Trained for 7 epochs and 16800 steps.

Trained with datasets ['text-embeds-sdxl-nofilter', 'photo-concept-bucket']
Learning rate 4e-07, batch size 32, and 2 gradient accumulation steps.
Used DDPM noise scheduler for training with v_prediction prediction type and rescaled_betas_zero_snr=True
Using 'trailing' timestep spacing.
Base model: ptx0/terminus-xl-velocity-v2
VAE: madebyollin/sdxl-vae-fp16-fix

README.md

@@ -44,7 +44,7 @@ You may reuse the base model text encoder for inference.
 ## Training settings
 
 - Training epochs: 7
-- Training steps: 16600
+- Training steps: 16800
 - Learning rate: 4e-07
 - Effective batch size: 512
   - Micro-batch size: 32

optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cbdd15fc1d119bb277575b1ac080450abe6e6f1348c3a7a2dc0ddce69aeb2fc
+oid sha256:676e1f3f9758e633ca43d6f1e17e2bb57c66fde1762619626488a34ef96f0e95
 size 15406336826

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cba7bce59f5cdde5f7f3e0b9fe4d1b024bc7f882a8b7718620d66b1d0010a54
-size 16036
+oid sha256:2ca33088538dfcc10bdc9385f7e8ec7d4e380cee21582390f974c1089d6a20aa
+size 16100

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e043ed7855242c79e9c3b9afb9e52aa38ef8e4f54696146eed842077d5d1fab9
+oid sha256:d4d58469dc0ad5aa83fbe7f08aa14b9656c083cc9bbd302712a150c19ddd6291
 size 1000

training_state-photo-concept-bucket.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1ac163105a4a0363bdbd2a4454072e26c87682a0d56cd8135eac80ba042666c
-size 6415951
+oid sha256:c5b518ba591c5ea76d77795e53c3a9f32ea5e6a66c3d862ff33a2761e2e2b9cb
+size 7294762

training_state.json

@@ -1 +1 @@
-{"global_step": 16600, "epoch_step": 433, "epoch": 8, "exhausted_backends": [], "repeats": {"celebrities": 0, "pixel-art": 0, "movieposters": 0, "moviecollection": 0, "training-test": 0, "dalle3": 0, "photo-concept-bucket": 0}}
+{"global_step": 16800, "epoch_step": 633, "epoch": 8, "exhausted_backends": [], "repeats": {"celebrities": 0, "pixel-art": 0, "movieposters": 0, "moviecollection": 0, "training-test": 0, "dalle3": 0, "photo-concept-bucket": 0}}

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:339e3dcc563c848dee911300643327280984da3cfd1305b50cd41d93b4c19be2
+oid sha256:d279fbc6b7b82b223c784337bdfd90afd351592d703d9c7a1607d3b781b927a2
 size 5135151440