Trained for 0 epochs and 9000 steps.

Trained with datasets ['text-embeds-sdxl-nofilter', 'training-test', 'dalle3', 'photo-concept-bucket']
Learning rate 4e-07, batch size 4, and 4 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: 0
-- Training steps: 8000
+- Training steps: 9000
 - Learning rate: 4e-07
 - Effective batch size: 16
   - Micro-batch size: 4
@@ -69,7 +69,7 @@ You may reuse the base model text encoder for inference.
 ### dalle3
 - Repeats: 1
 - Total number of images: 57744
-- Total number of aspect buckets: 2
+- Total number of aspect buckets: 1
 - Resolution: 1.0 megapixels
 - Cropped: False
 - Crop style: None
@@ -77,7 +77,7 @@ You may reuse the base model text encoder for inference.
 ### photo-concept-bucket
 - Repeats: 0
 - Total number of images: 70616
-- Total number of aspect buckets: 5
+- Total number of aspect buckets: 4
 - Resolution: 1.0 megapixels
 - Cropped: True
 - Crop style: random

optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c595e617db564297fdeec76dd84c748a254799ffe8de522d8b026d0690b95599
+oid sha256:1c5fb4a52cbf58218b3e0ca3261904c233bf6895f9f9cfffbfeabd203026c139
 size 15406336826

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1aea102f5efb3a610f32039217429c30c71e712827a04ab55c77fd5d1a7f0fff
-size 16100
+oid sha256:df132266404cad7e3daf43793b9b1bbccb66243137d04410e452d5b75dcc63f7
+size 16036

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2923a6da3a6318c6fcfa28380ef898d41dfd6d231cadda47df4b6c794825d139
+oid sha256:8eb730670117893a941498760651c7bb31af112047a438fe7509a55386824f73
 size 1000

training_state-photo-concept-bucket.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9e2e178881d95ff47a75fe447f140c54468246cd238659989958a3980f7f62c
-size 8576779
+oid sha256:c35d2aba7a0651ff48f997b1cdfdedd4e2209063a28dfe9e04df3b60dd2975c4
+size 9128699

training_state.json

@@ -1 +1 @@
-{"global_step": 8000, "epoch_step": 5923, "epoch": 1, "exhausted_backends": ["celebrities", "pixel-art", "movieposters", "moviecollection", "training-test"], "repeats": {"celebrities": 0, "pixel-art": 0, "movieposters": 0, "moviecollection": 0, "training-test": 0, "dalle3": 1}}
+{"global_step": 9000, "epoch_step": 6923, "epoch": 1, "exhausted_backends": ["celebrities", "pixel-art", "movieposters", "moviecollection", "training-test"], "repeats": {"celebrities": 0, "pixel-art": 0, "movieposters": 0, "moviecollection": 0, "training-test": 0, "dalle3": 1}}

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a6f809f98a5d48cc16fe7272d2385fbe2a626aa80e8ba9dc84926f832d59e78
+oid sha256:81e8ca245a5180d0279bc92299a27a77095827e33c9a933f8e9ed8edb230daf7
 size 5135151416