Trained for 12 epochs and 22000 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

@@ -1003,8 +1003,8 @@ You may reuse the base model text encoder for inference.
 
 ## Training settings
 
-- Training epochs: 11
-- Training steps: 21500
+- Training epochs: 12
+- Training steps: 22000
 - 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 sha256:9269b461109ef875f9201423373abf5366ae7898119f48fb4f58ac35c88a5a00
+oid sha256:c3576f2e8e8bd66a43a4439ed3d6ed46001d0603aee2646632224702ae2b4023
 size 15406336826

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31fb9a3ddf6f02ff12c558049bb102f6b4b19626b37778aaad7ce75bf475ad32
+oid sha256:31b25609f77e9a2b895f0971a47c63bd003b5ab22b3ddf7ca070bc64cec1d9d8
 size 16100

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c9d5f0c4c36123e26bfc796b2b3afbe59ff19f0778dd20cc62003172c85400f
+oid sha256:4e4454174ebab232fc0d463de2e9762286993a7b20c65f0bf1c7a237879eba76
 size 1000

training_state-photo-concept-bucket.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6900c71e0e653f68bd8a23116a2c310412fba855fb45542312737895f78661bc
-size 8806671
+oid sha256:f2dd7b23b5eebcf11d86f3a17cb761fe62dce45881f23f1f92c02f2b924bfb44
+size 6218169

training_state.json

@@ -1 +1 @@
-{"global_step": 21500, "epoch_step": 1010, "epoch": 12, "exhausted_backends": [], "repeats": {"celebrities": 0, "pixel-art": 0, "movieposters": 0, "moviecollection": 0, "training-test": 0, "dalle3": 0, "photo-concept-bucket": 0}}
+{"global_step": 22000, "epoch_step": 421, "epoch": 13, "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 sha256:284417e66fc42d6bb040becf3922029f2c7e71b3e16915fea91f4d799e408240
+oid sha256:0ada4a9077a3d8b41dd43564a0b1587c976453f86678242a5c7e1f8d412995ed
 size 5135151440