Trained for 2 epochs and 2500 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: 1
-- Training steps: 2000
+- Training epochs: 2
+- Training steps: 2500
 - 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 sha256:709fe286305a67b23d5fda9c5222b44e830de0150e5aa11b867888d39afcad13
+oid sha256:dddf4c49ac67f35885c894ee9b3de8083fc8ac35e8cf4c6d7601a8eef0e37566
 size 3665677155

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:348f77d93153381368937426338c32f9870f95a362a50954869861a83c0ccc6e
+oid sha256:0d0499bc783fafd3db4928e67bef35014ac3904fa9c57a5eaa8cff43f2ee5273
 size 14344

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2eb1cce730426e835242d18b368f2e671b3eb662cbe1682f8619450b7c2c1bb9
+oid sha256:d394596b6a9a6eb220c4b514546efe6b5d39875b7f3c514eaa13e2af3c14e8d3
 size 1000

training_state-mj-v6.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac388b02b593d4407be82560c961ed11c58beba92b0af8980b97b6adac92038b
-size 17560675
+oid sha256:224d58c5580e8b29acfd9ebfc0692bd0417f3a75e84eb04e36f45966ac71bfaa
+size 11808867

training_state.json

@@ -1 +1 @@
-{"global_step": 2000, "epoch_step": 701, "epoch": 2, "exhausted_backends": [], "repeats": {"mj-v6": 0}}
+{"global_step": 2500, "epoch_step": 153, "epoch": 3, "exhausted_backends": [], "repeats": {"mj-v6": 0}}

transformer/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88c393cc9a95a5fc97227138567a228c231c4ff496da3d92a9a8a2c1f424624e
+oid sha256:01f153efd4afe63280b3a6812f3eb4cbbc4928db24b04396ee4d2526e301d78d
 size 1221780352