Trained for 6 epochs and 206000 steps.

Trained with datasets ['text-embeds', 'text-embeds-extra', 'image-embeds', 'sports', 'mj-60', 'id-75k', 'celebrities', 'normalnudes', 'guys', 'signs', 'dalle3', 'sfwbooru', 'moviecollection', 'bookcovers', 'nijijourney', 'experimental', 'ethnic', 'gay', 'architecture', 'shutterstock', 'midjourney-v6-520k-raw', 'nijijourney-v6-520k-raw', 'cinemamix-1mp', 'nsfw-1024', 'anatomy', 'bg20k-1024', 'yoga', 'photo-aesthetics', 'text-1mp']
Learning rate 1e-06, batch size 8, and 1 gradient accumulation steps.
Used DDPM noise scheduler for training with epsilon prediction type and rescaled_betas_zero_snr=False
Using 'linspace' timestep spacing.
Base model: ptx0/pixart-900m-1024-ft-v0.7-stage1
VAE: ptx0/pixart-900m-1024-ft-v0.7-stage1

README.md

@@ -552,7 +552,7 @@ You may reuse the base model text encoder for inference.
 ## Training settings
 
 - Training epochs: 6
-- Training steps: 205000
+- Training steps: 206000
 - Learning rate: 1e-06
 - Effective batch size: 64
  - Micro-batch size: 8

optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ad94b5acb1c8900508c61daf2ed67fe1371f7adf1f0308e16fb4e378b5fdf1d
+oid sha256:0a5d8cc322df998eda6a4a1b177e9bb0e407718d3b2bb721d444dc95ae7eb52e
 size 5451415117

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ea84b1221c5a7ca4d1ccea5ec0858ca545d4fa515a8aec5b69cb3e3ce9a2037
+oid sha256:19f4a5d3d6bf22f365aad079cac7301cf4c2cbaee2aa10f8184c1f7247aae3ea
 size 16036

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a278d23889d0af87147bee4036087690e9d5d1b7b6c2bb7a22df9db176579f29
+oid sha256:eee7deefbcc62d2620f5e06cc53f5d56328b627baae2bdd0b0fc559063ddac30
 size 1000

training_state-dalle3.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33e3ece871848dbf2faf73c1725659255e56a16e73097d6e1f32273665210e45
-size 8227525
+oid sha256:f0e6792252bab2af520f72477accad3b3a707587c89eca3653c7a3f18d792e9d
+size 8274232

training_state-midjourney-v6-520k-raw.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ca4b487f74588e7971e6d9f6e4e1c664d01f96a9dc719c99cb5900ebcd5f526
-size 2395938
+oid sha256:58d341ea570fd667ff9b58be2efbfcf267ff29dd187c389fb7d526266f130394
+size 2440034

training_state-nijijourney-v6-520k-raw.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b60a20743c1a3d58125f08ef2865aa32048cae30c676dfd11413595e652fc9a
-size 2540362
+oid sha256:dfbd8b18242cfa8a6eabeef6d57a2a1efd1afe785206b2ad254642573c072584
+size 2583186

training_state.json

@@ -1 +1 @@
-{"global_step": 205000, "epoch_step": 205006, "epoch": 7, "exhausted_backends": ["nijijourney", "guys", "signs", "normalnudes", "bookcovers", "celebrities", "sports", "moviecollection", "gay", "yoga", "experimental", "ethnic", "cinemamix-1mp", "architecture"], "repeats": {"nijijourney": 0, "signs": 0, "guys": 0, "celebrities": 0, "bookcovers": 0, "normalnudes": 0, "moviecollection": 0, "sports": 0, "gay": 0, "experimental": 0, "yoga": 0, "ethnic": 0, "architecture": 0, "cinemamix-1mp": 0, "photo-aesthetics": 0, "anatomy": 0, "text-1mp": 0, "nsfw-1024": 0, "shutterstock": 0, "id-75k": 0, "bg20k-1024": 0, "mj-60": 0, "sfwbooru": 0, "midjourney-v6-520k-raw": 0, "nijijourney-v6-520k-raw": 0, "dalle3": 0}}
+{"global_step": 206000, "epoch_step": 206006, "epoch": 7, "exhausted_backends": ["nijijourney", "guys", "signs", "normalnudes", "bookcovers", "celebrities", "sports", "moviecollection", "gay", "yoga", "experimental", "ethnic", "cinemamix-1mp", "architecture"], "repeats": {"nijijourney": 0, "signs": 0, "guys": 0, "celebrities": 0, "bookcovers": 0, "normalnudes": 0, "moviecollection": 0, "sports": 0, "gay": 0, "experimental": 0, "yoga": 0, "ethnic": 0, "architecture": 0, "cinemamix-1mp": 0, "photo-aesthetics": 0, "anatomy": 0, "text-1mp": 1, "nsfw-1024": 0, "shutterstock": 0, "id-75k": 0, "bg20k-1024": 0, "mj-60": 0, "sfwbooru": 0, "midjourney-v6-520k-raw": 0, "nijijourney-v6-520k-raw": 0, "dalle3": 0}}

transformer/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45b756e24c8c15dbd2931916c1144b28f34bfd8f661509e8a75e032c765ea81b
+oid sha256:29153a3bada6498f49b9fd4ccaf8a1062cc7ecb1357d877065370ec495b17334
 size 1816969728