Instructions to use MATLOWAI/MiniMax-H3-Motion-Adapter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use MATLOWAI/MiniMax-H3-Motion-Adapter 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("MiniMaxAI/MiniMax-H3", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("MATLOWAI/MiniMax-H3-Motion-Adapter") prompt = "A man with short gray hair plays a red electric guitar." 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") - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
What specific effects can be achieved or improved?
#2
by QHunyuan - opened
I'm sorry I can't understand your description at all. Can you describe it in easy-to-understand language?
In short: it is a narrowly trained adjustment to the model's behavior at a single step of the pipeline—you trade the fluidity of rapid motion for a bit of color and detail.
Reduce the degree of liquefaction/distortion of high-dynamic pictures?
added a few examples on here so you don't have to dig around on github.