Trained for 0 epochs and 7000 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: 6000
+- Training steps: 7000
 - 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:ed70998267d02449989bcf35702542feac26451b366a6c6c364a65ebc2b1e8a5
+oid sha256:192bf1a4733ddcf5ee77ae72c9d5a6561556ef0dc0d793e6bce619e5b9851bc1
 size 5451415117

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a8db8db1fea598b10c0473dce4b6c76bd0b66998be5ac5bb3c216454c3d6200
-size 16036
+oid sha256:2832f2a96600350e952b9d4afd1da883de226389ba03d89efc16ca0930056069
+size 16100

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa90d1596151fc982c9df01c65a1b9accaa596352fb73dd2d76f53176687cc0d
+oid sha256:f72b16b354f840c8683806f5e4924ba5c92df6e688e00495e40ee959b0607f81
 size 1000

training_state-dalle3.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c71e2cdc1ee76e4a6cb07c96e7b96fc04eaca8c3fde758d06d8b4eaf20b31238
-size 10558965
+oid sha256:f26136d446e0fd9d87c92adc9db7a1305bbadbbc7de29c636e824cc671648d15
+size 10807060

training_state.json

@@ -1 +1 @@
-{"global_step": 6000, "epoch_step": 6000, "epoch": 1, "exhausted_backends": [], "repeats": {"ideogram": 4}}
+{"global_step": 7000, "epoch_step": 7000, "epoch": 1, "exhausted_backends": [], "repeats": {"ideogram": 5}}

transformer/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98a02c95706b6a63f6c64718fc8954d964a836cbec72a233ec1ed426a5d9f440
+oid sha256:df94e2a21d703b15a9f1b11493474ec2547287b9d592c7046e57f3ca5ab83a99
 size 1816969728