Instructions to use ByteDance/AnimateDiff-Lightning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ByteDance/AnimateDiff-Lightning with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("ByteDance/AnimateDiff-Lightning", 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
Distinct gifs instead of seamless video
#38
by dynamitemaggy - opened
Hey guys, I'm using comfyUI. AnimateDiff is outputting a lot of different gifs fused together instead of one seamless video. i downloaded all the models correctly along with ByteDances workflow. After some research I read that maybe "Pad prompt/negative prompt to be same length" setting will help, but i dont know where to find it on comfyAI. Has anyone had the same issue?