Instructions to use SammyLim/VideoMaMa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use SammyLim/VideoMaMa with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("SammyLim/VideoMaMa", 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
VideoMaMa License request: switch to MIT? :)
#2
by JJHaggar - opened
Thanks for releasing VideoMaMa model! ^_^
Would it be possible to change the license to a permissive open-source one, ideally MIT (or similar), for the model weights. A permissive license would make reuse and integration much easier, and it usually helps adoption and contributions a lot :)
Also, there is a related discussion on GitHub about switching the code license to a permissive one as well: https://github.com/cvlab-kaist/VideoMaMa/issues/1
If you are open to it, aligning the license across both places would be really helpful for users and contributors ^_^