Instructions to use eramth/flux-kontext-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use eramth/flux-kontext-4bit with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("eramth/flux-kontext-4bit", dtype=torch.bfloat16, device_map="cuda") prompt = "Turn this cat into a dog" input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png") image = pipe(image=input_image, prompt=prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -19,7 +19,7 @@ pip install bitsandbytes
|
|
| 19 |
```python
|
| 20 |
from diffusers import FluxKontextPipeline
|
| 21 |
import torch
|
| 22 |
-
pipeline = FluxKontextPipeline.from_pretrained("eramth/flux-4bit",torch_dtype=torch.float16).to("cuda")
|
| 23 |
# This allows you to generate higher resolution images without much extra VRAM usage.
|
| 24 |
pipeline.vae.enable_tiling()
|
| 25 |
|
|
|
|
| 19 |
```python
|
| 20 |
from diffusers import FluxKontextPipeline
|
| 21 |
import torch
|
| 22 |
+
pipeline = FluxKontextPipeline.from_pretrained("eramth/flux-kontext-4bit",torch_dtype=torch.float16).to("cuda")
|
| 23 |
# This allows you to generate higher resolution images without much extra VRAM usage.
|
| 24 |
pipeline.vae.enable_tiling()
|
| 25 |
|