Trained for 0 epochs and 4700 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 4e-07, 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: 4600
+- Training steps: 4700
 - Learning rate: 4e-07
 - Effective batch size: 32
   - Micro-batch size: 8
@@ -140,7 +140,7 @@ You may reuse the base model text encoder for inference.
 - Crop aspect: random
 ### experimental
 - Repeats: 0
-- Total number of images: 3042
+- Total number of images: 3040
 - 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 sha256:2f40b27258f312446db5b77ca9638c9f5f36ee375525667a37e833aea00a1199
+oid sha256:bafd0975eb6db133fed61be82b06b84d51410399c54dc68317c87c4fb6833480
 size 15406336826

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63f206927c0a3ae9abab060652a9681e0a800cb8514f6cd5a9a0d14b23c488a1
+oid sha256:bf8381d09428c344f8a189bcacf4efe9bfffb51af10bf6cd01e5422a0389ea89
 size 14344

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf1741b799bc85f13e1fcf13b28d3ca090564588102eab56e6cdc464bb320977
+oid sha256:36648ded4c922a8add9ae1cac66044d7b2ae3abb2e87f306a1691166bf9b0071
 size 1000

training_state-anatomy.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4c9519db4da48afd67c6a1f1f05e03169a968a4d1c7775f785d30c151bcaace
-size 2614265
+oid sha256:50ef165f0f15df8532c9b5cadd4069797698cb97b255ee391ddd1fefa40ed675
+size 2636974

training_state-architecture.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:948c076cf8bb46459f2c7acdc4501b11d66734d54b0586ae81934f7e560153b9
-size 393939
+oid sha256:2b999f46da774b1dee5b0339db25c4a14aca623a1be9d7fe8d5675b26d92f79d
+size 404555

training_state-bg20k-1024.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf518988a9c64d3a72eaa93591297debeb9bd833c1c87587e144191275e47ea1
-size 15465912
+oid sha256:71b54a978b8f2accf0f1f05bb772da8a08700cd675ce5c8203d76decbf3e1df7
+size 15526429

training_state-cinemamix-1mp.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98c083504b127ef68ed496ef050829aacb51578a8081dbf2f88d60b840068552
-size 1836087
+oid sha256:8c8632c1a9af0d249390fb3438915e3f7e2c34ee1bd5a438933530a194c096cd
+size 1886358

training_state-ethnic.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22e9f1f81df5bfcacfd019ce16632b96ee7bfa929bcf55b4e50f82cb1a2e7a60
-size 720397
+oid sha256:e3d8cdf7f7a97f3744768c5158dc02098bff0281a44ff1f3efcf3de712a82658
+size 720400

training_state-experimental.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59112c49d341633b05d389d2c7930f4ad44008ac95f67b73b8097aea5a09fde6
-size 744788
+oid sha256:6f4365f6f84bc95078e4d0b6e2f6a96ce805f2ceb97653391cd945faadf96c9d
+size 375564

training_state-nsfw-1024.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccad02f7c0646dd613783a78b8df324fe76e519c617b209d87c0220b8b83c516
-size 1023978
+oid sha256:6e31539190798bc5968600034fc4eb820d0752fccda1b395de53989aee935972
+size 1036461

training_state-photo-aesthetics.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93dc67f9a38337fecb4eeb45cc37996e3860ca144e69a005a841de1fd8ba54a6
-size 5430829
+oid sha256:0afd60b2f373ba8100321214da8ad8ab1026ae00a5543a4eae48254b33cc5c3b
+size 5474894

training_state-photo-concept-bucket.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e68cd691f90489e82d78f6f2b5b4065bf6b8b1d7433a17c0c9ce50cd13831ff1
-size 15318259
+oid sha256:a4d0fdeda1551d8d271485840c29ead25e48f0086f9ec610c9a4428204a6915a
+size 15331591

training_state-shutterstock.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:918f4b1912e2e592185c9bdc1265a78214b794dbfbfdc1bc27e30034074f77f1
-size 5764289
+oid sha256:4dc35ea405b0a63d948208b150a8ef1500122c23bfd75005d121ef3a6c64e52b
+size 5839584

training_state-text-1mp.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cafbacea72f2a1ecaaf1cca5e7fdc7fc94efe3da90a85b78000d36324140176
-size 2458681
+oid sha256:2a9c87ecc537bb8bde8a78487a531a1828c710d3c93733a3febec37547f46652
+size 2508288

training_state-yoga.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a19546c3eb747b2da507e3ec2559148fd522ef1e91fc4760378d28810e8a034
-size 1134311
+oid sha256:8c42cd6daf7f410901d1244f6c334f2260da74fb995b308185ca8b4abdd4e2e2
+size 1178240

training_state.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fac0f6481ab0107111e473fc27d36eb8ba6bf2a0a90f96f4fdc9cca0c48b485
-size 472
+oid sha256:dc4797a0d92f07650a2066f80c71ea8716e1b9cd8393b7091806bfc282eebaed
+size 507

unet/config.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b4f66b29903b7b160884370e09d17b26d1f2fd4bf0193947843628ded13c22c
+oid sha256:ce25a06f2b94df35d4fa5d1bb4d2a44c0b6c9e12d223a7fb95a2afd55301b11f
 size 1837

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8dc62b664a1b943f368c20782642b4b1f5151b4cf49f60036bce63bb09b420e
+oid sha256:c742946c1af412feeae6d607b1282a983770f0ebde8a3121c498414079e27181
 size 5135151440