Trained for 1 epochs and 30750 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: 30500
+- Training steps: 30750
 - Learning rate: 4e-07
 - Effective batch size: 4
   - Micro-batch size: 4
@@ -205,7 +205,7 @@ You may reuse the base model text encoder for inference.
 ### anatomy
 - Repeats: 5
 - Total number of images: 16395
-- Total number of aspect buckets: 25
+- Total number of aspect buckets: 24
 - 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:f78105661e0a7f630f30312d1a0a543920e37163de0073d114b02b8fa9b0b736
+oid sha256:7b3966fbb8db84c58c052d564f0fca53969b6ad4aa48fa7fec448269a12e76a7
 size 5196082660

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6508b5927a439d8b8875d489db3e397c76491b9841fc208e74c8f92d5bb5be7f
-size 14344
+oid sha256:738805e1f6cc25f2706a72780de3bd2565de148dd5298bb25068ed70da0f92a1
+size 14408

training_state-anatomy.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2746469ad3ed8faddb423e16252e52de6d39a22233ba3c7272d5dd583c24b7aa
-size 2452839
+oid sha256:c942253fe8e9b87243cccebe3f7873e2df6054b6b923e94fb11dc3b1ed907b76
+size 2498765

training_state-bg20k-1024.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01c4d962ddbc1522549884cd2412c7b243ce74d2a4ba58d1b6382d8a6a5f3a1d
-size 20818537
+oid sha256:3b45e2c4d55d876941ebd9a7104ce05f1312bb8da42f786704d6dd81cd739916
+size 20941957

training_state.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8414e1e6e773fb8ede5779a1415c2831329c98eca38755721e97dd76cfbe07ae
+oid sha256:25b59eb3bd5b05272b615f18aed8aba1d785019c4c51a1612e3d373342c72a3c
 size 679

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7202f404a3d4c524ee3e97fd3aefa328c22f1bb1b8b555a2debd8512ef269c8a
+oid sha256:c3876878b65791100e063156e201639c0ba95038777f7378662d8f35da9b0a32
 size 1731905416