Trained for 3 epochs and 3500 steps.

Trained with datasets ['text-embeds', 'mj-v6']
Learning rate 8e-06, batch size 32, and 4 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

@@ -210,8 +210,8 @@ You may reuse the base model text encoder for inference.
 
 ## Training settings
 
-- Training epochs: 2
-- Training steps: 3000
+- Training epochs: 3
+- Training steps: 3500
 - Learning rate: 8e-06
 - Effective batch size: 128
   - Micro-batch size: 32

optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6be48cc782677f2354537d6e0bfb7df6313e20da4a8b3b79c06b4120059c4dcf
+oid sha256:fdf25c6b3ce5e1782dcf79482e60e9412dc65d57fcdd527d093a2089e1266a1e
 size 3665677155

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7646cf26f263c7e311caf3d24424b072c2429f5ccf2c99d81f00af80f7de9052
-size 14344
+oid sha256:b5a357d361469b4f14e9f83db727fc543c6ad6f92c8d7b5b8788569c90812278
+size 14280

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4beec63126998040f00cefceadff78db11f493a3f2cc333822a34fdde9434243
+oid sha256:32c5484f657772c0e4b8347102a4bff0865f0eb2e4699a6081b826ee611a35f0
 size 1000

training_state-mj-v6.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d16ab9d843c7ba0452f9553bd9da0aa833cdd0aaacf4e1388cf3d882bf835d9
-size 17056867
+oid sha256:ac9790ec78672ee24757746842ddc5c1e67845dc9bf6840bfae7ae80133b2bf0
+size 11305059

training_state.json

@@ -1 +1 @@
-{"global_step": 3000, "epoch_step": 653, "epoch": 3, "exhausted_backends": [], "repeats": {"mj-v6": 0}}
+{"global_step": 3500, "epoch_step": 105, "epoch": 4, "exhausted_backends": [], "repeats": {"mj-v6": 0}}

transformer/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f2b3e2b0c02ab64e27cd0accada200e0af2e16cc0dfe94c9577dce408b852ff
+oid sha256:7b588665bcd6770db3571f10d1a611fcc326bd1882c1a6e9255a07594b1eb7a1
 size 1221780352