Instructions to use fudan-generative-ai/hallo2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use fudan-generative-ai/hallo2 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("fudan-generative-ai/hallo2", 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
Missing "scripts" directory?
#6
by LydianMelody - opened
Forgive me if I'm missing something, I'm a novice. The instructions mention files that don't seem to exist such as scripts/inference_long.py, scripts/train_stage1 and even requirements.txt.
Hello @LydianMelody , you are supposed to clone the repo from github first (not shown in the hf readme)
git clone https://github.com/fudan-generative-vision/hallo2
cd hallo2