Instructions to use UmeAiRT/FLUX.1-dev-LoRA-Romanticism with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use UmeAiRT/FLUX.1-dev-LoRA-Romanticism with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("UmeAiRT/FLUX.1-dev-LoRA-Romanticism") prompt = "A painting depicts a woman in a white dress holding a french flag, surrounded by a group of people. The woman is in the center of the scene, with her arms raised in the air. The people around her are in various positions, some standing and others sitting. The painting is in a romantic style, with a focus on the woman and her flag as the central subject. The other people in the scene add depth and interest to the composition, creating a dynamic and engaging image. in romantic style" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Update README.md
Browse files
README.md
CHANGED
|
@@ -66,4 +66,16 @@ You should use `romantic` to trigger the image generation.
|
|
| 66 |
|
| 67 |
Weights for this model are available in Safetensors format.
|
| 68 |
|
| 69 |
-
[Download](/UmeAiRT/FLUX.1-dev-LoRA-Romanticism/tree/main) them in the Files & versions tab.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 66 |
|
| 67 |
Weights for this model are available in Safetensors format.
|
| 68 |
|
| 69 |
+
[Download](/UmeAiRT/FLUX.1-dev-LoRA-Romanticism/tree/main) them in the Files & versions tab.
|
| 70 |
+
|
| 71 |
+
## Training parameter
|
| 72 |
+
|
| 73 |
+
epochs : 40
|
| 74 |
+
|
| 75 |
+
steps : 2000
|
| 76 |
+
|
| 77 |
+
lora_rank : 32
|
| 78 |
+
|
| 79 |
+
optimizer : prodigy
|
| 80 |
+
|
| 81 |
+
resolution : 1024
|