Trained for 1 epochs and 9800 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

@@ -43,8 +43,8 @@ You may reuse the base model text encoder for inference.
 
 ## Training settings
 
-- Training epochs: 91
-- Training steps: 9600
+- Training epochs: 1
+- Training steps: 9800
 - 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 sha256:369806a7b004ced383ed9030bffe2aab86450a12e180e259a14854bb640ffe95
+oid sha256:fe40a02f06b2913ce88c8a7a93799f774eaba1326b0e8970e9e7d19d033c5447
 size 15406336826

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21fec9ae3d73d361f3fe5d6cd15204da7ccc96d6d98121f47e45e2a67f77b22c
-size 16100
+oid sha256:c17098186660ca09dfa69252b26135584cc873b0a5b835cff72bf4e59a148885
+size 16036

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e147bbbf8df330e849a5e469d5dc325230077c78970259d898b712c153dd76d7
+oid sha256:bae97ab39f4525134af3a4a6e6bbacc0f3ef728937d8915851c866257ad63408
 size 1000

training_state-photo-concept-bucket.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fed261b31dd12e0fbecc5c15895c8a67639229c14f3458607f64e53dc8ad6549
-size 4368057
+oid sha256:d8a8be5e318b70d60788466ad411db3725c32684ec58748df90a434c09b140a2
+size 5247011

training_state.json

@@ -1 +1 @@
-{"global_step": 9600, "epoch_step": 1215, "epoch": 1, "exhausted_backends": ["celebrities", "pixel-art", "movieposters", "moviecollection", "training-test", "photo-concept-bucket"], "repeats": {"celebrities": 0, "pixel-art": 0, "movieposters": 0, "moviecollection": 0, "training-test": 0, "dalle3": 1, "photo-concept-bucket": 0}}
+{"global_step": 9800, "epoch_step": 200, "epoch": 2, "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 sha256:41f4609468562be636b6d14baa17c69d0ddd9a0a7257bc82eb3991a7dcb4a5bf
+oid sha256:c561b8b3154ca62241e55a818213d7f14718e7fc580c63583dda99c1c25a9d71
 size 5135151416