Trained for 7 epochs and 99000 steps.

Trained with datasets ['text-embeds-pixart-filter', 'photo-concept-bucket']
Learning rate 1e-06, batch size 24, 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-large
VAE: madebyollin/sdxl-vae-fp16-fix

README.md

@@ -1291,8 +1291,8 @@ You may reuse the base model text encoder for inference.
 
 ## Training settings
 
-- Training epochs: 6
-- Training steps: 98000
+- Training epochs: 7
+- Training steps: 99000
 - Learning rate: 1e-06
 - Effective batch size: 192
   - Micro-batch size: 24

optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77af603403560ef53d7c7a9f182b6a846f586635e41e5cc21ada848ebc7bf25e
+oid sha256:a3ef8c034fe3a2f33597ab42ec0258930c815b66d3868cc9f819bd7fce8b21ae
 size 5451415117

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0df0a967a9628eb95f77e5df4da8d333955278fdfc2342ae87b1f34953d4f31b
-size 16036
+oid sha256:63b6fab2fa5d5eda067c0e15e07bdafda7e7170a1838b24efaf1706b40a9ff1d
+size 16100

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af4767cc2a894671f3250d4b86b2ad3568d6c9e75b3b29afe13e9985acbb6327
+oid sha256:2781c871232fc2f4481dac795190a70a0e26ca2a9a93a7b3c66fcfdfa530ace3
 size 1000

training_state-photo-concept-bucket.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ebbc2f5192a3ac92956584eb572f8972f3295c949c2139f4f38fa50cdd930ae
-size 10343091
+oid sha256:7778c5eba4f5e0256e3cdd70087def9164d19ebbef803554b0dd09b7bf8559f0
+size 6556704

training_state.json

@@ -1 +1 @@
-{"global_step": 98000, "epoch_step": 1, "epoch": 7, "exhausted_backends": [], "repeats": {"bookcovers": 0, "signs": 0, "normalnudes": 0, "nijijourney": 0, "movieposters": 0, "celebrities": 0, "pixel-art": 0, "propagandaposters": 0, "sports": 0, "moviecollection": 0, "gay": 0, "experimental": 0, "yoga": 0, "ethnic": 0, "cinemamix-1mp": 0, "architecture": 0, "mj-60": 0, "text-1mp": 65, "shutterstock": 0, "nsfw-1024": 0, "photo-aesthetics": 0, "anatomy": 0, "bg20k-1024": 0, "sfwbooru": 0, "midjourney-v6-520k-raw": 0, "nijijourney-v6-520k-raw": 0, "photo-concept-bucket": 0, "dalle3": 0}}
+{"global_step": 99000, "epoch_step": 1, "epoch": 8, "exhausted_backends": [], "repeats": {"bookcovers": 0, "signs": 0, "normalnudes": 0, "nijijourney": 0, "movieposters": 0, "celebrities": 0, "pixel-art": 0, "propagandaposters": 0, "sports": 0, "moviecollection": 0, "gay": 0, "experimental": 0, "yoga": 0, "ethnic": 0, "cinemamix-1mp": 0, "architecture": 0, "mj-60": 0, "text-1mp": 65, "shutterstock": 0, "nsfw-1024": 0, "photo-aesthetics": 0, "anatomy": 0, "bg20k-1024": 0, "sfwbooru": 0, "midjourney-v6-520k-raw": 0, "nijijourney-v6-520k-raw": 0, "photo-concept-bucket": 0, "dalle3": 0}}

transformer/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ad5dac03fc30491ecb807b84971340bea313581d685a60c8432a5daf4fad833
+oid sha256:a77717d9f4aa7d86aabfa047dad9df64bace30e3c2f53ef0702b830e23a5fff8
 size 1816969728