Trained for 6 epochs and 8000 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

@@ -1006,7 +1006,7 @@ You may reuse the base model text encoder for inference.
 ## Training settings
 
 - Training epochs: 6
-- Training steps: 7500
+- Training steps: 8000
 - 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: 5
+- Total number of aspect buckets: 2
 - 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:fac1c361c49492f2dfcf6ea263ae9bfda5f3f55655e9096bf52e4f9696f37dec
+oid sha256:f7afbbf2ad5c2cd853d28f2709b73c60bdf809a07ccb18aa17f0fdb08be73781
 size 3665677155

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aacc5eeb25af66e038202d2713755b60b22f92d7d45425465d179d397186e6bf
-size 16100
+oid sha256:bf4bd5a21b7f0d28f9d4045285a388e3c39a99b4d48ebaef8585d8b9d1930969
+size 16036

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98c1cf42104a81232cceef08ac43a3ccc3ce5bed5d8ab60ba0794c574561391f
+oid sha256:90131b3f456c0d9c5147b1d07474e54b5ce615e41e6a51397a55037165fa9d5a
 size 1000

training_state-photo-concept-bucket.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:242981d8ce10251c0607500f2010250fd6c9b7b3040ffed0a0916dd189a3c045
-size 5367493
+oid sha256:1008c2a2068cfc84781d22be887c27fa97d731143b31092877fc8c377af7fcf0
+size 7564176

training_state.json

@@ -1 +1 @@
-{"global_step": 7500, "epoch_step": 239, "epoch": 7, "exhausted_backends": [], "repeats": {"photo-concept-bucket": 0}}
+{"global_step": 8000, "epoch_step": 739, "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 sha256:94b9277272fa3b09c22abe2fb75c4ef2fae2f25df1e2299124c75ebb0a25b2a4
+oid sha256:416c82dd3e97cd36538f260b5e97ce748a6b5f50162936da84b3ffeab02b18c2
 size 1221780352