 0, "nsfw-1024": 0, "photo-aesthetics": 0, "anatomy": 0, "bg20k-1024": 0}}
+{"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}}

transformer/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9a6ece57fd9f74e7bf4182daba10090ef0b65098328e0c154cdcd160dd9458a
+oid sha256:ded5384b2b0141e12a012c69dc7503cddb23d673ed4faaea4a5c0c6261db45ce
 size 1816969728