Instructions to use kabachuha/ltx2-squish-one-hand with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use kabachuha/ltx2-squish-one-hand with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image, export_to_video # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Lightricks/LTX-2", torch_dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("kabachuha/ltx2-squish-one-hand") prompt = "In the video, a miniature toy house is presented. A person's gigantic long right arm appears from the right, stretches all way to the toy house and grabs the miniature toy house from the right. The toy house is held in the person’s gigantic right hand in the distance. The person then presses on the toy house, causing a handsquish effect. The person keeps pressing up on the toy house, further showing the handsquish effect. In the end the person squishes and crushes the toy house into a mess." input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/guitar-man.png") image = pipe(image=input_image, prompt=prompt).frames[0] export_to_video(output, "output.mp4") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things