Trained for 0 epochs and 5400 steps.

Trained with datasets ['text-embeds-sdxl', 'photocb-clip-embeds', 'celebrities', 'movieposters', 'normalnudes', 'propagandaposters', 'guys', 'pixel-art', 'signs', 'moviecollection', 'bookcovers', 'nijijourney', 'experimental', 'ethnic', 'sports', 'gay', 'architecture', 'shutterstock', 'cinemamix-1mp', 'nsfw-1024', 'anatomy', 'bg20k-1024', 'yoga', 'photo-aesthetics', 'text-1mp', 'photo-concept-bucket']
Learning rate 1e-06, batch size 8, 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-v1
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: 5300
+- Training steps: 5400
 - Learning rate: 1e-06
 - Effective batch size: 32
   - Micro-batch size: 8
@@ -188,7 +188,7 @@ You may reuse the base model text encoder for inference.
 - Crop aspect: random
 ### cinemamix-1mp
 - Repeats: 0
-- Total number of images: 9009
+- Total number of images: 8992
 - Total number of aspect buckets: 3
 - Resolution: 1.0 megapixels
 - Cropped: True

optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:346b22f3a91dee81ffbef8165f4d11b94222cb81865e93c3895373d76b6e364b
+oid sha256:12290737df559a9cd2f5d39d4061b4164c7fa663ebd6d647999ed6a3b2e8a024
 size 15406336826

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef1527518954b766e6cee80dee6a21adcc155b43cb53d182b772ea62a3dab149
-size 14344
+oid sha256:334699aff7a283f24bef002a65fadffd811bf1b935b47e85040aeddda0ba4eed
+size 14280

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0c72b80a3bc656df6e9ceb1c5f217d1792c1f750d8eb36cf217c62bec34e780
+oid sha256:f1a7becfca6223d90119516fb4167eb9bcab6cd1ce4dcb85173f3e3ef9c6cab7
 size 1000

training_state-anatomy.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5aedee6318bdd7512e9b712d4bc23c56432c2d997414a149553d056c50cda60
-size 2790600
+oid sha256:66b4928ddda8be37c22dca23e44b30290be57739739d0333119992f59d1c5789
+size 2830806

training_state-bg20k-1024.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bc2c6bbc031470625e9228fd31c6877f46b7d23d8a999aaa3bda48b1dedde41
-size 15880331
+oid sha256:92edd0c188bd38264d3d1da1bdf485136db04c071e1150346f5619bf9758c30c
+size 15954939

training_state-cinemamix-1mp.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e525e1e056b71b668531d0d7badf3223f55260e04f5bae7dd3991c2412995883
-size 2212767
+oid sha256:2720bc13236eb1a483daf4b3845a5428d0111f7b85fbfec92424bd8724d74d2f
+size 1078568

training_state-nsfw-1024.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fcc740cc5000c297318bd028aeb3abba15a994c8b34146810bfe5f5deadeac4
-size 1138523
+oid sha256:a595f5216d989f0bdc4b628297d196a72ebc336c6cf3f84e974ba89a9c36f443
+size 1163610

training_state-photo-aesthetics.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25224408b5329c855eecc954a910b13c6cc477d81495faa448ba9afa705b591d
-size 5838667
+oid sha256:3f3c7d309502829156e86add5a0b47d17ef057511359b0305434d7a6e7ab2ccd
+size 5917533

training_state-photo-concept-bucket.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af4228ef64ea4ac58cbd39469cfafc74a520e6453c2f34b0eace9ffa3b47a18c
-size 15414410
+oid sha256:b989933d3ab4be00e441af3c8fc849aa083b44504011d7ab0c06b5fe53b1e02b
+size 15433501

training_state-shutterstock.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a2f1e3e35795d9f9174d121ac3eac0073e38479af63de7aaa60d9fc4a929021
-size 6388405
+oid sha256:3243d91900fb6f7a35c6c234d8ce698924ea75f2084c6873deeb7b35b48d35d4
+size 6488457

training_state-text-1mp.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a9cc5da6adb2a330ea4cb21b90e50f8022cb5e4465e751e105eb73a5e5eee56
-size 2827671
+oid sha256:f64cbcce4f63ec4199511058e8b9756114cd0c187838c23855d8baf46425b770
+size 2891511

training_state.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32900e19928dc458fd7184cc8a0ddc070e2bd76bc5860116854cf998f263ccb8
-size 561
+oid sha256:74dc1bf145bd9efd63fd3504a1eebe3355b1ce61adc19f122a0c4a925844ef54
+size 598

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5c32d0e0721e00a86bc1d50e283d59a14993928520360a2705d80eea620c24d
+oid sha256:eb98c022a8ac4c93ea6ba37bad19d49a67be91eb3bdaf68e1a8bd2fc5099f99a
 size 5135151440