当前位置：首页 > news >正文

如何快速上手AnyFlow-FAR-Wan2.1-1.3B-Diffusers：5分钟搭建文本到视频生成环境

news 2026/7/13 15:33:34

如何快速上手AnyFlow-FAR-Wan2.1-1.3B-Diffusers：5分钟搭建文本到视频生成环境

【免费下载链接】AnyFlow-FAR-Wan2.1-1.3B-Diffusers项目地址: https://ai.gitcode.com/hf_mirrors/nvidia/AnyFlow-FAR-Wan2.1-1.3B-Diffusers

AnyFlow-FAR-Wan2.1-1.3B-Diffusers是一款基于Wan2.1-T2V-1.3B-Diffusers文本到视频骨干模型开发的1.3B因果视频扩散模型，支持文本到视频（T2V）、图像到视频（I2V）和视频到视频（V2V）多种生成任务，让用户能够轻松将创意转化为生动视频内容。

🚀 为什么选择AnyFlow-FAR-Wan2.1-1.3B-Diffusers？

这款模型具有以下核心优势：

⚡ 任意步数生成：不同于传统蒸馏模型固定步数预算，单个模型可适应任意推理预算，实现高质量少步生成，且随着采样步数增加提供稳定改进
🔀 多架构支持：支持因果和双向视频扩散模型的任意步蒸馏
🎬 多任务兼容：一个因果视频扩散模型即可支持文本到视频、图像到视频和视频到视频生成
📈 可扩展性能：已在1.3B至14B参数范围内验证了性能表现

⚙️ 环境准备步骤

1️⃣ 创建Conda环境

首先需要创建并激活专用的Conda环境：

conda create -n far python=3.10 conda activate far

2️⃣ 安装PyTorch和依赖项

安装PyTorch及相关依赖：

pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu128 pip install -r requirements.txt --no-build-isolation

📥 模型下载方法

克隆仓库

通过以下命令克隆项目仓库：

git clone https://gitcode.com/hf_mirrors/nvidia/AnyFlow-FAR-Wan2.1-1.3B-Diffusers

使用Hugging Face Hub下载

安装Hugging Face Hub工具并下载模型：

pip install "huggingface_hub[cli]" hf download nvidia/AnyFlow-FAR-Wan2.1-1.3B-Diffusers --repo-type model --local-dir experiments/pretrained_models/AnyFlow-FAR-Wan2.1-1.3B-Diffusers

🔍 项目核心文件结构

项目主要包含以下关键目录和文件：

scheduler/：包含调度器配置文件scheduler_config.json
text_encoder/：文本编码器配置和模型文件，如config.json和模型权重文件
tokenizer/：分词器相关文件，包括special_tokens_map.json、spiece.model等
transformer/：转换器配置和模型文件config.json、diffusion_pytorch_model.safetensors
vae/：VAE配置和模型文件config.json、diffusion_pytorch_model.safetensors
LICENSE.md：模型许可协议文件
README.md：项目说明文档
model_index.json：模型索引配置文件

🎮 快速开始生成视频

文本到视频生成

使用以下Python代码实现文本到视频生成：

import torch from diffusers.utils import export_to_video from far.pipelines.pipeline_far_wan_anyflow import FARWanAnyFlowPipeline model_id = "nvidia/AnyFlow-FAR-Wan2.1-1.3B-Diffusers" pipeline = FARWanAnyFlowPipeline.from_pretrained(model_path).to('cuda', dtype=torch.bfloat16) prompt = "CG game concept digital art, a majestic elephant with a vibrant tusk and sleek fur running swiftly towards a herd of its kind." video = pipeline( prompt=prompt, height=480, width=832, num_frames=81, num_inference_steps=4, generator=torch.Generator('cuda').manual_seed(0) ).frames[0] export_to_video(output, "output.mp4", fps=16)

图像到视频生成

基于现有图像生成视频：

import torch from diffusers.utils import export_to_video from PIL import Image from torchvision import transforms from far.pipelines.pipeline_far_wan_anyflow import FARWanAnyFlowPipeline model_id = "nvidia/AnyFlow-FAR-Wan2.1-1.3B-Diffusers" pipeline = FARWanAnyFlowPipeline.from_pretrained(model_path).to('cuda', dtype=torch.bfloat16) # 加载图像 image_path = 'assets/example_image.jpg' prompt = 'A towering, battle-scarred humanoid robot walking through the skeletal remains of a city ruin.' image = Image.open(image_path).convert('RGB') image = transforms.ToTensor()(transforms.Resize([480, 832])(image)).unsqueeze(0).unsqueeze(0) video = pipeline( prompt=prompt, context_sequence={'raw': image}, height=480, width=832, num_frames=81, num_inference_steps=4, generator=torch.Generator('cuda').manual_seed(0) ).frames[0] export_to_video(output, "output.mp4", fps=16)

视频到视频生成

基于现有视频生成新视频：

import torch from diffusers.utils import export_to_video import decord from torchvision import transforms from far.pipelines.pipeline_far_wan_anyflow import FARWanAnyFlowPipeline decord.bridge.set_bridge('torch') model_id = "nvidia/AnyFlow-FAR-Wan2.1-1.3B-Diffusers" pipeline = FARWanAnyFlowPipeline.from_pretrained(model_path).to('cuda', dtype=torch.bfloat16) # 加载视频 video_path = 'assets/example_video.mp4' prompt = "A focused trail runner's powerful strides through a dense, sun-dappled forest." video_reader = decord.VideoReader(video_path) frame_idxs = select_frame_indices(len(video_reader), video_reader.get_avg_fps(), target_fps=16)[:num_cond_frames] frames = video_reader.get_batch(frame_idxs) frames = (frames / 255.0).float().permute(0, 3, 1, 2).contiguous() frames = transforms.Resize([480, 832])(frames).unsqueeze(0) video = pipeline( prompt=prompt, context_sequence={'raw': frames}, height=480, width=832, num_frames=81, num_inference_steps=4, generator=torch.Generator('cuda').manual_seed(0) ).frames[0] export_to_video(output, "output.mp4", fps=16)