Trained for 0 epochs and 18400 steps.

Trained with datasets ['text-embeds', 'photocb-clip-embeds', 'mj-60', '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 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: 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: 18200
+- Training steps: 18400
 - Learning rate: 4e-07
 - Effective batch size: 8
   - Micro-batch size: 8
@@ -109,7 +109,7 @@ You may reuse the base model text encoder for inference.
 ### shutterstock
 - Repeats: 0
 - Total number of images: 20944
-- Total number of aspect buckets: 31
+- Total number of aspect buckets: 32
 - Resolution: 1.0 megapixels
 - Cropped: False
 - Crop style: None
@@ -171,7 +171,7 @@ You may reuse the base model text encoder for inference.
 - Crop style: None
 - Crop aspect: None
 ### photo-concept-bucket
-- Repeats: 1
+- Repeats: 0
 - Total number of images: 567424
 - Total number of aspect buckets: 37
 - Resolution: 1.0 megapixels

optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4e7a9cbed051e95317141e3fe5babd9048ed2b643f73ed29faff9f6df0b50d8
+oid sha256:cba21444edb1237ee9de006915a8460e4e815abebd83ebd563e5852fc6ecec1b
 size 15406336826

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9e4ad8ac42d0043dce4fcda205226bb46e7ff1b4598ef2a22b36cd245fe7d52
-size 14344
+oid sha256:d6efe610c0791da8754ca6060df5ed67eb73e3e4b982d43859cacebe01f41980
+size 14408

training_state-anatomy.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6453f8259b7428f62c4965fad510ad149c569a1485d943d509e4c04a2ad88717
-size 3517671
+oid sha256:cd8991cf8eca9bb44b35a01e9fae9861fb77626c011ba3fab86ad0f138729d64
+size 3547135

training_state-bg20k-1024.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e82f4ba2dba241afe9c28c93f6cc5ba54bca087f83dcb0feeac4aaf00e89a45
-size 17742039
+oid sha256:2eed6212bf257339a2849aaaa03c1a4cb346d078982fdbbb149d7fc551ee84e0
+size 17780821

training_state-photo-aesthetics.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca1f8bf3fec92e2ec49563fa6e96f1fcc6b75979f9e1ab2295a473e7cf4017cf
-size 7299940
+oid sha256:259cad466aa534373923fcdc5e7f95b057b6ae95be2eb38bf7e764d2f591db6a
+size 7335283

training_state-photo-concept-bucket.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78ab7d93d33a96863455b81a4a5e653e60c41eaf52ae23b4002a04c811f63a17
-size 15764002
+oid sha256:a9f554ca48538905e0b0e77373ae49e82530769bef76fd45a8ac226c2a894be7
+size 15772641

training_state-shutterstock.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b46019bf028e81dbbe15d950a56f4fab6aca158c25f4a2e7d6eff601902f9e34
-size 8581711
+oid sha256:39e769fbf90e6cbc3b1b4b96b9d755ff739eb96960c21343d659ca5db9f4f51e
+size 8657009

training_state-text-1mp.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d439f6e7f535c8e41eae724a166279ba5a2ee1945e438e9fdbae0f83c907e833
-size 2368163
+oid sha256:c8ebfe46a2f230cebce058aac9dde1e81816a7147b35a1a19d2ba6ea62e6303a
+size 2403932

training_state.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb30d5ecb181bfbf2b586b790d617a46cfdc701275b7c20bfae967ff82b8cc48
+oid sha256:d4af3662d79961d598a16d67bb0fafa54bd960c487d99da4560956dc9a1a73ab
 size 346

unet/config.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78a170395d0bee38c99ba1c6d503753f5d6a893d492c2ac505778d08c763e6c7
+oid sha256:2b1ec617660b09d33544028f6b7b3a6328664d650cb35ba92ae7bb47e7ba6773
 size 1838

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b478d034424d2074798cb93460424450608b51603cda80ba012616151ee9a0f
+oid sha256:aa6875b35cba09fd7e3808bce61b8a2d2cb7235a3b288c31666df85f9e16d1bd
 size 5135151440