Instructions to use jaeyong2/FLUX.1-dev-ko-Preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use jaeyong2/FLUX.1-dev-ko-Preview with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("jaeyong2/FLUX.1-dev-ko-Preview", 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
Update README.md
Browse files
README.md
CHANGED
|
@@ -16,9 +16,11 @@ base_model:
|
|
| 16 |
## Model Details
|
| 17 |
|
| 18 |
|
| 19 |
-
###
|
| 20 |
|
| 21 |
-
black-forest-labs/FLUX.1-dev를 기반으로
|
|
|
|
|
|
|
| 22 |
|
| 23 |
### example
|
| 24 |
```
|
|
|
|
| 16 |
## Model Details
|
| 17 |
|
| 18 |
|
| 19 |
+
### 한국어 적용
|
| 20 |
|
| 21 |
+
- black-forest-labs/FLUX.1-dev를 기반으로 사용
|
| 22 |
+
- Bingsu/clip-vit-large-patch14-ko를 적용
|
| 23 |
+
- T5 Encoder에 한국어 vocab 확장을 적용 + fine-tuning (코랩 쿼타 이슈로 인해서, 1 X A100을 2시간 학습)
|
| 24 |
|
| 25 |
### example
|
| 26 |
```
|