Instructions to use ntk1507/UFC with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ntk1507/UFC with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("ntk1507/UFC", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Add model card
#2
by nielsr HF Staff - opened
This PR adds a comprehensive model card for the paper "Universal Few-Shot Spatial Control for Diffusion Models". This includes:
- Linking to the official paper: Universal Few-Shot Spatial Control for Diffusion Models.
- Including a direct link to the GitHub repository: https://github.com/kietngt00/UFC.
- Adding
pipeline_tag: text-to-imagefor better discoverability on the Hub. - Adding
library_name: diffusers, as the implementation is explicitly based on the Diffusers library. - Incorporating the abstract and the detailed model checkpoints table from the original repository for user convenience and completeness.
Thank you Nielsr for your pull request!
ntk1507 changed pull request status to merged