Trained for 0 epochs and 5500 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: 5000
+- Training steps: 5500
 - Learning rate: 1e-06
 - Effective batch size: 192
   - Micro-batch size: 24
@@ -167,7 +167,7 @@ You may reuse the base model text encoder for inference.
 ### anatomy
 - Repeats: 5
 - Total number of images: ~21056
-- Total number of aspect buckets: 3
+- Total number of aspect buckets: 1
 - Resolution: 1.0 megapixels
 - Cropped: True
 - Crop style: random
@@ -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: 28
+- Total number of aspect buckets: 15
 - 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: 45
+- Total number of aspect buckets: 35
 - 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: 25
+- Total number of aspect buckets: 11
 - Resolution: 1.0 megapixels
 - Cropped: False
 - Crop style: None
@@ -263,7 +263,7 @@ You may reuse the base model text encoder for inference.
 ### dalle3
 - Repeats: 0
 - Total number of images: ~1242072
-- Total number of aspect buckets: 7
+- 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 sha256:94ae33358fbbf77fc75cb16af0e0ebfc800d5a9f2be8c77bb5d1ba464525ec3c
+oid sha256:1e9674252ce4ece4f58d923749b69f9c928be43818c0ca98efb6f3ec006138a7
 size 5451415117

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:710a01f740a88634592036a4142b4c029b9729613b04434880f110055664d70f
+oid sha256:8726f0b286825c7d70d4a5412b3defa948c273f0120759f6028918daf1308e3e
 size 16100

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6db68071d6a3fca0758715a9a86721a7db2e381ba247175f7f1d75233038ba6d
+oid sha256:4b4f24f412eb316b43c6fca6b8eb89aa2d2d44fb4b2dee7fb2dec4caaeb101c8
 size 1000

training_state-photo-concept-bucket.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6afbaff78244208782b4bbb4c1532b5920ac1d4a6c8232e15549302e8ae3281d
-size 6017342
+oid sha256:737efa0eb772e42d8c1dc7d6f75cf690bff607c33cec78f4300f868140a780b3
+size 6166382

training_state.json

@@ -1 +1 @@
-{"global_step": 5000, "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"], "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": 4, "bg20k-1024": 0}}
+{"global_step": 5500, "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"], "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": 4, "bg20k-1024": 0}}

transformer/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06752f72f4dbcea1a10b33cb1cf65184fad3372b750c6b64f65920e8b68d66cb
+oid sha256:21dae37b18a64da5a50bba5e84518ed7afff741cfb40d5aba7ad224c39dfe3ef
 size 1816969728