Instructions to use emte/flux1-dev-copy with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use emte/flux1-dev-copy with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("emte/flux1-dev-copy", 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
Commit ·
9852fe8
1
Parent(s): 8cb47d9
Update README.md (#46)
Browse files- Update README.md (04bf310e2362f0204cf061263c03f050c353bc16)
Co-authored-by: Sayak Paul <sayakpaul@users.noreply.huggingface.co>
README.md
CHANGED
|
@@ -42,7 +42,7 @@ The FLUX.1 models are also available via API from the following sources
|
|
| 42 |
To use `FLUX.1 [dev]` with the 🧨 diffusers python library, first install or upgrade diffusers
|
| 43 |
|
| 44 |
```shell
|
| 45 |
-
pip install
|
| 46 |
```
|
| 47 |
|
| 48 |
Then you can use `FluxPipeline` to run the model
|
|
@@ -60,7 +60,6 @@ image = pipe(
|
|
| 60 |
height=1024,
|
| 61 |
width=1024,
|
| 62 |
guidance_scale=3.5,
|
| 63 |
-
output_type="pil",
|
| 64 |
num_inference_steps=50,
|
| 65 |
max_sequence_length=512,
|
| 66 |
generator=torch.Generator("cpu").manual_seed(0)
|
|
|
|
| 42 |
To use `FLUX.1 [dev]` with the 🧨 diffusers python library, first install or upgrade diffusers
|
| 43 |
|
| 44 |
```shell
|
| 45 |
+
pip install -U diffusers
|
| 46 |
```
|
| 47 |
|
| 48 |
Then you can use `FluxPipeline` to run the model
|
|
|
|
| 60 |
height=1024,
|
| 61 |
width=1024,
|
| 62 |
guidance_scale=3.5,
|
|
|
|
| 63 |
num_inference_steps=50,
|
| 64 |
max_sequence_length=512,
|
| 65 |
generator=torch.Generator("cpu").manual_seed(0)
|