Trained for 4 epochs and 6000 steps.

Trained with datasets ['text-embeds-pixart-nofilter', 'photo-concept-bucket']
Learning rate 1e-06, batch size 32, and 2 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: PixArt-alpha/PixArt-Sigma-XL-2-1024-MS
VAE: madebyollin/sdxl-vae-fp16-fix

README.md

@@ -1006,7 +1006,7 @@ You may reuse the base model text encoder for inference.
 ## Training settings
 
 - Training epochs: 4
-- Training steps: 5500
+- Training steps: 6000
 - Learning rate: 1e-06
 - Effective batch size: 512
   - Micro-batch size: 32

optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf4ec21d442bb85461467ac52de2b4a65fda8fd8acc9ae87c77fe0bd880ddafc
+oid sha256:a83e6455cf1a121fafa5b1faa7e91b73e579fd401d6b48526e2a3751e4944f81
 size 3665677155

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfd0c7a7b81f87f1866bf49f48b788d38c4b202d5ec2e9b5f4c81dfd9cefe36e
-size 16100
+oid sha256:5e73b98a3d8ee2b7aef6d6cbe2d379d46b97de0c9f5b49ed1704eb1188741134
+size 16164

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8455dbf5b441fa4ecbf748064df8779303204e3a230a7228ca16030675e12075
+oid sha256:86f0f5ea0af7792b9e1932da1418b5468c1b1a5e968b535e8064fba4c7d22ae0
 size 1000

training_state-photo-concept-bucket.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61641d895a4535c9f20dd0971a87e290fb5bf5eb054a58551703846261580866
-size 6035795
+oid sha256:59fc46d0e1b9e5493bbea60e19b076514a515e9fd7d2d8a274ffb796c86025e1
+size 8231528

training_state.json

@@ -1 +1 @@
-{"global_step": 5500, "epoch_step": 391, "epoch": 5, "exhausted_backends": [], "repeats": {"photo-concept-bucket": 0}}
+{"global_step": 6000, "epoch_step": 891, "epoch": 5, "exhausted_backends": [], "repeats": {"photo-concept-bucket": 0}}

transformer/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4005e5da302326631c2a860d03b01f1b93c2211ea71ed366759d2f7388483a87
+oid sha256:78f2fce43f92ad022686e50a761a7260d48cfe6b2528b6da6a87b5b9533e5d84
 size 1221780352