Trained for 5 epochs and 93000 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

@@ -46,8 +46,8 @@ You may reuse the base model text encoder for inference.
 
 ## Training settings
 
-- Training epochs: 4
-- Training steps: 92000
+- Training epochs: 5
+- Training steps: 93000
 - 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 sha256:2caabfaea767ffa9b48fb41687610f1427b527e24358b2963a849248d7489221
+oid sha256:ef3444f9f9870d57e5b7261a3f2314fea6942c422ea956119f1c3d64fa1464de
 size 5451415117

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30c62744c650eb2a6c45cd930937eff439b05f341b91185dbc9d3cbe7bd9e70e
+oid sha256:38e091d7cf5068dc815330db381d5b8b62819d70445d8f9d6628c87d7b307a5b
 size 16036

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9eab47c67e333e4f8095ffe0c186876608397ab4096d0edff6e510eaa21865d
+oid sha256:9efa5f0a3ea200d041d590ceec1f3f71ea40582349d9d94dd8ec9203fa94ef87
 size 1000

training_state-photo-concept-bucket.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be7a65240d5c4f4bb9e6ce19fb22b2076b63184253b9b916752f8cfdc99a7f62
-size 10172610
+oid sha256:23a3962df8a590a24af6f376dffa694a1498ebf8bc23762dc05a3af4460595da
+size 6386271

training_state.json

@@ -1 +1 @@
-{"global_step": 92000, "epoch_step": 1, "epoch": 5, "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": 93000, "epoch_step": 1, "epoch": 6, "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 sha256:6116e9d9d251fc25b7f9ce6bad84f9109b0a733d7706c3c6b04b807cef986913
+oid sha256:781e59b6b00d4358a6d28fe04f5238a4a8e4ce2178bb84b681b7d1855bbac408
 size 1816969728