Instructions to use showlab/OmniConsistency with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use showlab/OmniConsistency 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("showlab/OmniConsistency", dtype=torch.bfloat16, device_map="cuda") 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
hosting the style LoRAs in separate repos for each one
#2
by linoyts - opened
Hey, Linoy from HF here 🤗
Awesome work, thanks for sharing the weights on the hub!
For the style LoRAs in /LoRAs - it would be great if it can be separated to one repo per LoRA,
This will help with discoverability, indexing, metrics, etc and is more aligned with our philosophy of “one-repo-per-model” on the hub 🤗
- For example, with having a single repo per LoRA helps people to share that specific LoRA link, also it can give download metrics for each LoRA independently.
- all these LoRAs can then also be easily grouped together using the Collections feature
- You can also use the component that then previews each LoRA on your model page - it's great way to boost visibility of LoRAs by showing output previews with a super easy to use readme template.