Instructions to use ACCC1380/nyako_style with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ACCC1380/nyako_style with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("circlestone-labs/Anima", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("ACCC1380/nyako_style") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
File size: 805 Bytes
f927ea3 a0912d2 f927ea3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 | from pathlib import Path
import re,json
root=Path('/data/nyako-training-150')
print((root/'status.json').read_text() if (root/'status.json').exists() else 'No status')
p=root/'artifacts/logs/train.log'
s=p.read_text(errors='replace') if p.exists() else ''
# Only emit trainer progress/numeric diagnostics, never dataset/caption log lines.
for pattern in [r'\d+%\|[^\r\n]*?(?:loss|avr_loss)[^\r\n]*',r'(?:torch\.[A-Za-z.]*Error|RuntimeError|ValueError|ImportError|ModuleNotFoundError|AssertionError|TypeError):[^\r\n]*',r'epoch \d+/\d+',r'num (?:train images|epochs|batches per epoch)[^\r\n]*']:
matches=re.findall(pattern,s)
for m in matches[-3:]: print(m)
print('Log bytes:',p.stat().st_size if p.exists() else 0)
print('Weight checkpoints:',len(list((root/'artifacts/output').glob('*.safetensors'))))
|