Trained for 0 epochs and 250 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

@@ -879,8 +879,8 @@ You may reuse the base model text encoder for inference.
 ## Training settings
 
 - Training epochs: 0
-- Training steps: 6500
-- Learning rate: 1e-06
+- Training steps: 250
+- Learning rate: 4e-07
 - Effective batch size: 8
   - Micro-batch size: 8
   - Gradient accumulation steps: 1
@@ -903,15 +903,15 @@ You may reuse the base model text encoder for inference.
 - Crop aspect: None
 ### experimental
 - Repeats: 0
-- Total number of images: 3127
-- Total number of aspect buckets: 15
+- Total number of images: 3104
+- Total number of aspect buckets: 17
 - Resolution: 1.0 megapixels
 - Cropped: False
 - Crop style: None
 - Crop aspect: None
 ### ethnic
 - Repeats: 0
-- Total number of images: 3050
+- Total number of images: 3008
 - Total number of aspect buckets: 18
 - Resolution: 1.0 megapixels
 - Cropped: False
@@ -935,7 +935,7 @@ You may reuse the base model text encoder for inference.
 - Crop aspect: None
 ### architecture
 - Repeats: 0
-- Total number of images: 4296
+- Total number of images: 4256
 - Total number of aspect buckets: 18
 - Resolution: 1.0 megapixels
 - Cropped: False
@@ -943,15 +943,15 @@ You may reuse the base model text encoder for inference.
 - Crop aspect: None
 ### shutterstock
 - Repeats: 0
-- Total number of images: 20970
-- Total number of aspect buckets: 30
+- Total number of images: 20944
+- Total number of aspect buckets: 32
 - Resolution: 1.0 megapixels
 - Cropped: False
 - Crop style: None
 - Crop aspect: None
 ### cinemamix-1mp
 - Repeats: 0
-- Total number of images: 9023
+- Total number of images: 9016
 - Total number of aspect buckets: 6
 - Resolution: 1.0 megapixels
 - Cropped: False
@@ -959,7 +959,7 @@ You may reuse the base model text encoder for inference.
 - Crop aspect: None
 ### nsfw-1024
 - Repeats: 0
-- Total number of images: 3777
+- Total number of images: 3776
 - Total number of aspect buckets: 4
 - Resolution: 1.0 megapixels
 - Cropped: False
@@ -967,15 +967,15 @@ You may reuse the base model text encoder for inference.
 - Crop aspect: None
 ### anatomy
 - Repeats: 5
-- Total number of images: 16355
-- Total number of aspect buckets: 21
+- Total number of images: 16328
+- Total number of aspect buckets: 22
 - Resolution: 1.0 megapixels
 - Cropped: False
 - Crop style: None
 - Crop aspect: None
 ### bg20k-1024
 - Repeats: 0
-- Total number of images: 89180
+- Total number of images: 89160
 - Total number of aspect buckets: 42
 - Resolution: 1.0 megapixels
 - Cropped: False
@@ -983,7 +983,7 @@ You may reuse the base model text encoder for inference.
 - Crop aspect: None
 ### yoga
 - Repeats: 0
-- Total number of images: 3568
+- Total number of images: 3528
 - Total number of aspect buckets: 14
 - Resolution: 1.0 megapixels
 - Cropped: False
@@ -991,7 +991,7 @@ You may reuse the base model text encoder for inference.
 - Crop aspect: None
 ### photo-aesthetics
 - Repeats: 0
-- Total number of images: 33073
+- Total number of images: 33024
 - Total number of aspect buckets: 25
 - Resolution: 1.0 megapixels
 - Cropped: False
@@ -999,7 +999,7 @@ You may reuse the base model text encoder for inference.
 - Crop aspect: None
 ### text-1mp
 - Repeats: 5
-- Total number of images: 13136
+- Total number of images: 13104
 - Total number of aspect buckets: 21
 - Resolution: 1.0 megapixels
 - Cropped: False
@@ -1007,7 +1007,7 @@ You may reuse the base model text encoder for inference.
 - Crop aspect: None
 ### photo-concept-bucket
 - Repeats: 1
-- Total number of images: 567449
+- Total number of images: 567424
 - Total number of aspect buckets: 37
 - Resolution: 1.0 megapixels
 - Cropped: False

optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20507412ed158d8f42190e5328c926acacc276a50504526a3686334bbdfa5464
+oid sha256:ad6f4d4aa80f5eb596d818a2ec0d13137c4557a42cffc3cb705928bda95f70e1
 size 15406336826

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d97cdf186fc857e70be41d7fade75cac2f3959b227c06b19c84844d36d6602b
-size 14408
+oid sha256:69ff3181752ccf7d0185e2a25632cf9ad50cca6f0e6d43486a8509cee4248fe5
+size 14344

