Trained for 0 epochs and 6200 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 1e-06, 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: 6100
+- Training steps: 6200
 - Learning rate: 1e-06
 - Effective batch size: 32
   - Micro-batch size: 8

optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cdc5e7b00e5ddb84ddc9add148d0107cdb01e4162254d7d1f966ef78a2dabf4
+oid sha256:9a10fb5e1f12ae63a47af73599ce9fcacd1764093aa3e323fe2b0f91a735e462
 size 15406336826

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08970e2980219f8148023dcb886246c6a2042b84fd10a782c4d7eac941b3d636
-size 14408
+oid sha256:b10c2fdff0af3d3a4e45ee5fadb2ead50ccca320698092853f2d8dda547c17d8
+size 14344

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0847d581747153869dfde03d88c3118710a01210328c907e8fd0d02e350043d
+oid sha256:17c60b6867f921b804fe31ebf89544740744482fbce717bba30c2d20a58e6a88
 size 1000

training_state-bg20k-1024.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a1b640e0eccb46753e2e265748c69aec59f2c9b5a7664e34182e7e316532977
-size 16571220
+oid sha256:51b9350da6aac8d7bac1a1375ff2c1f2f066bdbdd98af7630e3701bc1327f293
+size 16660601

training_state-photo-concept-bucket.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f6026c6111e28841806f74342d443fef2b952ad89fd031ce49c5e2648b2e7c3
-size 15558133
+oid sha256:5045944517dd21035d573eee42ad29adc24e8fe5d1b048ba39aeccb40e7a7e9e
+size 15576149

training_state.json

@@ -1 +1 @@
-{"global_step": 6100, "epoch_step": 141, "epoch": 1, "exhausted_backends": ["guys", "signs", "nijijourney", "propagandaposters", "bookcovers", "pixel-art", "normalnudes", "celebrities", "sports", "movieposters", "moviecollection", "gay", "ethnic", "experimental", "yoga", "architecture", "cinemamix-1mp"], "repeats": {"guys": 0, "signs": 0, "nijijourney": 0, "propagandaposters": 0, "bookcovers": 0, "pixel-art": 0, "normalnudes": 0, "celebrities": 0, "sports": 0, "movieposters": 0, "moviecollection": 0, "gay": 0, "ethnic": 0, "experimental": 0, "yoga": 0, "architecture": 0, "cinemamix-1mp": 0, "text-1mp": 1}}
+{"global_step": 6200, "epoch_step": 241, "epoch": 1, "exhausted_backends": ["guys", "signs", "nijijourney", "propagandaposters", "bookcovers", "pixel-art", "normalnudes", "celebrities", "sports", "movieposters", "moviecollection", "gay", "ethnic", "experimental", "yoga", "architecture", "cinemamix-1mp"], "repeats": {"guys": 0, "signs": 0, "nijijourney": 0, "propagandaposters": 0, "bookcovers": 0, "pixel-art": 0, "normalnudes": 0, "celebrities": 0, "sports": 0, "movieposters": 0, "moviecollection": 0, "gay": 0, "ethnic": 0, "experimental": 0, "yoga": 0, "architecture": 0, "cinemamix-1mp": 0, "text-1mp": 1}}

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56cb8a632382512edfefbc6316e0bda495515f095865371e03845e872de216b7
+oid sha256:dce25e4c4885ed01df9182ada5b9f15e8aec69d3821382fa08bc73b3406c4392
 size 5135151440