Trained for 5 epochs and 175000 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: 5
-- Training steps: 174000
+- Training steps: 175000
 - 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:bcf1e27aaa0b64f3882a180222c21be19f0e617dd594421ce80b7863cbbeea22
+oid sha256:6ae8fc730c6689a13da74b6deb0dcc5b94dbc40234c428db5f49ec81556c95d3
 size 5451415117

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e97c5637e7976cc43f95fccfda552ed0f4730f32a049273225f110f2fe4d5f5
+oid sha256:6355d6a3a84fb328082d75961308ef48affe650c2eaed84ce1ec729a7d6b0aa9
 size 16036

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71be2f1014f37c7a42fd5b08a68e86ab17f99b72de0bd26b474c5dd4673f931d
+oid sha256:281dbfc5c4ad3ffb536c53c8ad99671b468925adf6574320595e53e218ea8650
 size 1000

training_state-dalle3.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fd1f18d0273aef8016d04c069be53fbf693974f0971328f76137612c826bc2c
-size 15002118
+oid sha256:95071e7bcebf7154c2a754f4c735244af9d4c6773df5d75bebd723b9089f118f
+size 15062807

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dfec7c3f051ac6a12e271ac531bbcffc2e7cb527aeb95845a1d05718f4e8434
-size 2437490
+oid sha256:ceddbf6554827b865081bc55e843e5114e6b3a03459c9a374dadc136ae90b54a
+size 2480314

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f497769fe431a8f19416b7250da63dfb307f8313fc291d6f27a2ad0a5db7ed6c
-size 2587426
+oid sha256:9d650b4de06df4d35d7750feee71d155e898b2ae3e4be6aa3df49348740c306f
+size 2626858

training_state.json

@@ -1 +1 @@
-{"global_step": 174000, "epoch_step": 174005, "epoch": 6, "exhausted_backends": ["signs", "guys", "nijijourney", "bookcovers", "celebrities", "normalnudes", "sports", "moviecollection", "gay", "experimental", "yoga", "cinemamix-1mp", "ethnic", "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}}
+{"global_step": 175000, "epoch_step": 175005, "epoch": 6, "exhausted_backends": ["signs", "guys", "nijijourney", "bookcovers", "celebrities", "normalnudes", "sports", "moviecollection", "gay", "experimental", "yoga", "cinemamix-1mp", "ethnic", "architecture", "shutterstock", "nsfw-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": 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 sha256:26dae8a4c9a8cbba0b1c9ca2476a41865f4b40e60aeece03987c831e500b7682
+oid sha256:f862773aa904b8191ed3f4841cd933454d8424be18a7222864f495791ddc4ccc
 size 1816969728