Trained for 4 epochs and 5000 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

@@ -211,7 +211,7 @@ You may reuse the base model text encoder for inference.
 ## Training settings
 
 - Training epochs: 4
-- Training steps: 4500
+- Training steps: 5000
 - 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:b96c1bae6a72652b186900eb03a6c287247fa11b7920cbac12544db8c89b2b51
+oid sha256:6b408c484f29623d82441f52f58f2d45b9c225c2d747b330624aad2474df1520
 size 3665677155

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdbfb805eec536b56b3b633b4742408ff8c2748f070c32b0fe972233a252109f
+oid sha256:86ae4043f57450c7708f7daf759c419c4397cd95df061dc1b051de557a991eec
 size 14344

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0844688ae0af661e554629f561715f5b75edd370a4ce4234c64f4e7eeb14ac9b
+oid sha256:08d2b1d2ff87fc142d6b57325846dcb28ce085536f556fb63ed5e84f3e0ddc37
 size 1000

training_state-mj-v6.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6459816f33e8bc79116695a87a5a239f195f9789f321032d4b12140f778d72d2
-size 10801251
+oid sha256:3cef1b05385597e3baa55f8913fca926efa04a3b3c3d356f85f3ee49877635e8
+size 16049251

training_state.json

@@ -1 +1 @@
-{"global_step": 4500, "epoch_step": 57, "epoch": 5, "exhausted_backends": [], "repeats": {"mj-v6": 0}}
+{"global_step": 5000, "epoch_step": 557, "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 sha256:273e100c970b8b1c9e08c2547028c3d0865005dd6f988715bbaf11931ca1c080
+oid sha256:046425dd53749c2893bc16e71223ece74b59d2e1fcfe475c5063c31753c33fd5
 size 1221780352