Hugging Face's logo

terminusresearch
/
pixart-900m-1024-ft-v0.6

Text-to-Image
Diffusers
Safetensors
PixArtSigmaPipeline
stable-diffusion
stable-diffusion-diffusers
simpletuner
full
Model card Files Community
3
PseudoTerminal X commited on
Commit
f65f789
·
verified ·
1 Parent(s): 8887e3b

Trained for 5 epochs and 7000 steps.

Browse files

Trained with datasets ['text-embeds-pixart-nofilter', 'photo-concept-bucket']
Learning rate 1e-06, batch size 32, and 2 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: PixArt-alpha/PixArt-Sigma-XL-2-1024-MS
VAE: madebyollin/sdxl-vae-fp16-fix

Files changed (7) hide show
  1. README.md +2 -2
  2. optimizer.bin +1 -1
  3. random_states_0.pkl +1 -1
  4. scheduler.bin +1 -1
  5. training_state-photo-concept-bucket.json +2 -2
  6. training_state.json +1 -1
  7. transformer/diffusion_pytorch_model.safetensors +1 -1
README.md CHANGED
@@ -1006,7 +1006,7 @@ You may reuse the base model text encoder for inference.
1006
  ## Training settings
1007
 
1008
  - Training epochs: 5
1009
- - Training steps: 6500
1010
  - Learning rate: 1e-06
1011
  - Effective batch size: 512
1012
  - Micro-batch size: 32
@@ -1024,7 +1024,7 @@ You may reuse the base model text encoder for inference.
1024
  ### photo-concept-bucket
1025
  - Repeats: 0
1026
  - Total number of images: ~550912
1027
- - Total number of aspect buckets: 3
1028
  - Resolution: 1.0 megapixels
1029
  - Cropped: False
1030
  - Crop style: None
 
1006
  ## Training settings
1007
 
1008
  - Training epochs: 5
1009
+ - Training steps: 7000
1010
  - Learning rate: 1e-06
1011
  - Effective batch size: 512
1012
  - Micro-batch size: 32
 
1024
  ### photo-concept-bucket
1025
  - Repeats: 0
1026
  - Total number of images: ~550912
1027
+ - Total number of aspect buckets: 2
1028
  - Resolution: 1.0 megapixels
1029
  - Cropped: False
1030
  - Crop style: None
optimizer.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ad3965834a6526e758b833c4ee78502327219cef375057bf1ae4faa3acd5ce9
3
  size 3665677155
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64665e38810f1a021cb8a239de747b440369c2612a7c2d2cd320b11ecc2a1859
3
  size 3665677155
random_states_0.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27b20523384276b767427a63a182510522a8c8eeee2d8d0f46f520fc61f300f3
3
  size 16100
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:deaefb46a10ce99a68e02f0da3f4ff8e58c251f251d214e54030b1b26cf340b1
3
  size 16100
scheduler.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:811775b78ef12f6bb2c279b2d12c78ba09d065f4d220a180dcff8335349e53d4
3
  size 1000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf279504429d3c2d2a5c21e1c623c13a2525b896fa37b0d59112adfbafdb6526
3
  size 1000
training_state-photo-concept-bucket.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:157d2981f8917d0cb46b82629f6c1f75f44698b7463793166ff81f3b01c788ab
3
- size 5701701
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:158bf06c93adaeaaebc834fe572d619eb8d0cf04697860780b7c6b0034cab677
3
+ size 7897798
training_state.json CHANGED
@@ -1 +1 @@
1
- {"global_step": 6500, "epoch_step": 315, "epoch": 6, "exhausted_backends": [], "repeats": {"photo-concept-bucket": 0}}
 
1
+ {"global_step": 7000, "epoch_step": 815, "epoch": 6, "exhausted_backends": [], "repeats": {"photo-concept-bucket": 0}}
transformer/diffusion_pytorch_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc1af4263f9cf7b53e03f1081e4b36d72f68358f10431b2ca8b2319bdc003bd4
3
  size 1221780352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35708525bec2c02bb3edb7ac3f780b74f0dbd86a7c79c6fc408ab7366990dd62
3
  size 1221780352