Instructions to use wangyunnan/Canvas with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use wangyunnan/Canvas with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("wangyunnan/Canvas", 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
Commit History
-
Update README.md
Verified signaturec0df965 -
Update README.md
Verified signature### <div align="center"> Canvas: Compositional Generation for Art Painting with Seamless Subject-Driven Infusion<div> <div align="center"> <div style="text-align: center;"> </div> </div> </div> ## 📣 Update Log - [2025.4.01] 🎉 We release the pre-trained Canvas and CreaCulture at HuggingFace ([Model](https://huggingface.co/wangyunnan/Canvas)&[Dataset](https://huggingface.co/datasets/wangyunnan/CreaCulture)). - [2025.3.15] 🎉 Here comes Canvas, we release the code and dataset of Canvas. ## 🪄✨ Abstract <b>TL; DR: <font color="red">Canvas</font> is an automatic artistic image generation framework, which leverages manually collected and finely annotated CeaCulture datasets.</b> <details><summary>CLICK for the full abstract</summary> While diffusion-based art image synthesis has witnessed great success in terms of quality, there are still deficiencies in integrating artist-specified subjects with artistic style. In this paper, we propose Canvas, a framework that leverages the capa…9513edd -
Upload folder using huggingface_hub
Verified signature81916d1 -
initial commit
Verified signaturee3f04e1