Instructions to use aaa-ceku7/GFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use aaa-ceku7/GFT with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("aaa-ceku7/GFT", 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 Settings
- Draw Things
- DiffusionBee
Add model card for GFT: Visual Generation Without Guidance with pipeline and library tags
#1
by nielsr HF Staff - opened
This PR significantly enhances the model card by:
- Adding a descriptive introduction to the Guidance-Free Training (GFT) model.
- Linking to the paper Visual Generation Without Guidance.
- Linking to the GitHub repository at https://github.com/thu-ml/GFT.
- Setting the
pipeline_tagtotext-to-image, which will enable discoverability on the Hub at https://huggingface.co/models?pipeline_tag=text-to-image. - Adding
library_name: diffusersto enable the "Use in Diffusers" widget and automated code snippet on the model page, as indicated by the_diffusers_versioninconfig.jsonand mentions of Stable Diffusion compatibility in the GitHub README. - Including a relevant image and its caption from the GitHub repository for better visual context.
- Adding the BibTeX citation.
aaa-ceku7 changed pull request status to merged