Trained for 0 epochs and 4600 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: 4500
+- Training steps: 4600
 - Learning rate: 4e-07
 - Effective batch size: 32
   - Micro-batch size: 8
@@ -148,8 +148,8 @@ You may reuse the base model text encoder for inference.
 - Crop aspect: random
 ### ethnic
 - Repeats: 0
-- Total number of images: 3076
-- Total number of aspect buckets: 2
+- Total number of images: 3072
+- Total number of aspect buckets: 3
 - Resolution: 1.0 megapixels
 - Cropped: True
 - Crop style: random

optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3414a6bb1986b6a0196e9d7268534e029263248b8e47c22846aca6dda7952580
+oid sha256:2f40b27258f312446db5b77ca9638c9f5f36ee375525667a37e833aea00a1199
 size 15406336826

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b27f7e9fe5dd76179d72e2e48a2770a37db46cd293c22cdc88250beba1b50e66
+oid sha256:63f206927c0a3ae9abab060652a9681e0a800cb8514f6cd5a9a0d14b23c488a1
 size 14344

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45208bf3f2442d6774cfd03820db737813b9d5fb8b781378144db873cf39a9db
+oid sha256:bf1741b799bc85f13e1fcf13b28d3ca090564588102eab56e6cdc464bb320977
 size 1000

training_state-anatomy.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b369c3da8134061f0be6fb61ece18735c425ccff86be5ee975477f39f83c9ff9
-size 2585212
+oid sha256:a4c9519db4da48afd67c6a1f1f05e03169a968a4d1c7775f785d30c151bcaace
+size 2614265

training_state-architecture.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f5871fc3fa67726eb58df92d1507311bcefe4a244df31c7b4bd76dffec23dbd
-size 383044
+oid sha256:948c076cf8bb46459f2c7acdc4501b11d66734d54b0586ae81934f7e560153b9
+size 393939

training_state-bg20k-1024.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e978fc1ffc034ae6499dc9288f5adecf0c1be8f4c736822de20e349a45cb9e54
-size 15415187
+oid sha256:cf518988a9c64d3a72eaa93591297debeb9bd833c1c87587e144191275e47ea1
+size 15465912

training_state-cinemamix-1mp.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8f7187307b79b7263d5c05abbe115cc000ae65c1db06cc5be955c9a44c95433
-size 1796368
+oid sha256:98c083504b127ef68ed496ef050829aacb51578a8081dbf2f88d60b840068552
+size 1836087

training_state-ethnic.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f261562f1db695be9e1139aa953c765632cabd56ef30332b72232262a29fa36
-size 1430478
+oid sha256:22e9f1f81df5bfcacfd019ce16632b96ee7bfa929bcf55b4e50f82cb1a2e7a60
+size 720397

training_state-experimental.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f763d5b75caae7f48eb4c510b84eb43dbb5750fb7d622e2aae3ea165f3b7a10c
-size 723734
+oid sha256:59112c49d341633b05d389d2c7930f4ad44008ac95f67b73b8097aea5a09fde6
+size 744788

training_state-nsfw-1024.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:607c2ddfb331bbaa8e40b6339ab433ba31b4efaaae03fe228eb7694f758e71ab
-size 1010071
+oid sha256:ccad02f7c0646dd613783a78b8df324fe76e519c617b209d87c0220b8b83c516
+size 1023978

training_state-photo-aesthetics.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a332efffb9a515adc1c69117f3e6ae5e49e78b924cde8e1b37bcf1b4405fbe6
-size 5378077
+oid sha256:93dc67f9a38337fecb4eeb45cc37996e3860ca144e69a005a841de1fd8ba54a6
+size 5430829

training_state-photo-concept-bucket.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbefd12ea9a67f32229d3a8037cfb1ac9e5817855788abccc5f7e0a7889582dd
-size 15305726
+oid sha256:e68cd691f90489e82d78f6f2b5b4065bf6b8b1d7433a17c0c9ce50cd13831ff1
+size 15318259

training_state-shutterstock.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae0e56fca4c401b14c478760154c005b036ccf8b0b16cf0729c7a3bc1e300f23
-size 5707283
+oid sha256:918f4b1912e2e592185c9bdc1265a78214b794dbfbfdc1bc27e30034074f77f1
+size 5764289

training_state-text-1mp.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:845940c20c2bb3981cfc1039d426ce39ab3f69769ab4ba05d0e2fb14fa3e8c60
-size 2397936
+oid sha256:2cafbacea72f2a1ecaaf1cca5e7fdc7fc94efe3da90a85b78000d36324140176
+size 2458681

training_state-yoga.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e31eea1021b82d55824c51bfef0fb261b26f9c86a9fab3e7009cac68cacf588a
-size 1102513
+oid sha256:5a19546c3eb747b2da507e3ec2559148fd522ef1e91fc4760378d28810e8a034
+size 1134311

training_state.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42df107d69e772dd7feb0299afd77260e50d80fc162d03284b989cb133c5cce2
-size 449
+oid sha256:4fac0f6481ab0107111e473fc27d36eb8ba6bf2a0a90f96f4fdc9cca0c48b485
+size 472

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:384b8f1b54c1f8dd86acef6a58163fbdf113bb6762844f6e16da203d843babd6
+oid sha256:f8dc62b664a1b943f368c20782642b4b1f5151b4cf49f60036bce63bb09b420e
 size 5135151440