Trained for 1 epochs and 2000 steps.

Trained with datasets ['text-embeds', 'mj-v6']
Learning rate 8e-06, batch size 2, 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: ptx0/pixart-900m-1024-ft
VAE: madebyollin/sdxl-vae-fp16-fix

README.md

@@ -211,7 +211,7 @@ You may reuse the base model text encoder for inference.
 ## Training settings
 
 - Training epochs: 1
-- Training steps: 1500
+- Training steps: 2000
 - Learning rate: 8e-06
 - Effective batch size: 2
   - Micro-batch size: 2

optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa4ae04e2d59f88dc639f2e3ec74478108b769a708f7a3d6814724ea05f391c9
+oid sha256:898539234bc565eebda477ad9ffe9e61df2e6ed7d6139df940d8f80ba49f7bac
 size 5451415117

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63ea7e5d2aee2b5f8b4a45c53fbed9b710e4f3106323efaed0b7728787344435
+oid sha256:a255dbade4def9deac767af6f6f22491136da38a67b5b24bfae79df5ba3ba6bf
 size 14344

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e9401b92a0437e861b78763e41ede39d20dc2bdd763568f11b5463d73323d27
+oid sha256:2eb1cce730426e835242d18b368f2e671b3eb662cbe1682f8619450b7c2c1bb9
 size 1000

training_state.json

@@ -1 +1 @@
-{"global_step": 1500, "epoch_step": 410, "epoch": 2, "exhausted_backends": [], "repeats": {"mj-v6": 0}}
+{"global_step": 2000, "epoch_step": 910, "epoch": 2, "exhausted_backends": [], "repeats": {"mj-v6": 0}}

transformer/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69235b3b54174dbd958d9a6db848cc2a081fa0c0c8ef5261bbd6f0278b004026
+oid sha256:20c760818e3cee478842dec8eba1538adfabbca70c84e120df6695793e2186dc
 size 1816969728