Instructions to use memoavatar/memo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use memoavatar/memo with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("memoavatar/memo", 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
A Spaces demo
#1
by jujutechnology - opened
Are you planning on adding a working demo here on Huggingface?
it probably takes to long to process so it would not work for the free version but idik
I understand. You could possible set it up as they did here:
https://huggingface.co/spaces/multimodalart/dreambooth-training
With a note that it wont work unless you duplicate it and use a minimum level gpu(A10, L40s, etc). I've seen it done with other Spaces.
Just an idea.
Cheers,
Do you think it would work on a A10?
There is a Space up now. It uses an L40s.
https://huggingface.co/spaces/fffiloni/MEMO
Takes about 5-6 minutes per 8 second video.
I may try and duplicate it on an A10