Instructions to use cuio/MiniT2I_bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use cuio/MiniT2I_bf16 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("cuio/MiniT2I_bf16", 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
Update pipeline.py
Browse files- pipeline.py +1 -1
pipeline.py
CHANGED
|
@@ -678,7 +678,7 @@ class MiniT2IPipeline(DiffusionPipeline):
|
|
| 678 |
self,
|
| 679 |
prompt: Union[str, List[str]],
|
| 680 |
model_type: str = "b16",
|
| 681 |
-
repo_id_or_path: Union[str, os.PathLike] = "
|
| 682 |
torch_dtype: Optional[torch.dtype] = torch.bfloat16,
|
| 683 |
text_encoder_dtype: torch.dtype = torch.float32,
|
| 684 |
device: Optional[Union[str, torch.device]] = None,
|
|
|
|
| 678 |
self,
|
| 679 |
prompt: Union[str, List[str]],
|
| 680 |
model_type: str = "b16",
|
| 681 |
+
repo_id_or_path: Union[str, os.PathLike] = "cuio/MiniT2I_bf16",
|
| 682 |
torch_dtype: Optional[torch.dtype] = torch.bfloat16,
|
| 683 |
text_encoder_dtype: torch.dtype = torch.float32,
|
| 684 |
device: Optional[Union[str, torch.device]] = None,
|