Trained for 6 epochs and 7500 steps.

Trained with datasets ['text-embeds-pixart-nofilter', 'photo-concept-bucket']
Learning rate 1e-06, batch size 32, and 2 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

@@ -1005,8 +1005,8 @@ You may reuse the base model text encoder for inference.
 
 ## Training settings
 
-- Training epochs: 5
-- Training steps: 7000
+- Training epochs: 6
+- Training steps: 7500
 - Learning rate: 1e-06
 - Effective batch size: 512
   - Micro-batch size: 32
@@ -1024,7 +1024,7 @@ You may reuse the base model text encoder for inference.
 ### photo-concept-bucket
 - Repeats: 0
 - Total number of images: ~550912
-- Total number of aspect buckets: 2
+- Total number of aspect buckets: 5
 - Resolution: 1.0 megapixels
 - Cropped: False
 - Crop style: None

optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64665e38810f1a021cb8a239de747b440369c2612a7c2d2cd320b11ecc2a1859
+oid sha256:fac1c361c49492f2dfcf6ea263ae9bfda5f3f55655e9096bf52e4f9696f37dec
 size 3665677155

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:deaefb46a10ce99a68e02f0da3f4ff8e58c251f251d214e54030b1b26cf340b1
+oid sha256:aacc5eeb25af66e038202d2713755b60b22f92d7d45425465d179d397186e6bf
 size 16100

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf279504429d3c2d2a5c21e1c623c13a2525b896fa37b0d59112adfbafdb6526
+oid sha256:98c1cf42104a81232cceef08ac43a3ccc3ce5bed5d8ab60ba0794c574561391f
 size 1000

training_state-photo-concept-bucket.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:158bf06c93adaeaaebc834fe572d619eb8d0cf04697860780b7c6b0034cab677
-size 7897798
+oid sha256:242981d8ce10251c0607500f2010250fd6c9b7b3040ffed0a0916dd189a3c045
+size 5367493

training_state.json

@@ -1 +1 @@
-{"global_step": 7000, "epoch_step": 815, "epoch": 6, "exhausted_backends": [], "repeats": {"photo-concept-bucket": 0}}
+{"global_step": 7500, "epoch_step": 239, "epoch": 7, "exhausted_backends": [], "repeats": {"photo-concept-bucket": 0}}

transformer/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35708525bec2c02bb3edb7ac3f780b74f0dbd86a7c79c6fc408ab7366990dd62
+oid sha256:94b9277272fa3b09c22abe2fb75c4ef2fae2f25df1e2299124c75ebb0a25b2a4
 size 1221780352