ComfyUI-Veo2-Experimental

ComfyUI-Veo2-Experimental
★ 33

文本到视频短视频生成Veo2集成720p/24fps
在 ComfyUI 中集成 Google Veo 2 的文本/图像到视频生成功能，支持720p@24fps、时长与纵横比配置并保存输出，便于快速制作短视频。
💡 在ComfyUI内用文本一键生成并导出短视频。
🍴 8 Forks💻 Python🔄 2025-04-12
📦
网盘下载
复制链接后前往夸克网盘下载
https://pan.quark.cn/s/8f9eee5e2cdb
📦 requirements.txt
google-genai>=0.2.0
image
📄 README

ComfyUI-Veo2-Experimental

A custom node extension for ComfyUI that integrates Google’s Veo 2 text-to-video generation capabilities.

Overview of Veo 2

Veo 2 is designed to generate high-quality videos from text or image prompts, supporting a variety of cinematic and visual styles. It excels in rendering intricate details across frames and offers features like real-world physics simulation and nuanced motion accuracy.

⚠️ Important: This feature may not yet be available in your country. You may also be charged by Google for additional usage 0.35$ per sec.

Key Features of Veo 2

  • Text-to-Video Generation: Create videos from descriptive text prompts
  • Resolution: Outputs videos in 720p resolution at 24 frames per second
  • Aspect Ratios: Supports standard formats like 16:9 and 9:16
  • Maximum Video Length: Up to 8 seconds per video
  • Watermarking: Videos are watermarked with SynthID for ethical AI use

    • Features

  • Generate videos from text prompts using Google’s Veo 2 model
  • Configure video aspects like duration, aspect ratio, and person generation
  • Save generated videos to your output directory
  • Convert Veo videos to VHS-compatible image format for further processing

    • Requirements

  • ComfyUI (latest version recommended)
  • Google Cloud API Key with access to Veo 2
  • Python 3.8+
  • Google Generative AI Python SDK: pip install google-genai

    • Installation

  • Clone this repository into your ComfyUI custom_nodes folder:

    • “`

    cd /path/to/ComfyUI/custom_nodes

    git clone https://github.com/ShmuelRonen/ComfyUI-Veo2-Experimental

    “`

  • Install the Google Generative AI SDK:

    • “`

    pip install –upgrade google-genai

    “`

  • Get your free API key from Google AI Studio:
  • Visit Google AI Studio
  • Log in with your Google account
  • Click on “Get API key” or go to settings
  • Create a new API key
  • Copy the API key for use in .env file
  • #### Create a .env file in the extension directory with your Google API key:

    • “`

    GOOGLE_API_KEY=your_google_api_key_here

    “`

  • Restart ComfyUI

    • Usage

    Veo Text to Video

  • Add the “Veo Text to Video” node to your workflow
  • Enter your prompt describing the video you want to generate
  • Configure:
  • Aspect ratio (16:9 or 9:16)
  • Person generation setting (don’t allow or allow adult)
  • Duration (5-8 seconds)
  • Connect to “Veo Video Saver” to view and save results

    • Veo Video Saver

  • Connect video output from a Veo generation node
  • Configure:
  • Save to output (true/false)
  • Filename prefix
  • Execute to save videos to your ComfyUI output directory

    • Veo to VHS

    Converts Veo videos to a format compatible with other ComfyUI video processing nodes.

    Notes

  • Video generation may take several minutes
  • The extension implements rate limiting to avoid quota errors
  • Image-to-video generation is currently not supported by Google’s API
  • Maximum video duration is 8 seconds

    • Troubleshooting

    If you encounter “Google API key is required” errors:

  • Check that your .env file is in the correct location
  • Verify your API key is valid and has access to Veo 2
  • Restart ComfyUI

    • License

    [Your License Here]