Trained for 4 epochs and 4500 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: 3
-- Training steps: 4000
+- Training epochs: 4
+- Training steps: 4500
 - 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 sha256:664ac8c09727af6e47e0611142340885e5f7256fab2f23b9f396ab042cf09466
+oid sha256:b96c1bae6a72652b186900eb03a6c287247fa11b7920cbac12544db8c89b2b51
 size 3665677155

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f61b896f3567a25eafb77371015f5cdac5af1d6c3642962ce5679c570d9273a
+oid sha256:fdbfb805eec536b56b3b633b4742408ff8c2748f070c32b0fe972233a252109f
 size 14344

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bc35c4fe64ca9260b42737f3bc4ae4d5e5918cfc8a4ac4e18fe27fe53d3195a
+oid sha256:0844688ae0af661e554629f561715f5b75edd370a4ce4234c64f4e7eeb14ac9b
 size 1000

training_state-mj-v6.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2c338fd8ace1ded0ed2cc1f95f2b27eb29f8a307b6594b6ae5faaa6bb65931a
-size 16553059
+oid sha256:6459816f33e8bc79116695a87a5a239f195f9789f321032d4b12140f778d72d2
+size 10801251

training_state.json

@@ -1 +1 @@
-{"global_step": 4000, "epoch_step": 605, "epoch": 4, "exhausted_backends": [], "repeats": {"mj-v6": 0}}
+{"global_step": 4500, "epoch_step": 57, "epoch": 5, "exhausted_backends": [], "repeats": {"mj-v6": 0}}

transformer/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9aa3365d24b5219374f6160de6aa245b84b9c8c4b1691f52e71ed9b2eb3de1d0
+oid sha256:273e100c970b8b1c9e08c2547028c3d0865005dd6f988715bbaf11931ca1c080
 size 1221780352