Trained for 0 epochs and 8000 steps.

Trained with datasets ['text-embeds-pixart-filter', 'photo-concept-bucket', 'ideogram', 'midjourney-v6-520k-raw', 'sfwbooru', 'nijijourney-v6-520k-raw', 'dalle3']
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 'trailing' timestep spacing.
Base model: terminusresearch/pixart-900m-1024-ft-v0.6
VAE: madebyollin/sdxl-vae-fp16-fix

README.md

@@ -1562,7 +1562,7 @@ You may reuse the base model text encoder for inference.
 ## Training settings
 
 - Training epochs: 0
-- Training steps: 7000
+- Training steps: 8000
 - 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 sha256:192bf1a4733ddcf5ee77ae72c9d5a6561556ef0dc0d793e6bce619e5b9851bc1
+oid sha256:af0760c828c42e0b3d376b13b304561984da274521f4f3979709e79c02d3e50a
 size 5451415117

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2832f2a96600350e952b9d4afd1da883de226389ba03d89efc16ca0930056069
-size 16100
+oid sha256:6dedaac6f306fe9db118699313b9b306daabc6d5451b7e947e47f91136d6eca1
+size 16164

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f72b16b354f840c8683806f5e4924ba5c92df6e688e00495e40ee959b0607f81
+oid sha256:dbd56ac68ba3b8763227c7d94f5939ee50822f12eda29b2e9914934807520f04
 size 1000

training_state-dalle3.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f26136d446e0fd9d87c92adc9db7a1305bbadbbc7de29c636e824cc671648d15
-size 10807060
+oid sha256:e7bdbd7a4af8d85233be5d863005a1cb5355202ba810578915f71ec3c0306bcf
+size 11163524

training_state.json

@@ -1 +1 @@
-{"global_step": 7000, "epoch_step": 7000, "epoch": 1, "exhausted_backends": [], "repeats": {"ideogram": 5}}
+{"global_step": 8000, "epoch_step": 8000, "epoch": 1, "exhausted_backends": ["sfwbooru"], "repeats": {"ideogram": 6, "sfwbooru": 0}}

transformer/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df94e2a21d703b15a9f1b11493474ec2547287b9d592c7046e57f3ca5ab83a99
+oid sha256:8027c5070082862b80f72e60b4b41ee07adc943f120240291e436c8d1bedae18
 size 1816969728