Diffusers
stable-diffusion
stable-diffusion-1-5
lora
diffusion
arabic
lebanese-houses
image-generation
Instructions to use saramattar123/lhhouse-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use saramattar123/lhhouse-lora with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("saramattar123/lhhouse-lora") 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
LHHouse LoRA — Traditional Lebanese Houses
This model is a LoRA fine-tuned on Stable Diffusion 1.5 to generate traditional Lebanese stone houses and rural Lebanese architecture.
Training
- Base model: Stable Diffusion 1.5
- Fine-tuning method: LoRA
- Training images: 80
- Image resolution: 512x512
- Captions: Arabic
- Trigger word:
lhhouse - Dataset: saramattar123/lebanese-traditional-houses-arabic
Example prompt
lhhouse، بيت لبناني تقليدي من الحجر في قرية جبلية، أشجار زيتون، جبال خضراء
Intended use
This LoRA was created as part of a Diffusion Models homework project to demonstrate custom dataset creation, Arabic captioning, and Stable Diffusion fine-tuning.
Files
The main LoRA weights are stored in:
pytorch_lora_weights.safetensors
- Downloads last month
- 15
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for saramattar123/lhhouse-lora
Base model
runwayml/stable-diffusion-v1-5