Instructions to use jiashanlu/impress with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use jiashanlu/impress 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("jiashanlu/impress") prompt = "High fashion photo of an elegant oriental woman with fair skin and long black hair, wearing an intricately designed traditional Indian sari. She is gracefully holding a perfume bottle while standing in a highly luxurious Indian palace, Mahadjah style. The background features opulent decor with golden accents, intricate carvings, and a grand chandelier. The setting includes richly adorned furniture and colorful silk drapes. The lighting is soft and diffused, casting a regal glow over the scene. The camera angle is a mid-shot, capturing her upper body and the extravagant palace interior. Shot with a Canon EOS 5D. impress <lora:impress:1>" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee