Trained for 5 epochs and 6000 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: 5
-- Training steps: 5500
+- Training steps: 6000
 - 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 sha256:083ced81d053298275b56202c9e468c054311eaf5c0de4ecd8c2fbe4948b09a9
+oid sha256:7d08e47990ad6d508f45b88b2496e7daaa7eea82b76f11ee99c0195ca99b173b
 size 3665677155

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0fddde73d47b8aafd98e3c6c125faf1eea661799c7eacbb92771d93d8ee006a
-size 14280
+oid sha256:ac2a70f0fdae2c02ec3f30c675b1515bdf570ab1a00bf1ec8c7bc7a539601cd8
+size 14344

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbec9aff97e801a07f80ddafe16983f4f0ad6cbed9817c950ad8294236d1685d
+oid sha256:6416ba923469ed00c6a8a8d7f3f7db82be2a54e984ce3bb746f1dc05eefbf06f
 size 1000

training_state-mj-v6.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60b5b681d9bef75b790f5743c5fe332600a5777e22bfefaaa77e2611a2e364cd
-size 10297443
+oid sha256:6da246c84235d608989a130620df4cba7ac97a6179b6737ce64d9bc400fbd3e2
+size 15545443

training_state.json

@@ -1 +1 @@
-{"global_step": 5500, "epoch_step": 9, "epoch": 6, "exhausted_backends": [], "repeats": {"mj-v6": 0}}
+{"global_step": 6000, "epoch_step": 509, "epoch": 6, "exhausted_backends": [], "repeats": {"mj-v6": 0}}

transformer/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:388dd63045347e4c7f9d1a967b8278c958ea468811be170f5552d3bdd5b94bdb
+oid sha256:aca8751233ed7cdaf6516c28ad68998f3e6c0ecd68f34af305a4e139367580d2
 size 1221780352