Instructions to use guoyww/animatediff-motion-lora-v1-5-3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use guoyww/animatediff-motion-lora-v1-5-3 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("guoyww/animatediff-motion-lora-v1-5-3", 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
metadata
library_name: diffusers
pipeline_tag: text-to-video
tags:
- animatediff
Motion LoRAs
Motion LoRAs allow adding specific types of motion to your animations.
Currently, the following types of loras are available for models using the guoyww/animatediff-motion-adapter-v1-5-2 checkpoint.
- Zoom In/Out
- Pan Left/Right
- Tilt Up/Down
- Rolling Clockwise/Anticlockwise
This lora improves the generation quality and is meant to be used with AnimateDiff v3 guoyww/animatediff-motion-adapter-v1-5-3 checkpoint and SparseCtrl checkpoints.
Please refer to the AnimateDiff documentation for information on how to use these Motion LoRAs.
