Image-to-Image
Diffusers
English
flux-kontext-lora
flux
lora
kontext
web-design
ui-ux
design-transformation
instruction-following
Instructions to use styly-agents/instructdesign-kontext with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use styly-agents/instructdesign-kontext 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("black-forest-labs/FLUX.1-dev", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("styly-agents/instructdesign-kontext") 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
- Local Apps
- Draw Things
Tan commited on
Add model configuration
Browse files- config.json +15 -0
config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_type": "flux-kontext-lora",
|
| 3 |
+
"base_model": "black-forest-labs/FLUX.1-dev",
|
| 4 |
+
"lora_checkpoint": "flux_kontext_lora_v4_consolidated_000010000.safetensors",
|
| 5 |
+
"training_steps": 10000,
|
| 6 |
+
"dataset_size": 937,
|
| 7 |
+
"parameters": {
|
| 8 |
+
"steps": 20,
|
| 9 |
+
"cfg": 1.0,
|
| 10 |
+
"guidance": 5.0,
|
| 11 |
+
"sampler": "er_sde",
|
| 12 |
+
"scheduler": "kl_optimal",
|
| 13 |
+
"lora_strength": 1.0
|
| 14 |
+
}
|
| 15 |
+
}
|