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
c6c2f1a
·
verified ·
1 Parent(s): f62e67b

Trained for 3 epochs and 77000 steps.

Browse files

Trained with datasets ['text-embeds-pixart-filter', 'photo-concept-bucket', '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 'linspace' timestep spacing.
Base model: ptx0/pixart-900m-1024-ft-large
VAE: madebyollin/sdxl-vae-fp16-fix

Files changed (11) 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-midjourney-v6-520k-raw.json +2 -2
  7. training_state-nijijourney-v6-520k-raw.json +2 -2
  8. training_state-photo-concept-bucket.json +2 -2
  9. training_state-sfwbooru.json +0 -0
  10. training_state.json +1 -1
  11. transformer/diffusion_pytorch_model.safetensors +1 -1
README.md CHANGED
@@ -1292,7 +1292,7 @@ You may reuse the base model text encoder for inference.
1292
  ## Training settings
1293
 
1294
  - Training epochs: 3
1295
- - Training steps: 76000
1296
  - Learning rate: 1e-06
1297
  - Effective batch size: 192
1298
  - Micro-batch size: 24
 
1292
  ## Training settings
1293
 
1294
  - Training epochs: 3
1295
+ - Training steps: 77000
1296
  - Learning rate: 1e-06
1297
  - Effective batch size: 192
1298
  - Micro-batch size: 24
optimizer.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:73d3899060eee1b2f9d92609f3a103e6aa8d9315095744c2dd4e445a0fdd6035
3
  size 5451415117
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42276827bbd0bd34979e73d829c082f6f8675beb3a1e73610f6cd3597a780c91
3
  size 5451415117
random_states_0.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:360a1af8c47f7c12c7c5d10288b5250fc149a6472c17801e899f96388ad740e4
3
  size 16100
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a820b2a8746ed694ad9f3aea133039efaa84e002a72487a1c3ac799e1e3547c
3
  size 16100
scheduler.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b101b57a6a6673aadd5e8220f61744398c1ec0d635d5661ee3751695194fbbd7
3
  size 1000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85164d055bb03b403b032d8b1546cbd2ef79d2fdc7739bc38ddf6b228e862e64
3
  size 1000
training_state-dalle3.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:02f39a0c01110f33ceb6c4fef79f5edc8c9de5f42e5a26186fc6daa65167e6e9
3
- size 9784537
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cb219711b294b051d8caed9ba5dc686ce967ea574204f7ed99b9862dbb879d8
3
+ size 10161985
training_state-midjourney-v6-520k-raw.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8066a84af837886cd1552e2302fdde547f17c5202939436c14416c53fd366129
3
- size 6183619
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f1d91ba9b21076fb2560a87888aebcc4d7d35c6ba1dbfa84e44fc3aa3a956f4
3
+ size 6675547
training_state-nijijourney-v6-520k-raw.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:33ff7e2ce93eed0c7c85129ee1b4be5c990fd6ea0dd0efa768271759c7e36883
3
- size 6803203
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2f2e51f85deaf04010e7b6e82052e6fad97635dfba4a6148203a9681606ea55
3
+ size 7370803
training_state-photo-concept-bucket.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f8e1d556d248300ff7d23f49c15947c9c6eee2f8d70a1ce0be2a54232ead7b9f
3
- size 6430768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0ced7c084a49ac7ac7d3d39cbbd27909816c965aa7ee063fb6fb230ef3e3714
3
+ size 6814083
training_state-sfwbooru.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_state.json CHANGED
@@ -1 +1 @@
1
- {"global_step": 76000, "epoch_step": 1, "epoch": 4, "exhausted_backends": [], "repeats": {"bookcovers": 0, "signs": 0, "normalnudes": 0, "nijijourney": 0, "movieposters": 0, "celebrities": 0, "pixel-art": 0, "propagandaposters": 0, "sports": 0, "moviecollection": 0, "gay": 0, "experimental": 0, "yoga": 0, "ethnic": 0, "cinemamix-1mp": 0, "architecture": 0, "mj-60": 0, "text-1mp": 65, "shutterstock": 0, "nsfw-1024": 0, "photo-aesthetics": 0, "anatomy": 0, "bg20k-1024": 0, "sfwbooru": 0, "midjourney-v6-520k-raw": 0, "nijijourney-v6-520k-raw": 0, "photo-concept-bucket": 0, "dalle3": 0}}
 
1
+ {"global_step": 77000, "epoch_step": 1, "epoch": 4, "exhausted_backends": [], "repeats": {"bookcovers": 0, "signs": 0, "normalnudes": 0, "nijijourney": 0, "movieposters": 0, "celebrities": 0, "pixel-art": 0, "propagandaposters": 0, "sports": 0, "moviecollection": 0, "gay": 0, "experimental": 0, "yoga": 0, "ethnic": 0, "cinemamix-1mp": 0, "architecture": 0, "mj-60": 0, "text-1mp": 65, "shutterstock": 0, "nsfw-1024": 0, "photo-aesthetics": 0, "anatomy": 0, "bg20k-1024": 0, "sfwbooru": 0, "midjourney-v6-520k-raw": 0, "nijijourney-v6-520k-raw": 0, "photo-concept-bucket": 0, "dalle3": 0}}
transformer/diffusion_pytorch_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:512c158435e95980529a37bd15555fbd1165db85a53fc2f030d5a622453bc5c9
3
  size 1816969728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:663e4bdb75bbfa13e7235f1f82c07c087307715b0111c4acc3a548d097b917b2
3
  size 1816969728