Instructions to use RED-AIGC/TDD with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use RED-AIGC/TDD with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("RED-AIGC/TDD", 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
Comparsion with Hyper-SD and SDXL-Lightning?
#1
by XiaXin-Aloys - opened
Comparsion with Hyper-SD and SDXL-Lightning?
In our paper, we compared with Hyper-SD, and found that our model performs better in terms of saturation and realism. While Hyper-SD excels in details, its overall style tends to be more vivid.