Instructions to use uncropped/ruby with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use uncropped/ruby with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("LyliaEngine/Pony_Diffusion_V6_XL", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("uncropped/ruby") prompt = "zPDXL3, rubyj4y, realistic, brown hair, long hair, brown eyes, jewelry, lips, earrings, breasts, midriff, bare shoulders, sitting, freckles, smile, teeth, <lora:ruby_jay:1>" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
metadata
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: >-
zPDXL3, rubyj4y, realistic, brown hair, long hair, brown eyes, jewelry,
lips, earrings, breasts, midriff, bare shoulders, sitting, freckles,
smile, teeth, <lora:ruby_jay:1>
parameters:
negative_prompt: 'NEGATIVE_HANDS, watermark, web address, '
output:
url: images/ruby_jay-v1_e15.png
base_model: LyliaEngine/Pony_Diffusion_V6_XL
instance_prompt: rubyj4y
ruby

- Prompt
- zPDXL3, rubyj4y, realistic, brown hair, long hair, brown eyes, jewelry, lips, earrings, breasts, midriff, bare shoulders, sitting, freckles, smile, teeth, <lora:ruby_jay:1>
- Negative Prompt
- NEGATIVE_HANDS, watermark, web address,
Trigger words
You should use rubyj4y to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.