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
68a0e51
•
1 Parent(s): 158cb22

Trained for 0 epochs and 26000 steps.

Browse files

Trained with datasets ['text-embeds-pixart-filter', 'photo-concept-bucket', 'moviecollection', 'experimental', 'ethnic', 'sports', 'architecture', 'shutterstock', 'cinemamix-1mp', 'nsfw-1024', 'anatomy', 'bg20k-1024', 'yoga', 'photo-aesthetics', 'text-1mp', 'movieposters', 'normalnudes', 'pixel-art', 'signs', '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 (8) hide show
  1. README.md +3 -3
  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-text-1mp.json +0 -0
  7. training_state.json +1 -1
  8. transformer/diffusion_pytorch_model.safetensors +1 -1
README.md CHANGED
@@ -77,7 +77,7 @@ You may reuse the base model text encoder for inference.
77
  ## Training settings
78
 
79
  - Training epochs: 0
80
- - Training steps: 25500
81
  - Learning rate: 1e-06
82
  - Effective batch size: 192
83
  - Micro-batch size: 24
@@ -262,8 +262,8 @@ You may reuse the base model text encoder for inference.
262
  - Crop aspect: None
263
  ### dalle3
264
  - Repeats: 0
265
- - Total number of images: ~1242072
266
- - Total number of aspect buckets: 1
267
  - Resolution: 1.0 megapixels
268
  - Cropped: False
269
  - Crop style: None
 
77
  ## Training settings
78
 
79
  - Training epochs: 0
80
+ - Training steps: 26000
81
  - Learning rate: 1e-06
82
  - Effective batch size: 192
83
  - Micro-batch size: 24
 
262
  - Crop aspect: None
263
  ### dalle3
264
  - Repeats: 0
265
+ - Total number of images: ~1119168
266
+ - Total number of aspect buckets: 31
267
  - Resolution: 1.0 megapixels
268
  - Cropped: False
269
  - Crop style: None
optimizer.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:96bd52e7b455c7c68ab77efad6ad14ab143b1569a3bc67657e9fbc6897bb40bf
3
  size 5451415117
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fa6164d60e26d6a2f1e5d42eacb8e5b65a177fd09a7d223a5a1bf279c00c730
3
  size 5451415117
random_states_0.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:72e067c333826a97d00c37ea5b5cb3926bf781bf14c44defb17c33767f68723c
3
- size 16100
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03f0f6107964c451e80fc367d2580ba0c04fc72eb9967f182309bf5f43ee01a0
3
+ size 16036
scheduler.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d648c8923d393a386dadfe4a293f466f5f472b27e230e3543633a34bf32f8af1
3
  size 1000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb5abdd61b6cd28c70fce30469fee212db34a07d7e397f085db0c84ab3a8ec9d
3
  size 1000
training_state-dalle3.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b1ffeecd1990a4e933cb23aeddd7c4d2de7a34f2bd4c465d2bf2c895913613db
3
- size 19477964
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e61d7c7dc5d25b47243c084d0d5876a4cdb6e4aeb6279e4e9a5a7d01c3d96fd0
3
+ size 8855654
training_state-text-1mp.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_state.json CHANGED
@@ -1 +1 @@
1
- {"global_step": 25500, "epoch_step": 1, "epoch": 1, "exhausted_backends": ["signs", "nijijourney", "pixel-art", "propagandaposters", "sports", "gay", "experimental", "yoga", "ethnic", "cinemamix-1mp", "architecture", "mj-60", "normalnudes", "bookcovers", "celebrities", "movieposters", "shutterstock", "nsfw-1024", "photo-aesthetics", "moviecollection", "bg20k-1024", "anatomy", "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": 91, "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}}
 
1
+ {"global_step": 26000, "epoch_step": 1, "epoch": 1, "exhausted_backends": ["signs", "nijijourney", "pixel-art", "propagandaposters", "sports", "gay", "experimental", "yoga", "ethnic", "cinemamix-1mp", "architecture", "mj-60", "normalnudes", "bookcovers", "celebrities", "movieposters", "shutterstock", "nsfw-1024", "photo-aesthetics", "moviecollection", "bg20k-1024", "anatomy", "sfwbooru", "midjourney-v6-520k-raw", "nijijourney-v6-520k-raw", "photo-concept-bucket", "dalle3"], "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": 97, "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:a5700e20d1fe2f72795311207d8240f222d248b22e89611d9e759f3541e09db4
3
  size 1816969728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4900f0b7ea2e3a8a81ce7aaf5e972f492f19d0ec18bbc7eb8f4217062d9c1b82
3
  size 1816969728