Instructions to use FangDai/Tiger-Model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use FangDai/Tiger-Model with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("FangDai/Tiger-Model", dtype=torch.bfloat16, device_map="cuda") 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
| from torchvision import transforms | |
| THYROID_LABEL = ['Benign', 'Malignant'] | |
| THYROID_SUBGROUP = [['Papillary','Follicular','Medullary']] | |
| def THYROID(): | |
| return (THYROID_LABEL, THYROID_SUBGROUP[0]) | |
| def Transforms(name): | |
| # if name in ["Thyroid"]: | |
| data_transforms_ONE = { | |
| 'valid': transforms.Compose([ | |
| transforms.CenterCrop(512), | |
| transforms.Resize(224), | |
| transforms.ToTensor(), | |
| transforms.Normalize([.5, .5, .5], [.5, .5, .5]) | |
| ]), | |
| 'train': transforms.Compose([ | |
| transforms.CenterCrop(512), | |
| transforms.RandomCrop(256), | |
| transforms.Resize(224), | |
| transforms.ToTensor(), | |
| transforms.Normalize([.5, .5, .5], [.5, .5, .5]) | |
| ]) | |
| } | |
| return data_transforms_ONE | |