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
8ba085a
•
1 Parent(s): 5b7439e

Trained for 4 epochs and 88000 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 +2 -2
  2. optimizer.bin +1 -1
  3. random_states_0.pkl +2 -2
  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
@@ -1216,8 +1216,8 @@ You may reuse the base model text encoder for inference.
1216
 
1217
  ## Training settings
1218
 
1219
- - Training epochs: 3
1220
- - Training steps: 87000
1221
  - Learning rate: 1e-06
1222
  - Effective batch size: 192
1223
  - Micro-batch size: 24
 
1216
 
1217
  ## Training settings
1218
 
1219
+ - Training epochs: 4
1220
+ - Training steps: 88000
1221
  - Learning rate: 1e-06
1222
  - Effective batch size: 192
1223
  - Micro-batch size: 24
optimizer.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:71f5675910ae14a09f6ee25ec0d784e30ffef4781f0e57b3f3cfed1586ddde27
3
  size 5451415117
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fc4830bd211bfab0b8f89b7a69b6e0d10337ad1a80386593eede2e8902acf3b
3
  size 5451415117
random_states_0.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c8ef6c72dcb8774bd1b7b67246d1c39a56fcb09dcdc5d8f0677fbf3853204150
3
- size 16036
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85f6ae0a3ab0378073b39b124c7a88312c94ee7f2f7023c2bd4eab1b0eaceeb4
3
+ size 16100
scheduler.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec7d6af3e643a84bd8897ed320aeb3e1511ef9760b1a21a005ec8a0abffe30de
3
  size 1000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99c38cbbb88c652a783e5e8e0130ab206f9b6e2b158c62708f922666592cb9be
3
  size 1000
training_state-dalle3.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e3c9cbb20b413d65bb1621e2eacbfd81d50c98d935d5158e91a59bf84daf5f8
3
- size 17957506
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d1207d5e9d60a13e697409cad4ac5df8f80a55489ff0ed41e239ee2ee79fbff
3
+ size 9102214
training_state-midjourney-v6-520k-raw.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:16ddf4fb12505d6b02e69553aea269263ba6d6c99330b851a23300aa7019b070
3
- size 4739973
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91ad7036159eb7dd1781ce643511e14005cef5b63e6fd4d27822a61547228184
3
+ size 5036611
training_state-nijijourney-v6-520k-raw.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d7abcfaff044c867b478a01552861dfe19f85fdf528afd4c966cda6ff9f940a
3
- size 5404005
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:653fc864dc17a5838521acd0f6852c0f4147284e6cbd2d871ad16c1cfc734579
3
+ size 5707603
training_state-photo-concept-bucket.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c9b30827b8f9af656b91349341d2942a18539d5df9edf482a3cee4c8c8e26be
3
- size 5296539
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cbeb4eca76bf8f485a290bbdb4f7053f3ceb049bee2ef6694cb46bc8eaa1362
3
+ size 5536591
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": 87000, "epoch_step": 1, "epoch": 4, "exhausted_backends": ["sfwbooru", "midjourney-v6-520k-raw", "nijijourney-v6-520k-raw", "photo-concept-bucket"], "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": 88000, "epoch_step": 1, "epoch": 5, "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:b78f2afffa5ef8a17fcdb1b815a86eb07c606204c38d8000c973bff38ee36d4a
3
  size 1816969728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:619fd341e6ecc23483622cd862c2fbdf793c919385fe119a421d8f3437d24f28
3
  size 1816969728