Trained for 0 epochs and 4800 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: 4700
+- Training steps: 4800
 - Learning rate: 4e-07
 - Effective batch size: 32
   - Micro-batch size: 8

optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bafd0975eb6db133fed61be82b06b84d51410399c54dc68317c87c4fb6833480
+oid sha256:fb3c4d871399b7ab6c67aed872f05c3b35d101372d473644c280b2f725d1156c
 size 15406336826

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf8381d09428c344f8a189bcacf4efe9bfffb51af10bf6cd01e5422a0389ea89
+oid sha256:b633bac54877cd0067086c98cd4082095a41038e4e6684abc7a1d52d93c94cac
 size 14344

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36648ded4c922a8add9ae1cac66044d7b2ae3abb2e87f306a1691166bf9b0071
+oid sha256:3c6c82f81cfc86720dbebaa21e517f5bab4604e80373a64fec76de4b7b1abb3d
 size 1000

training_state-anatomy.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50ef165f0f15df8532c9b5cadd4069797698cb97b255ee391ddd1fefa40ed675
-size 2636974
+oid sha256:6cb8edf79965c4a7f2ad65a518e4ad03e540251d3908f60f4e4cbf846af84ed3
+size 2657189

training_state-architecture.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b999f46da774b1dee5b0339db25c4a14aca623a1be9d7fe8d5675b26d92f79d
-size 404555
+oid sha256:d9efb7460bd99f5069926fed2b4f34103d47a533045a70b637614b9ec4142be7
+size 416508

training_state-bg20k-1024.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71b54a978b8f2accf0f1f05bb772da8a08700cd675ce5c8203d76decbf3e1df7
-size 15526429
+oid sha256:02caf5e4eb715e6f3aeb6dfb7eafbba9571b65e138489a61c1e2657d75c84b1e
+size 15597540

training_state-cinemamix-1mp.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c8632c1a9af0d249390fb3438915e3f7e2c34ee1bd5a438933530a194c096cd
-size 1886358
+oid sha256:bfdee8f80d0bc79644677e5025fe51717e2fa259ed93b8e5488068ef35c69fb6
+size 1936591

training_state-nsfw-1024.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e31539190798bc5968600034fc4eb820d0752fccda1b395de53989aee935972
-size 1036461
+oid sha256:1660e16c8dcb6d60e2acbfff6f0320811a43166381a24f32b9bad5194ddb05d6
+size 1049582

training_state-photo-aesthetics.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0afd60b2f373ba8100321214da8ad8ab1026ae00a5543a4eae48254b33cc5c3b
-size 5474894
+oid sha256:23e04f0753e37bd0642c1401500b9ebf0507d2ca3156b2c4cf8aaf4356cc6c3c
+size 5531552

training_state-photo-concept-bucket.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4d0fdeda1551d8d271485840c29ead25e48f0086f9ec610c9a4428204a6915a
-size 15331591
+oid sha256:f0bd6318c3d9f4aeed2dad51028dec118646709c295b7d558c4483dcfaf214ec
+size 15346217

training_state-shutterstock.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dc35ea405b0a63d948208b150a8ef1500122c23bfd75005d121ef3a6c64e52b
-size 5839584
+oid sha256:16d1b5c27906b760ad86d5565baa5018573735c8e71d64d6a15c0a55b302d751
+size 5919911

training_state-text-1mp.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a9c87ecc537bb8bde8a78487a531a1828c710d3c93733a3febec37547f46652
-size 2508288
+oid sha256:fe53b194b5f801aef1e8874a20a383c40e0bb540682db4b1df39b569317e7b48
+size 2561036

training_state-yoga.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c42cd6daf7f410901d1244f6c334f2260da74fb995b308185ca8b4abdd4e2e2
-size 1178240
+oid sha256:3f740a1f345e9dcd3701a1e28aa0f240a3738e27268603f9315365428f37858c
+size 1216205

training_state.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc4797a0d92f07650a2066f80c71ea8716e1b9cd8393b7091806bfc282eebaed
+oid sha256:6f37c5f130eb5fccbf8a7e65b533590b7d4a4cb294e8f31f798a796e6d14fd39
 size 507

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c742946c1af412feeae6d607b1282a983770f0ebde8a3121c498414079e27181
+oid sha256:32b15b50f4cea7fa7b7555118e7531d0fb74b450dad22fbc14ee7ed96652294f
 size 5135151440