Trained for 0 epochs and 14000 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: 0
-- Training steps: 13000
+- Training steps: 14000
 - Learning rate: 1e-06
 - Effective batch size: 64
   - Micro-batch size: 8
@@ -745,7 +745,7 @@ You may reuse the base model text encoder for inference.
 - Crop aspect: square
 ### bg20k-1024
 - Repeats: 0
-- Total number of images: ~96144
+- Total number of images: ~89280
 - Total number of aspect buckets: 1
 - Resolution: 1.0 megapixels
 - Cropped: True

optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4868b92276722b1933329266e59598a4fd03fe5fec74c38d3b6384a972105150
+oid sha256:1857c5f9adcda776ef7c9688bc9a9c0144bb3aca987b9f3064f93d395b05c923
 size 5451415117

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdb779847c6407bd72fef47db78a0c19240084e99ab01ce6cc2c8039e31792a5
+oid sha256:66dffa94b856a6a7895665fcca3ca90f715d275c1a08cfba01ee173f88cc4c3f
 size 16100

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89abbd8f098bd47be661e04b3effa9b2fa5b2e0231d0bc3148a87905693b90d1
+oid sha256:018e5f0be85fac7c8f72ef95e2008e0f67b1111fbda2f4aac103c502e30f9d50
 size 1000

training_state-dalle3.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db94ceda26f3c7617c17d484153812ab33668d8f90d4f135ffe8b429171f4921
-size 8849393
+oid sha256:b885da8af401f1ce4ee1491df7c80bf279232f28e45489c504630003db8aa53e
+size 8931082

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68a586826e97be9081daa1c4f9c9241bea5d1a1c0eb565d1fb5ba31ba678edfa
-size 2937810
+oid sha256:37867328450a47f848c01e66723e3b9f666e34ab31d12de50cbf262e3c47a105
+size 3014554

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2355449044be2e937cd51129aa0f0a5759f004c8b0e76a66893e283239a9981
-size 3041954
+oid sha256:87fe91e1d658e78ba3c3aea7bc0a75713a80a0c6c45997b7ee50df1eb9e2fff0
+size 3122090

training_state.json

@@ -1 +1 @@
-{"global_step": 13000, "epoch_step": 13000, "epoch": 1, "exhausted_backends": ["nijijourney", "signs", "guys", "celebrities", "bookcovers", "normalnudes", "moviecollection", "sports", "gay", "experimental", "yoga", "ethnic", "architecture", "cinemamix-1mp", "photo-aesthetics", "nsfw-1024", "shutterstock", "id-75k", "text-1mp"], "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": 3, "text-1mp": 0, "nsfw-1024": 0, "shutterstock": 0, "id-75k": 0}}
+{"global_step": 14000, "epoch_step": 14000, "epoch": 1, "exhausted_backends": ["nijijourney", "signs", "guys", "celebrities", "bookcovers", "normalnudes", "moviecollection", "sports", "gay", "experimental", "yoga", "ethnic", "architecture", "cinemamix-1mp", "photo-aesthetics", "nsfw-1024", "shutterstock", "id-75k", "text-1mp", "bg20k-1024"], "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": 4, "text-1mp": 0, "nsfw-1024": 0, "shutterstock": 0, "id-75k": 0, "bg20k-1024": 0}}

transformer/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf4e835420892dfc6236a210737668b7b024b153a2e33c4a4845dda704e00be6
+oid sha256:8e92362056860098a57514125a3b1971f7dd26bdec8932a202305883c9bff1fd
 size 1816969728