Trained for 0 epochs and 12000 steps.

Trained with datasets ['text-embeds-pixart-filter', 'photo-concept-bucket', 'text-1mp', 'ideogram', '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 'trailing' timestep spacing.
Base model: terminusresearch/pixart-900m-1024-ft-v0.6
VAE: madebyollin/sdxl-vae-fp16-fix

README.md

@@ -1562,7 +1562,7 @@ You may reuse the base model text encoder for inference.
 ## Training settings
 
 - Training epochs: 0
-- Training steps: 11000
+- Training steps: 12000
 - Learning rate: 1e-06
 - Effective batch size: 192
   - Micro-batch size: 24

optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:533324d792d9365a13fd744b567e1334a736a0a8f31cd4339171a57ce2d8703e
+oid sha256:b142a2c505ec8a7fc57bd4dc6c0f06e88de4dd828c7d7b93a051d542c6c54837
 size 5451415117

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc69f757c179f348638310a9507b3d95860902ff225883a155c8530fc85ebb32
-size 16100
+oid sha256:01f6133806a13854b243058e1ae3eefa82e493d14f73bfb02559f698e25a22fc
+size 16036

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b74647d3271e63a276c245513653e7ab34576fe6e545a8c48e31dc5749d07e86
+oid sha256:4e571c799b1ecbbc67f40fb9bd00bb71e5a729ed3e1c74672dc4d36152385417
 size 1000

training_state-dalle3.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e38de8ac569dcd8ff3570be8c3f9afe2f54e635dd92ac2be7854a44a5877f13
-size 12062201
+oid sha256:d546c3498057c9084df25e8a284d1fc5b3189353b81f4521bb4c9c1ed3b77ad2
+size 12359726

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b01ce72be3d8eea5d9ab8d4ad89aefc0cd86056c345f1a24121bc98a209b92a4
-size 9325531
+oid sha256:80636c76b3f7f68d583da2d6e5d810faf5e339595d637a997170a7378c264737
+size 9708691

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7b7d1b91196b3b55948ee5b98a595c53cb73941f182dcf3b112afc580de8933
-size 10657603
+oid sha256:8e549691784a06669c4e411750c8553dfb7d7263be70b92005c983c2d85c6ffc
+size 5404005

training_state-photo-concept-bucket.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12d9e8337417c7209690617b90485fac6a00a234123dc65a9acc6b798ca99459
-size 9014989
+oid sha256:984ab02d38f5110c70455f4d095dd1e821972bbfc452944c84b07602890666ba
+size 9336293

training_state.json

@@ -1 +1 @@
-{"global_step": 11000, "epoch_step": 11000, "epoch": 1, "exhausted_backends": ["sfwbooru"], "repeats": {"ideogram": 9, "sfwbooru": 0, "text-1mp": 4}}
+{"global_step": 12000, "epoch_step": 12000, "epoch": 1, "exhausted_backends": ["sfwbooru", "nijijourney-v6-520k-raw"], "repeats": {"ideogram": 10, "sfwbooru": 0, "text-1mp": 7, "nijijourney-v6-520k-raw": 0}}

transformer/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b9c5136c14fabb1e72e66b2ee81b3cd60c49ab62e1f230d82a8a7ef05359c4e
+oid sha256:86795fb9ce67f9956fd00b37a6ee1ef2d10f4e32df7141572f68abba83eb5d93
 size 1816969728