Trained for 4 epochs and 48100 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 8 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

@@ -43,8 +43,8 @@ You may reuse the base model text encoder for inference.
 
 ## Training settings
 
-- Training epochs: 3
-- Training steps: 47900
+- Training epochs: 4
+- Training steps: 48100
 - Learning rate: 4e-07
 - Effective batch size: 32
   - Micro-batch size: 4

optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55437ee1a87ba0b5e2f2920ced06f0926683962997510026c1248aa02ff8a7d1
+oid sha256:6d0e0b5e7e3a4b054eea93458c5bf6a886eb9762f4f7f78a44a968ce54566a74
 size 5196082660

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06eef4e863f0cb2d4f1c3ebef5ea4e227a7afe3412954ba2f184f7b3f6a2509b
-size 14344
+oid sha256:38309691f6faf8b9b41b51a97c6ce6da401b7fd5da0b99b4f0589cff210c75c1
+size 14408

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8d5f9999db1e64b457adaeaffb11aabcf672afe162934893980b257680471e2
+oid sha256:fb6fffb96dc1f2a3f4fcca7f44c0b0d66917851d03b28ce4bc0273112c3ef7ca
 size 1000

training_state-anatomy.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9ebfd7b14fb00e7ed56d289241858548500d8871d85b43eb512184a97965c88
-size 2918420
+oid sha256:bc7ebabeb24e50537f970c1dea3109dc95d2daa550b257da75f614c620fa7515
+size 3817232

training_state-bg20k-1024.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f022b731e6de4371388f2d656f8bbac0c8752a1a8f2a1e8c920aa4c54be0f965
-size 14640381
+oid sha256:a85174631a5fcab519df40169732bc809baebc0779c57e41d5599e824982337a
+size 14640384

training_state.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59329ec50660e455792c0d18128f000b8a45def17185c4213285b5e9e8f355d3
-size 709
+oid sha256:1c8aab492141522c7ca9750de1393cd1d4cec6535c754804976ee14190e7be50
+size 708

unet/config.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a863c0c11093cf3ed22452c8abc4351d8100746e67eb6c5b8a685e1cd6370e76
+oid sha256:dbaa55df1d6169fcad066f5feb8a155a545a64ee4af4f0fb06254b8c46cb3703
 size 1878

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:589b576c8303dcbeda8530a138569a05231abef0e9bfbee7b1e04c205b84780a
+oid sha256:d4bb790bff4318ea8f0379bcb3d9fca352ce7086c09de7009adf52071dfa99a1
 size 1731905416