Instructions to use CSU-JPG/Glance with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use CSU-JPG/Glance with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Qwen/Qwen-Image", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("CSU-JPG/Glance") prompt = "Qwen-Image, distillation" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Improve model card: Add pipeline tag, library name, paper, project, and code links
#1
by nielsr HF Staff - opened
This PR significantly enhances the model card for the "Glance: Accelerating Diffusion Models with 1 Sample" model by:
- Adding
pipeline_tag: text-to-imageto the YAML metadata, which ensures the model is correctly categorized and discoverable on the Hugging Face Hub. - Adding
library_name: diffusersto the YAML metadata. Evidence from the GitHub README (pip install git+https://github.com/huggingface/diffusers) and the inference code demonstrates compatibility withdiffusers, enabling the automated "how to use" widget on the Hub. - Adding a clear main title reflecting the paper: "Glance: Accelerating Diffusion Models with 1 Sample".
- Including explicit links at the top to the Hugging Face paper page, the official project page (
https://zhuobaidong.github.io/Glance/), and the GitHub repository (https://github.com/CSU-JPG/Glance) for easy access to more information. - Adding a concise "About" section derived from the paper's abstract to quickly inform users about the model's contributions.
- Preserving the existing "Usage" and "Inference" sections, including the Python code snippet, as found in the GitHub README.
- Including the "Training" section and the BibTeX citation from the GitHub repository for completeness and proper attribution.
- Removing redundant metadata (
--- license: apache-2.0 ---) from the markdown content, consolidating all metadata in the YAML front matter.
These updates make the model card more informative, discoverable, and user-friendly for the community.
Thank you so much!!! I will modify model card quickly