Trained for 0 epochs and 13000 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

@@ -228,3 +228,4 @@ 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
+training_state-midjourney-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: 12500
+- Training steps: 13000
 - Learning rate: 1e-06
 - Effective batch size: 192
   - Micro-batch size: 24
@@ -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: 3
+- 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: 2
+- Total number of aspect buckets: 1
 - 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:f9ee7a5e7f4f0eb9eabaaf35e2bd5ab5c48e081026d62235202ae5bd89118ab1
+oid sha256:b911f913bcf165d361e6de8250b36b411620fb86efeaa7122ffcd4c080e01829
 size 5451415117

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70794bb765702a7e7c79e569fc51645aedcedfff99ff80a935f8c1e04c96b7d8
-size 16100
+oid sha256:a55d3118a8aa8fd0a4a159e0010141b96509af1a4b1a3bd06999fc34941e470e
+size 16036

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:673bb12d1077420c1b7160b8d2768ebcca021b263616a0be504a3c5881097ead
+oid sha256:a6f8da65cee5c48fbfc575bdae9f6f54e8ba8adf0b40a831c65954e45f143edd
 size 1000

training_state-dalle3.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2de7f436f59174b0be85467dec52e78864dce2d4cd35927439d8c780ee28985
-size 12300798
+oid sha256:9733dee84d2ac4d9c389e56844b4f1661609a0985fb43507dd8251340a942b57
+size 12469305

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e91f82dc4bdd926db34bbb424169e5b0676902decf9e0ae721fcea101d9ab9fb
-size 11214459
+oid sha256:240526294a21e8db8726f4c63bf25e7fb848c3178d4daf9cd67def5d17f6cbee
+size 11428299

training_state-photo-concept-bucket.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6c801393280d2bd8c55c995ad51f19cdfa20c1e422e8c575f395995550535bf
-size 8437083
+oid sha256:a5c8fa4ca8b1d1c8d0101de2aa22119c148f67ccfb52736484f8fc2eb22b3ef0
+size 8582269

training_state.json

@@ -1 +1 @@
-{"global_step": 12500, "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": 29, "shutterstock": 0, "nsfw-1024": 0, "photo-aesthetics": 0, "anatomy": 0, "bg20k-1024": 0}}
+{"global_step": 13000, "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": 30, "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 sha256:908deb920c41dc9e5e77d48703880b1f018f81e7faeed5968cb30a580dd93bba
+oid sha256:e2b4fcdbf6f379a35ff4768b2e76d179205c12b0815dd26c6c3a3536c3e054ba
 size 1816969728