Trained for 0 epochs and 10000 steps.

Trained with datasets ['text-embeds-pixart-filter', 'photo-concept-bucket', 'text-1mp', '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: 9000
+- Training steps: 10000
 - Learning rate: 1e-06
 - Effective batch size: 192
   - Micro-batch size: 24
@@ -1585,6 +1585,14 @@ You may reuse the base model text encoder for inference.
 - Cropped: True
 - Crop style: random
 - Crop aspect: square
+### text-1mp
+- Repeats: 15
+- Total number of images: ~13056
+- Total number of aspect buckets: 1
+- Resolution: 1.0 megapixels
+- Cropped: True
+- Crop style: random
+- Crop aspect: square
 ### ideogram
 - Repeats: 15
 - Total number of images: ~36096

optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db320a3a30003b84ce972a8199c2d6ec5c9e2adf58a70671613f6244e42219cc
+oid sha256:02b0d581baaedf9a359931ce85b0bc1ff20b03ee0974e26817b4d4ea6c24d943
 size 5451415117

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b82e5a39ad6fa38decb37e51db4eb4c424849104cc2730bedfe9d4624e18d7af
-size 16036
+oid sha256:241516161f28420a23ee30cdbe589d5577647a66468942582715acd0fb9aacd3
+size 16100

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a75a07a445e729186793318d013c36b066f1cd41dec2ae7f9542745153948c5
+oid sha256:ec3386c1a1e3165e95e087cc5fed219f9a936cfdaf927dc9d05a2255eb24e135
 size 1000

training_state-dalle3.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dd700e1f52211880f97997332585926e43a97bb66e0834fd792155b3f62c76d
-size 11534817
+oid sha256:da0b6577c4e6655c3f3c18f4c249ac901435373d3ab7c2d002c8a75ffba40abb
+size 11809752

training_state.json

@@ -1 +1 @@
-{"global_step": 9000, "epoch_step": 9000, "epoch": 1, "exhausted_backends": ["sfwbooru"], "repeats": {"ideogram": 7, "sfwbooru": 0}}
+{"global_step": 10000, "epoch_step": 10000, "epoch": 1, "exhausted_backends": ["sfwbooru"], "repeats": {"ideogram": 8, "sfwbooru": 0, "text-1mp": 2}}

transformer/config.json

@@ -1,7 +1,7 @@
 {
   "_class_name": "PixArtTransformer2DModel",
   "_diffusers_version": "0.30.0.dev0",
-  "_name_or_path": "/home/ubuntu/training/models/checkpoint-1000",
+  "_name_or_path": "/home/ubuntu/training/models/checkpoint-9000",
   "activation_fn": "gelu-approximate",
   "attention_bias": true,
   "attention_head_dim": 72,

transformer/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef30c9c45d4932a0a889447742a96e924ed8371c4713b3571e21a594e9c0bdf9
+oid sha256:d513286e10914ce5d1b124ae3ac44d58dd1f0a0acfb5c770c5bcb069699e8a79
 size 1816969728