Trained for 1 epochs and 16250 steps.

Trained with datasets ['text-embeds-sd2x', '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']
Learning rate 4e-07, batch size 4, and 1 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: stabilityai/stable-diffusion-2-1
VAE: None

README.md

@@ -44,7 +44,7 @@ You may reuse the base model text encoder for inference.
 ## Training settings
 
 - Training epochs: 1
-- Training steps: 14750
+- Training steps: 16250
 - Learning rate: 4e-07
 - Effective batch size: 4
   - Micro-batch size: 4
@@ -172,7 +172,7 @@ You may reuse the base model text encoder for inference.
 - Crop aspect: None
 ### architecture
 - Repeats: 0
-- Total number of images: 4322
+- Total number of images: 4316
 - Total number of aspect buckets: 29
 - Resolution: 1.0 megapixels
 - Cropped: False
@@ -180,7 +180,7 @@ You may reuse the base model text encoder for inference.
 - Crop aspect: None
 ### shutterstock
 - Repeats: 0
-- Total number of images: 21014
+- Total number of images: 21015
 - Total number of aspect buckets: 34
 - Resolution: 1.0 megapixels
 - Cropped: False
@@ -205,7 +205,7 @@ You may reuse the base model text encoder for inference.
 ### anatomy
 - Repeats: 5
 - Total number of images: 16383
-- Total number of aspect buckets: 34
+- Total number of aspect buckets: 33
 - Resolution: 1.0 megapixels
 - Cropped: False
 - Crop style: None
@@ -213,7 +213,7 @@ You may reuse the base model text encoder for inference.
 ### bg20k-1024
 - Repeats: 0
 - Total number of images: 89216
-- Total number of aspect buckets: 51
+- Total number of aspect buckets: 53
 - Resolution: 1.0 megapixels
 - Cropped: False
 - Crop style: None

optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19758981dfa79c4c3b7b9beb7a546b5f7530e5b15e4c2a455ec12fe07827fe55
+oid sha256:3abab620f613a3ac7e0982c19034ce809cb53cc1233b0684321b035be49ca12c
 size 5196082660

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44e4c26a93f901c96359c83005ec6f3be2338fcb96aacf0ae6b5822400b9a063
-size 14344
+oid sha256:0330e38073c7f317a3e7cade6b3cca14d74a8e6f892b225e16c5aaeef474fe06
+size 14408

training_state-anatomy.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37bc0d928031fc36c76172ebc78c0e16f0e5936e6956a362d236f823757374e4
-size 2787477
+oid sha256:23a772fc81f6b515679682eba744e6b4dd46293900e4104223dc02b0414de45f
+size 2900606

training_state-architecture.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c10647ef70c748f9d4e390889d56655ad80cae1fc6610d07ffb7973f1d95de0
-size 445526
+oid sha256:2f36873878847112fbe6389f5153cd6d6e1b2e1b6794fa478e7de1d787679b60
+size 216492

training_state-bg20k-1024.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b21d5b627e1a78d74b95e2fe61c61c1a212b222783f6eba02f3e0d19902c03a
-size 15959082
+oid sha256:d2edda0eec12de976e599579b63cbf9fb7e551303290a9cd0e28509c770fa30c
+size 16234731

training_state-cinemamix-1mp.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0c1abc11d0b30fff6dd20f88c6301e1835fd641c6d0141766f2a772a6c6ddf4
-size 2131144
+oid sha256:ec85f948310c0dd66540700a437d542da3b714d6a2eafd03d25f166cffe73ccd
+size 1081983

training_state-nsfw-1024.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ee109da39c6379d6a7d0aa556078480094a08519725251eb38027083420f379
-size 1103792
+oid sha256:e999bfaa16e1f70fdc84754539b54c83a50a48187794fecb7360fa421308193c
+size 1169542

training_state-propagandaposters.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d23c6fb2e60cdafa05192089c84077ee7b9b7c658382cd81877f9dc881b83d01
+oid sha256:2e0ee9874afc5242f3ef8b7dc04a0b66fdd73bf7c164b8d8a55945c6827b48c7
 size 13544

training_state-shutterstock.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f631dafe0819eaf5e926ec5267225ef5d4ffee4b530df345ecf72e0b43fc84d
-size 6225595
+oid sha256:2562788f739b514a9deb370d5a1eebdd9870faa890ef8c93c26a65722f61a8c4
+size 6592211

training_state-yoga.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57cadf9e5dc0c698c6e1a385afb93f8cfcecbd5bc8a4fba3771a426bd3a804e7
-size 646692
+oid sha256:1bb4d57951063cec2d6d2c6231471a7aa85617812e1bbc86f0a95ba928871a56
+size 646695

training_state.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f20bf6e49365cce472a5e7c64ff2496495c653e2745518fe65afcc2df8454f26
-size 529
+oid sha256:7c079c8b10d516b050bec2efc27555dacca5eaa17f8a366ec832b842286b4f11
+size 601

unet/config.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caf46eafd149fe2a7b8ffff16efe57cd06dbc4a69db056f562f5ab08016245ee
+oid sha256:71d6ca0835b24ada0a88cb2e1c38502ffa56885291dc4516e0fc4d497238dab2
 size 1878

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a73036944d8e713e7d0e71431170f626e962b8a3cafc99b0591e58128709c13b
+oid sha256:e950aee142c838b98821273f2a37c185dfcf6bae71cc20d6c66cbb0bba33b4e5
 size 1731905416