Trained for 1 epochs and 45500 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

Files changed (9) hide show

README.md +2 -2
optimizer.bin +1 -1
random_states_0.pkl +2 -2
scheduler.bin +1 -1
training_state-dalle3.json +2 -2
training_state-photo-concept-bucket.json +2 -2
training_state-text-1mp.json +0 -0
training_state.json +1 -1
transformer/diffusion_pytorch_model.safetensors +1 -1

README.md CHANGED Viewed

@@ -62,7 +62,7 @@ You may reuse the base model text encoder for inference.
 ## Training settings
 - Training epochs: 1
-- Training steps: 45000
 - Learning rate: 1e-06
 - Effective batch size: 192
   - Micro-batch size: 24
@@ -80,7 +80,7 @@ You may reuse the base model text encoder for inference.
 ### photo-concept-bucket
 - Repeats: 0
 - Total number of images: ~564672
-- Total number of aspect buckets: 1
 - Resolution: 1.0 megapixels
 - Cropped: False
 - Crop style: None

 ## Training settings
 - Training epochs: 1
+- Training steps: 45500
 - Learning rate: 1e-06
 - Effective batch size: 192
   - Micro-batch size: 24
 ### photo-concept-bucket
 - Repeats: 0
 - Total number of images: ~564672
+- Total number of aspect buckets: 34
 - Resolution: 1.0 megapixels
 - Cropped: False
 - Crop style: None

optimizer.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d66f6a040a8a3a8250832f8d0ee9b558f46a3df0cf0761917126cbb7c8d1132
 size 5451415117

 version https://git-lfs.github.com/spec/v1
+oid sha256:1672d99f6f8abdfb51a94a5d68427bf038ab7686a0abb13a98425bf6445d369e
 size 5451415117

random_states_0.pkl CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:561bae90639b30db20bbee9b2175fa6cee59aa6ea2ff9a6b24575fc84920947e
-size 16100

 version https://git-lfs.github.com/spec/v1
+oid sha256:830b4a91122d65939d4c9ea37e73b31416b0587f10baf578661fe035c4dcd3df
+size 16036

scheduler.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d17c2497bd4b3197e88a4f72a943a970d937f13770477be5699e9e8dd989b4f5
 size 1000

 version https://git-lfs.github.com/spec/v1
+oid sha256:b81905139f429d647ca94bde4741aa67f6625047691fdf2e27bec479a6b5fa0d
 size 1000

training_state-dalle3.json CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52cd5b9cc7a9fc3178f8f7bff7f4fbdf6c04767d5c79c6b47225a8cb4b517485
-size 13940122

 version https://git-lfs.github.com/spec/v1
+oid sha256:33a5de3e5da5595675c72445f9da16cc918769726531f1f3eb88152a5b33c37b
+size 14339727

training_state-photo-concept-bucket.json CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7305525bdf101511fbf6a954d01fe1edd521540b6405715a9c176acee495f697
-size 10910988

 version https://git-lfs.github.com/spec/v1
+oid sha256:43754a53ad5e32dd0ac0aaa27f580e4997c8ba37ea528e20be5ad14bec99c237
+size 5270264

training_state-text-1mp.json CHANGED Viewed

The diff for this file is too large to render. See raw diff

training_state.json CHANGED Viewed

@@ -1 +1 @@

- {"global_step": ~~45000~~, "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", "nijijourney-v6-520k-raw", "midjourney-v6-520k-raw"], "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": 44, "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": 45500, "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", "nijijourney-v6-520k-raw", "midjourney-v6-520k-raw", "photo-concept-bucket"], "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": 47, "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 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcd446207dafbafc007c6afe8d73688c622df10637a253ca443e38205b76aac3
 size 1816969728

 version https://git-lfs.github.com/spec/v1
+oid sha256:3295fd1c7b375ca54cc2357124c3d5fc2b198a3eeac5fb8569c15c1e134ec8e8
 size 1816969728