Trained for 0 epochs and 6000 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

.gitattributes

@@ -324,3 +324,4 @@ assets/image_97_1.png filter=lfs diff=lfs merge=lfs -text
 assets/image_98_2.png filter=lfs diff=lfs merge=lfs -text
 assets/image_99_0.png filter=lfs diff=lfs merge=lfs -text
 assets/image_9_0.png filter=lfs diff=lfs merge=lfs -text
+training_state-dalle3.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1562,7 +1562,7 @@ You may reuse the base model text encoder for inference.
 ## Training settings
 
 - Training epochs: 0
-- Training steps: 5000
+- Training steps: 6000
 - 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 sha256:1c189c64ecb26612d52b33c52e59d34c489c6568623b94afc0be757f4e58f8dc
+oid sha256:ed70998267d02449989bcf35702542feac26451b366a6c6c364a65ebc2b1e8a5
 size 5451415117

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bfbcba7049d59c14811d4950b2a078d97a1b0cde3a7fd38840a1c206b26ecc8
-size 16100
+oid sha256:2a8db8db1fea598b10c0473dce4b6c76bd0b66998be5ac5bb3c216454c3d6200
+size 16036

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6db68071d6a3fca0758715a9a86721a7db2e381ba247175f7f1d75233038ba6d
+oid sha256:fa90d1596151fc982c9df01c65a1b9accaa596352fb73dd2d76f53176687cc0d
 size 1000

training_state.json

@@ -1 +1 @@
-{"global_step": 5000, "epoch_step": 5000, "epoch": 1, "exhausted_backends": [], "repeats": {"ideogram": 3}}
+{"global_step": 6000, "epoch_step": 6000, "epoch": 1, "exhausted_backends": [], "repeats": {"ideogram": 4}}

transformer/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ae41b9372b99b3274eacc8c3c39bdb1ec46a86364153c3fb48d6e7020ba5fa0
+oid sha256:98a02c95706b6a63f6c64718fc8954d964a836cbec72a233ec1ed426a5d9f440
 size 1816969728