Trained for 1 epochs and 5500 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: 5250
+- Training steps: 5500
 - Learning rate: 4e-07
 - Effective batch size: 4
   - Micro-batch size: 4
@@ -149,7 +149,7 @@ You may reuse the base model text encoder for inference.
 ### ethnic
 - Repeats: 0
 - Total number of images: 3065
-- Total number of aspect buckets: 23
+- Total number of aspect buckets: 22
 - Resolution: 1.0 megapixels
 - Cropped: False
 - Crop style: None
@@ -173,7 +173,7 @@ You may reuse the base model text encoder for inference.
 ### architecture
 - Repeats: 0
 - Total number of images: 4320
-- Total number of aspect buckets: 22
+- Total number of aspect buckets: 21
 - Resolution: 1.0 megapixels
 - Cropped: False
 - Crop style: None
@@ -181,7 +181,7 @@ You may reuse the base model text encoder for inference.
 ### shutterstock
 - Repeats: 0
 - Total number of images: 21013
-- Total number of aspect buckets: 34
+- Total number of aspect buckets: 33
 - Resolution: 1.0 megapixels
 - Cropped: False
 - Crop style: None

optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bebc0a69318a5456800f1dc4d518dde4eed710d3ac90bc5f312408f5944e5fc
+oid sha256:6896a4fd8f513878f60992c4e4b6bb2f974095794633316be6306cc37b78c39e
 size 5196082660

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad26a1702b4776675990cacb53d399d16cddbfadc6167bb504c933351ad2c61b
+oid sha256:c3ce3387429a78dfbed6daa721a3794977edbc138f27ca1a01b18260fbcab7d8
 size 14408

training_state-anatomy.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f27bd730e690c7d626a51e4a2f05187bfd7098d4bc780f589e715bfda70e998
-size 2314344
+oid sha256:64ec3f13525b7181d504a6da9f0c67949c2ca896f7cf0004b91f56bd35e04ec5
+size 2325477

training_state-architecture.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfa9c0da212a3c62a1385ecde43672e49089c2070a3ce4bafb495cd3e31f5f99
-size 268722
+oid sha256:b99d384693304464e1c0704fd8636345a796fc0467e767849bee146fb8c75324
+size 271901

training_state-bg20k-1024.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c62433504c0572094c237e4329cd3a33c2e79ba2aac3ec36ed4b69ed2e7b67f7
-size 14874144
+oid sha256:431912791f964839ca3c6506a524d400e1e063a7cacd5665839b47aead0903db
+size 14891923

training_state-cinemamix-1mp.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20f3b4369b8b835ea7764637a7dccca39596d9c1f08699e5041a5c0927e48d54
-size 1285238
+oid sha256:18cf585ea446365ee379d89e3c897d9ec816cd5be0a61b4fdd9c667e7f4d6f5b
+size 1308303

training_state-ethnic.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac4655a7127abac2b421fbfe041ab66431662b99f1013ffb7ed3f78cb4c60ad3
-size 913195
+oid sha256:bc41f537b7d8737b96f566e040e9340086974b6487fc73b1a13f6f44a6eda6df
+size 928788

training_state-experimental.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2b0428a63b9069200b624e0c43bec9b51f12dd24dea8424c94a91d2bbe371ee
-size 477980
+oid sha256:fc2c0334be829d2fa3c2a60554a8a93815c2176e8caf6a573985747bbfa9425b
+size 486568

training_state-gay.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e01e633327cd436a11293e4240b41751879d3ae1a8003be6f04a3120fd3e3dc5
-size 366035
+oid sha256:269238decb5473316aaef4fe16aa0a4c2c5b9cf7471528ab81f3669e42598883
+size 378413

training_state-moviecollection.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:869854a1be61126d2aa7a3683f0e3d71d8fecb8b97073fb0cddf65bd8c91be8a
-size 83388
+oid sha256:1463d8dfc13c2b4fcda286f4dae8b4b5a48e7baed148485d714f2fea2441814c
+size 87167

training_state-nsfw-1024.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1757d641d6b7ac50b427533d37e22cee536bc10754693203e5d873fa25a99504
-size 845873
+oid sha256:211012e5c78c0ebdce84bcc40dcc330dc839ed730b8dd064d8e7565b6173038a
+size 851173

training_state-shutterstock.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e80db410fe61e5d279d93c394ee4ed313ed76caae560c313a51451c05169599
-size 4753696
+oid sha256:9c9cc24730438e834d1ae4ad0a09116a5af98db0efedf0f33af86ad20b865e77
+size 4781023

training_state-yoga.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94223c1140e87b7e8522d2de694c09ce900f16efcdfc69338269abc265fd9052
-size 772780
+oid sha256:9b824cdd2061230b1eef757642d3b98a99732b3678d835c659ad5a72fe3b428c
+size 784169

training_state.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ff6d1e25b8de8c98e3312466ceb6a005b8f677f78f578723b5ee0906896cfbc
+oid sha256:720680f84265fbd7f77c55c2d1c2cc108a03ef9d8e7ac6bd749bc357be800211
 size 392

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15fe3f0effd7f81573b7eb153b90cf0b65fb02def3df0aae380f5f8d8f9eccdf
+oid sha256:a55bd3d7076e7d9e15ffe782e579cd0a8be27ddf4f246518acd74e4c05cb385c
 size 1731905416