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ba98ccf0ba4182e6dd389305e01f09ba519041c8bf9f46714dd649cb6b39bcc
+oid sha256:903228551a0e74e8357a525e68a6ad53fe382087e1795fac447cb265eca01872
 size 1000

training_state-anatomy.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d70e1bf668d9ff088f779abf5357509ff788edc99a6a73647a622bb57051103e
-size 2359644
+oid sha256:d59164d599f2e3c0e334d73c12f6ffa080889dc67770b3baf8b44bc973184719
+size 2195781

training_state-architecture.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f31522fa4891d2364786f365679c8c1ca35713e752327465c583ff1af6ef603b
-size 284888
+oid sha256:44557e983dc80b9782b74bb567bdc2f2c514761cfa6ff67d51723d363d83f3e8
+size 219613

training_state-bg20k-1024.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a77d86fa150024f3590ed7692b1f643b99ff9a529d652f490004a6e082d52502
-size 15001953
+oid sha256:2d250ee1632c994eb44635cc8fc89a074ba99ca427f3b01bad86d5be2a8d8270
+size 14647067

training_state-cinemamix-1mp.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdc4e9f01a42ecc9cba937d84efa84cc9c7dc20ccf7f146670e80019eedf0dda
-size 1440599
+oid sha256:51ce48d754585635583650cab3e28b3ad8c75a48e0d6ab8fa27f2aabe9d86f83
+size 1104430

training_state-ethnic.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b62ca61cf7c33db8b7cabb82f744ae7e8e2c4797630fd87556499d5f0cd5f18c
-size 1009932
+oid sha256:940b5ac87e7e5fe665ccffbe88d55c309a4d8b3d6fa1b12ba84106bbacb28eb9
+size 724140

training_state-experimental.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1803bdb540b848f7a1b4701a661ed1c52c944d2dec648aae0eba98e4234526ff
-size 550513
+oid sha256:79f14b870d03695a4cca192ff73fb65e75c98fe0a102692cb324d6b9c4ad0b37
+size 399754

training_state-gay.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb701ec10a96b346d0552c65c1e41d38b2cd0bc84cfce5510a362e32a128e43e
-size 201678
+oid sha256:e2e58d390f7441922512a3b083bf272b4b5e57488102d522097bd6bff1cf2673
+size 219650

training_state-mj-60.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71fddc9703e4815dc291321212874e7d92a0d1da9dd918382149f68ce5dfae16
-size 2746946
+oid sha256:d6b676620582ec0db3140810730d08db2ea73ebb7e1f6eef67d5ee67c9d11142
+size 2279795

training_state-nsfw-1024.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26a33666e9b385903b2e294ecf59cf75cfa3741e5149c43c727a89f854e56fb8
-size 375580
+oid sha256:d3630f4ba77da03dd32ce1539d47b6d7f2895004cf230f851492c9385e5f23ef
+size 274468

training_state-photo-aesthetics.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:252eed14b754407ab0115ed16877c01cd675b9d82163f2196140ffec972107c1
-size 4960675
+oid sha256:78be6020fda082dc51e6099841a9e31cc39f9d108ff1943297d2afe1d7e72e9c
+size 4579911

training_state-photo-concept-bucket.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea26674bbf0c19a5e5e5b36fca1cfaba9a1b157e9228f27e43bda78bc08c197a
-size 15209853
+oid sha256:6e3d7cc0919cf7565ae868dd8e39011d70277bc68f36bb50b87844a41ff1a899
+size 15133941

training_state-shutterstock.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:420a664d62bd66dee5b4a5a03f74fda4792601dd01d510cf687d1412eb621432
-size 4961849
+oid sha256:3e36914274cdc3bf3dbc019e03415d2d22aeb77be30330b9ae3835f89015a12a
+size 4456158

training_state-sports.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66eaa059d1a85ade4ec1083ea68b987a7a82f06d29448be3c858cd2d98349f4c
-size 131400
+oid sha256:2a2fcdb3251c038651c6a838de63b27c839dcbc6f0a5519989aca0677d399f41
+size 150647

training_state-text-1mp.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ccba9e3d09567c1605afd25bab5fcad9ea0d876024b414c9f642e9e32d97ea9
-size 1961916
+oid sha256:ffe0d50eb0aa16062ade938a84367bad72d45f677ee7fc702b93634fd275fc4a
+size 1662039

training_state-yoga.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d311e26a375c29e7e356b50ba097c9c1b08a21bf6283083e43a29095c8fe243
-size 872055
+oid sha256:a95e118713f1ef6c6f2c4570296a36d5617ea84a6dfdd1d31ab770b3ce880c34
+size 655332

training_state.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:006585f62b99941d17bc6da060cb52951a462682b8ea3f60edf2e2aa781731ae
-size 130
+oid sha256:0458a2b66434e6315636a25a90f1aa7d2dd5275ab7e256f8b3af17adb9356bd9
+size 92

unet/config.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfba72811ece4e2e5c5c09ef2241b8d155bf7ff4e01fb7a7b4aafdbc58aef890
-size 1837
+oid sha256:25871faec72d07b0d3411a5bc8ad69160b634deccaae6fdc6310374db4a0b237
+size 1823

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6a013a030f7b4f676baeb40fdf537e5e02cdcd59607d7efd0dacd2d500aa321
+oid sha256:d458548a9b2d1842a4d9fec6afe2f78f8c7d32bfbd459652eebd019b29da99b0
 size 5135151440