lightx2v/Minimax-h3-Turbo

Hugging Face Models Trending 2026/08/07 12:59 模型

摘要

面向 Minimax-h3-Turbo 视频生成模型的 Hugging Face 页面，提供通过 Diffusers 及 Colab/Kaggle 笔记本使用该模型的说明。

任务：图像到视频标签：diffusers, t2v, i2v, r2v, 图像到视频, en, zh, base_model:MiniMaxAI/MiniMax-H3, base_model:finetune:MiniMaxAI/MiniMax-H3, license:apache-2.0, region:us

查看原文

查看缓存全文

缓存时间: 2026/08/07 19:47

lightx2v/Minimax-h3-Turbo · Hugging Face

来源：https://huggingface.co/lightx2v/Minimax-h3-Turbo

使用 lightx2v/Minimax-h3-Turbo 与库、推理提供商、笔记本和本地应用的说明。通过这些链接开始使用。

库
Diffusers (https://huggingface.co/lightx2v/Minimax-h3-Turbo?library=diffusers)如何使用 Diffusers 运行 lightx2v/Minimax-h3-Turbo： 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("lightx2v/Minimax-h3-Turbo", dtype=torch.bfloat16, device_map="cuda") pipe.to("cuda") prompt = "A man with short gray hair plays a red electric guitar." image = load_image( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/guitar-man.png" ) output = pipe(image=image, prompt=prompt).frames[0] export_to_video(output, "output.mp4")
Notebooks
Google Colab (https://huggingface.co/lightx2v/Minimax-h3-Turbo/colab)
Kaggle (https://huggingface.co/lightx2v/Minimax-h3-Turbo/kaggle)