Instructions to use wav/TemporalNet2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use wav/TemporalNet2 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("wav/TemporalNet2", 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
| license: openrail | |
| # TemporalNet2 for Diffusers | |
| [CiaraRowles/TemporalNet2](https://huggingface.co/CiaraRowles/TemporalNet2) but converted for use with Diffusers! | |
| At the moment loading the checkpoint requires a tiny 3-line fix to Diffusers ([see this PR](https://github.com/huggingface/diffusers/pull/3815)). You can install the working version of diffusers with: | |
| ``` | |
| pip install git+https://github.com/JCBrouwer/diffusers@expose-controlnet-conditioning-channels | |
| ``` | |
| Then you can use the script included in this repo to stylize videos using text prompts. | |
| ``` | |
| python temporalvideo_hf.py --help | |
| ``` |