Instructions to use ali-vilab/i2vgen-xl with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ali-vilab/i2vgen-xl with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("ali-vilab/i2vgen-xl", 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
can't reproduce the same result as space demo
#13
by fenglinsen - opened
hello,
I build the environment, and use the diffusers, safetensors model to infer a same picture with the same prompt, but the result is much bad than the space demo, I don't know why , is this because I use fp16 in my own project?