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
f51c9d8
•
1 Parent(s): e7c3507

Trained for 2 epochs and 95000 steps.

Browse files

Trained with datasets ['text-embeds', 'text-embeds-extra', 'image-embeds', 'sports', 'mj-60', 'id-75k', 'celebrities', 'normalnudes', 'guys', 'signs', 'dalle3', 'sfwbooru', 'moviecollection', 'bookcovers', 'nijijourney', 'experimental', 'ethnic', 'gay', 'architecture', 'shutterstock', 'midjourney-v6-520k-raw', 'nijijourney-v6-520k-raw', 'cinemamix-1mp', 'nsfw-1024', 'anatomy', 'bg20k-1024', 'yoga', 'photo-aesthetics', 'text-1mp']
Learning rate 1e-06, batch size 8, 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-v0.7-stage1
VAE: ptx0/pixart-900m-1024-ft-v0.7-stage1

Files changed (10) hide show
  1. README.md +1 -1
  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-sfwbooru.json +0 -0
  9. training_state.json +1 -1
  10. transformer/diffusion_pytorch_model.safetensors +1 -1
README.md CHANGED
@@ -552,7 +552,7 @@ You may reuse the base model text encoder for inference.
552
  ## Training settings
553
 
554
  - Training epochs: 2
555
- - Training steps: 94000
556
  - Learning rate: 1e-06
557
  - Effective batch size: 64
558
  - Micro-batch size: 8
 
552
  ## Training settings
553
 
554
  - Training epochs: 2
555
+ - Training steps: 95000
556
  - Learning rate: 1e-06
557
  - Effective batch size: 64
558
  - Micro-batch size: 8
optimizer.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:005d55660cc2269ebdaed85bc450b9d6e62b438b1dd2de1fd0556149d6ef3771
3
  size 5451415117
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4f15290710c118f4f7cc8e199814df8ec8e0dfeab80ff969d5f8870ba7cc43c
3
  size 5451415117
random_states_0.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c2ce03b0a892bf7c264067d6dd0e78b7bacb3a2a34d52cb4c2ad95ee5ae512e9
3
- size 16164
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:280eec62edf312778a4502dddff6a4f7f1139ca321b4c5e5ff7e82f67eba927c
3
+ size 16100
scheduler.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2db1cb09a45879388ca6e687a7161b7e3cad4b101607d21ace9d0fbfb29fb379
3
  size 1000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24713f7f70751f70bf08c3a5888b6a7ecf6d45bb3768eef072167d0880bbc277
3
  size 1000
training_state-dalle3.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fde7a55c167fbca65927c8d06f70fb842c311635f9fbd37083e28fd120957bc5
3
- size 16926608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1fe08a5b5b21ac527b553195ff7e4e3ed313d8df3035e85976f134a3cf51e11
3
+ size 17056371
training_state-midjourney-v6-520k-raw.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:83502cb959cbd3b38e496d4e5f509948175ed37daec7fa84808cf40451271f42
3
- size 3959226
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4a01d8553b51155c4a1ef81e2f9433521f01944cf24aba693b513c79a0af242
3
+ size 4072434
training_state-nijijourney-v6-520k-raw.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:21dc88f47afc7f4da0e256ffb94ddac02399e4c3291138a0c56eb294aeaddde1
3
- size 4077362
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bca15347e08b74de3d4fcf60740c200b6fdb656627fab2d3b81448348080d8e
3
+ size 4174458
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": 94000, "epoch_step": 94002, "epoch": 3, "exhausted_backends": ["guys", "signs", "nijijourney", "bookcovers", "normalnudes", "celebrities", "gay", "sports", "moviecollection", "experimental", "ethnic", "cinemamix-1mp", "architecture", "yoga", "nsfw-1024", "shutterstock", "photo-aesthetics", "id-75k", "text-1mp", "bg20k-1024", "mj-60", "anatomy"], "repeats": {"nijijourney": 0, "signs": 0, "guys": 0, "celebrities": 0, "bookcovers": 0, "normalnudes": 0, "moviecollection": 0, "sports": 0, "gay": 0, "experimental": 0, "yoga": 0, "ethnic": 0, "architecture": 0, "cinemamix-1mp": 0, "photo-aesthetics": 0, "anatomy": 0, "text-1mp": 0, "nsfw-1024": 0, "shutterstock": 0, "id-75k": 0, "bg20k-1024": 0, "mj-60": 0, "sfwbooru": 0, "midjourney-v6-520k-raw": 0, "nijijourney-v6-520k-raw": 0}}
 
1
+ {"global_step": 95000, "epoch_step": 95002, "epoch": 3, "exhausted_backends": ["guys", "signs", "nijijourney", "bookcovers", "normalnudes", "celebrities", "gay", "sports", "moviecollection", "experimental", "ethnic", "cinemamix-1mp", "architecture", "yoga", "nsfw-1024", "shutterstock", "photo-aesthetics", "id-75k", "text-1mp", "bg20k-1024", "mj-60", "anatomy"], "repeats": {"nijijourney": 0, "signs": 0, "guys": 0, "celebrities": 0, "bookcovers": 0, "normalnudes": 0, "moviecollection": 0, "sports": 0, "gay": 0, "experimental": 0, "yoga": 0, "ethnic": 0, "architecture": 0, "cinemamix-1mp": 0, "photo-aesthetics": 0, "anatomy": 0, "text-1mp": 0, "nsfw-1024": 0, "shutterstock": 0, "id-75k": 0, "bg20k-1024": 0, "mj-60": 0, "sfwbooru": 0, "midjourney-v6-520k-raw": 0, "nijijourney-v6-520k-raw": 0}}
transformer/diffusion_pytorch_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4ae194a3a6a5da8c7c0d5408912aa2e0fb4d16d3f87918b00cdcd492702d825
3
  size 1816969728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8439d92bf063c79aada49d8615656eb409245efa07eb6c98aaa13f1cc5720589
3
  size 1816969728