Trained for 11 epochs and 21500 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

@@ -1004,7 +1004,7 @@ You may reuse the base model text encoder for inference.
 ## Training settings
 
 - Training epochs: 11
-- Training steps: 21000
+- Training steps: 21500
 - 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:fd590832cc09684a8c5a7749401f4ca621332e3e7e06ce7f4bbaab623e79e1d4
+oid sha256:9269b461109ef875f9201423373abf5366ae7898119f48fb4f58ac35c88a5a00
 size 15406336826

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33ef35c6fa731c152e9ff2d6e9fcd9c05a572b78e4a6eb69431212b57ebc1631
-size 16036
+oid sha256:31fb9a3ddf6f02ff12c558049bb102f6b4b19626b37778aaad7ce75bf475ad32
+size 16100

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a970460c3c0d0d0aa98587e2c7f79975be39d2f4cdb3fd97c2d4f915250a787
+oid sha256:6c9d5f0c4c36123e26bfc796b2b3afbe59ff19f0778dd20cc62003172c85400f
 size 1000

training_state-photo-concept-bucket.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b07656cb91009e058d16836d13494256d93098c4c96a84adfba13881af404f9
-size 6609279
+oid sha256:6900c71e0e653f68bd8a23116a2c310412fba855fb45542312737895f78661bc
+size 8806671

training_state.json

@@ -1 +1 @@
-{"global_step": 21000, "epoch_step": 510, "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": 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}}

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22104e39d3f4ce9fb0990e35a23cde5875ba34d18d7eba04f2784da0a1db6ecf
+oid sha256:284417e66fc42d6bb040becf3922029f2c7e71b3e16915fea91f4d799e408240
 size 5135151440