Hugging Face's logo

terminusresearch
/
pixart-900m-1024-ft-v0.7-stage1

Text-to-Image
Diffusers
Safetensors
PixArtSigmaPipeline
stable-diffusion
stable-diffusion-diffusers
simpletuner
full
Model card Files Community
PseudoTerminal X commited on
Commit
64d4dd2
·
verified ·
1 Parent(s): e2b6256

Trained for 0 epochs and 16000 steps.

Browse files

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

Files changed (9) hide show
  1. README.md +1 -1
  2. optimizer.bin +1 -1
  3. random_states_0.pkl +1 -1
  4. scheduler.bin +1 -1
  5. training_state-dalle3.json +2 -2
  6. training_state-ideogram.json +0 -0
  7. training_state-photo-concept-bucket.json +2 -2
  8. training_state.json +1 -1
  9. transformer/diffusion_pytorch_model.safetensors +1 -1
README.md CHANGED
@@ -1562,7 +1562,7 @@ You may reuse the base model text encoder for inference.
1562
  ## Training settings
1563
 
1564
  - Training epochs: 0
1565
- - Training steps: 15000
1566
  - Learning rate: 1e-06
1567
  - Effective batch size: 192
1568
  - Micro-batch size: 24
 
1562
  ## Training settings
1563
 
1564
  - Training epochs: 0
1565
+ - Training steps: 16000
1566
  - Learning rate: 1e-06
1567
  - Effective batch size: 192
1568
  - Micro-batch size: 24
optimizer.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7020cdc7a68ebe3852562ab9276b51876397848c7c7e45452d4eaeeb660a38dd
3
  size 5451415117
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32c0e62a2d0eb3efdfbb5694d1ac9573ef31c03dbe5b53a6c27d1290e9360968
3
  size 5451415117
random_states_0.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a7035753e1f6d8d51f9b4d6e8d7d20e304c2b2b786cea503cd553f264b1aa360
3
  size 16100
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:350de7ae1418fa7b010063fd2f9bcb3a2d3b59b467b4682cbaa27d69db810ed9
3
  size 16100
scheduler.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b2ac715c0ba8403b036157be3f4d2ac9044856a90437d0bfc1ff762db4c531a
3
  size 1000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6106345e0827a56561fdaabce80c1bb21548d10500693aa9145c0daa7211e467
3
  size 1000
training_state-dalle3.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be1252668766b788d9db64249ee12235b351942fb0f717829856d8b7c004474a
3
- size 13692924
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b136673655d870bd1d77fb99002497e186ed852b0c5df42b2d4fe5e152415d52
3
+ size 14741466
training_state-ideogram.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_state-photo-concept-bucket.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:93cb9fafc9791cf3ce1960ef08c83f061ef97c471e3572101681d2162ff40355
3
- size 10850153
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c3c80ad7c7948bd2b7d9051be20769eeac54003b3ebcad4961282da588d418a
3
+ size 5296539
training_state.json CHANGED
@@ -1 +1 @@
1
- {"global_step": 15000, "epoch_step": 15000, "epoch": 1, "exhausted_backends": ["sfwbooru", "nijijourney-v6-520k-raw", "midjourney-v6-520k-raw", "text-1mp"], "repeats": {"ideogram": 14, "sfwbooru": 0, "text-1mp": 0, "nijijourney-v6-520k-raw": 0, "midjourney-v6-520k-raw": 0}}
 
1
+ {"global_step": 16000, "epoch_step": 16000, "epoch": 1, "exhausted_backends": ["sfwbooru", "nijijourney-v6-520k-raw", "midjourney-v6-520k-raw", "text-1mp", "photo-concept-bucket", "ideogram"], "repeats": {"ideogram": 0, "sfwbooru": 0, "text-1mp": 0, "nijijourney-v6-520k-raw": 0, "midjourney-v6-520k-raw": 0, "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 sha256:8e64d645a4c056809388522ef7d018139da4349596189e608ae87d2166706290
3
  size 1816969728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1464fadaf92a36a16dca025a5a8e7b484674711a16c09139db87040d11bc20d
3
  size 1816969728