Instructions to use lume534/Lumi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use lume534/Lumi with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Phr00t/Qwen-Image-Edit-Rapid-AIO", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("lume534/Lumi") prompt = "Fashion-forward girl with platinum blonde high ponytail, wearing a white lace top, black acrylic nails, layered silver rings and necklaces, posing against a dark velvet curtain backdrop. Moody lighting, editorial style, close-up portrait, cinematic shadows, Vogue-inspired composition." image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Lumi
.jpeg)
- Prompt
- Fashion-forward girl with platinum blonde high ponytail, wearing a white lace top, black acrylic nails, layered silver rings and necklaces, posing against a dark velvet curtain backdrop. Moody lighting, editorial style, close-up portrait, cinematic shadows, Vogue-inspired composition.
- Negative Prompt
- low quality, worst quality, low resolution, blurry, motion blur, out of focus, grainy, noise, jpeg artifacts, bad lighting, harsh shadows, overexposed, underexposed, flat lighting, yellow light, green tint, bad anatomy, distorted face, asymmetrical face, crossed eyes, lazy eye, wide nose, bad lips, crooked smile, bad hands, extra fingers, missing fingers, fused fingers, deformed hands, uneven nails, chipped nails, plastic skin, wax skin, oily skin, over-smoothing, heavy filter, airbrush, uncanny valley, messy makeup, uneven eyeliner, smudged lipstick, patchy foundation, distorted jewelry, floating accessories, clipping, messy background, clutter, random objects, dirty background, watermark, text, logo, username, frame, border, anime, cartoon, illustration, 3d, cgi, doll, unrealistic look
Model description
Trigger words
You should use Lorarun to trigger the image generation.
Download model
Download them in the Files & versions tab.
- Downloads last month
- 12
Model tree for lume534/Lumi
Base model
Qwen/Qwen-Image-Edit-2511 Finetuned
Phr00t/Qwen-Image-Edit-Rapid-AIO




















