Trained for 0 epochs and 4000 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

@@ -47,7 +47,7 @@ You may reuse the base model text encoder for inference.
 ## Training settings
 
 - Training epochs: 0
-- Training steps: 3000
+- Training steps: 4000
 - Learning rate: 1e-06
 - Effective batch size: 64
   - Micro-batch size: 8
@@ -264,7 +264,7 @@ You may reuse the base model text encoder for inference.
 - Crop aspect: square
 ### text-1mp
 - Repeats: 5
-- Total number of images: ~21648
+- Total number of images: ~13184
 - 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 sha256:1813afb7a7c1272acbbfb6c2cb102348e75692b4a515aee372c11ce72fd0dbe2
+oid sha256:e861197a488cf8ef6782847f8bff57e7ada99f1ce995de4081005726907de0d4
 size 5451415117

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2e8d54983a440a40b202eaad0cb0f9f3303edac7a38289a9da1e0c5ec85c105
+oid sha256:6dc018ab41b0de5f3a222606c72711dd53073f28d20958434495a4459a84eed2
 size 16100

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac6062d6edf2a0bf8323ce35a6efa2e6c325456ac2d06268cfb156bf5fbbc675
+oid sha256:2e444b415a7f5db45cce0c300151c0661ab640d5869dbc46bf7bf27bd8201bf8
 size 1000

training_state-dalle3.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c14e58671e9f73d64e672d19e756426d1435a24e35275f77f7c4a0e9fbdcd03b
-size 8224186
+oid sha256:f99704b07ce7cb99296dc3f7c268b1129d2929995dd3686a83e8d7a9ef0cbf73
+size 8269351

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fce5abed15c34617511440f8ddc95e9c1ec3526a648ad9a225c7992132ba33f2
-size 2393394
+oid sha256:2db3cd75f255e2d9979502ba3d020b7678629556c3ac38c4e88f5ced5d65c6ea
+size 2431554

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:758ee24ab48a0e7d69b405a1d55ccf018eb8b62dc801de5f9c93611a840ffffb
-size 2544602
+oid sha256:b7ca524d4767b90853027459b96998b20df0ced20f59aab501664b3a4c9ac3c8
+size 2585730

training_state.json

@@ -1 +1 @@
-{"global_step": 3000, "epoch_step": 3000, "epoch": 1, "exhausted_backends": ["nijijourney", "signs", "guys", "celebrities", "bookcovers", "normalnudes", "moviecollection", "sports", "gay", "experimental", "yoga", "ethnic", "architecture", "cinemamix-1mp", "photo-aesthetics"], "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": 1}}
+{"global_step": 4000, "epoch_step": 4000, "epoch": 1, "exhausted_backends": ["nijijourney", "signs", "guys", "celebrities", "bookcovers", "normalnudes", "moviecollection", "sports", "gay", "experimental", "yoga", "ethnic", "architecture", "cinemamix-1mp", "photo-aesthetics"], "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": 1, "text-1mp": 1}}

transformer/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4a4414da898a18a92d146e38527f5b7944c3dfef5f6c30819e4914c8ff6a8e2
+oid sha256:7f2b1f9ba9ad09ec44ea3eef43b03862949f9e6fdc4a3ace03f55a753939b538
 size 1816969728