登录

Google-Colab_Notebooks

Isi-dev活跃维护

一堆可直接在 Google Colab 上跑的生成式 AI 笔记本，覆盖 ComfyUI 工作流、Flux Kontext、混元、LTX 视频等图生图与图生视频玩法，省去自己配环境。

A Collection of Google Colab Notebooks for various projects

暂无版本567star +3 / 7 天187fork同步于 2026-11-10 11:58 UTC
Colab 笔记本图生视频图生图ComfyUI 工作流多模态生成
对比 GitHubanimate-xcolab-notebookscomfyui-workflowflux-kontexthidream

怎么上手

由 README 提炼，执行前请确认
原文 
在浏览器打开对应笔记本的 Colab 徽章链接即可运行，例如：https://colab.research.google.com/github/Isi-dev/Google-Colab_Notebooks/blob/main/Contributions/Ming3TTS.ipynb
硬件要求按 README 说明

README 未给出具体显存要求；多个笔记本标注「Tested on the L4」，部分标注需要 Compute units，另有标为 Free 的 GGUF 版本。

下载：源码 zip·GitHub Releases（安装包）本站不镜像安装包

项目说明

由 README 自动翻译提炼
没人工点评？写下你的经验

一堆开箱即用的 Colab 笔记本，覆盖 TTS、图像编辑和多种视频生成模型

一堆可直接在 Google Colab 上跑的生成式 AI 笔记本，覆盖 ComfyUI 工作流、Flux Kontext、混元、LTX 视频等图生图与图生视频玩法，省去自己配环境。

核心能力

  • 按模型分目录整理 Wan、LTX、MiniMax、Qwen-Image 等笔记本
  • 提供 ComfyUI 版笔记本，可直接跑图生视频与视频编辑
  • 含 GGUF 量化与 LoRA 加速版本，降低显存门槛
  • 覆盖文生视频、图生视频、首尾帧、长视频等任务
  • 部分笔记本标注已在 L4 上测试过

容易踩的坑

部分笔记本需要 Colab Compute units，免费额度可能不够；模型权重需在笔记本内另行下载，首次运行耗时较长；标注 WIP 或 Experimental 的笔记本功能尚不稳定。

内容由模型根据 README 生成，可能不完整或不准确，以官方文档为准。看原文 README

最近发版

0 个版本
全部 release

暂无 release 数据（可能没有发版，或尚未同步）。

用户点评

登录用户的真实使用记录，可按版本和硬件筛选
共 0 条

    还没有人点评。第一个说出真实体验的人最有价值。

    README 原文

    未翻译
    在 GitHub 打开

    Google-Colab_Notebooks

    A Collection of Google Colab Notebooks for scripts & projects

    Latest Notebooks

    NotebooksInfo
    Open In ColabText to Speech with Ming-3.0-tts
    Open In ColabMiniMax-H3 for T2IV I2IV & R2V (Tested on the L4)
    Open In ColabQwen-Image 2.1 for Generating & Editing Images

    MiniMax

    NotebooksInfo
    Open In ColabMiniMax-H3 for T2IV I2IV & R2V (Tested on the L4)
    Open In ColabComfyUI-MiniMax-H3 Reference to Video by @know1234567 (Tested on the L4)
    Open In ColabComfyUI-MiniMaxMusic3 for Music Generation
    Open In ColabComfyUI-MiniMax-H3 for Video Generation (Tested on the L4)

    LTX

    NotebooksInfo
    Open in ColabLTX-23 for Text/Image to Video with Audio (by @know1234567)
    Open In ColabLTX-2 for Text/Image to Video with Audio
    Open In ColabComfyUI-LTX-2.3 for Text/Image to Video with Audio
    Open In ColabComfyUI-LTX-2 for Video Generation
    Open In ColabBasic Image to Video with LTX-Video
    Open In ColabText to Video with LTX-Video
    Open In ColabTwo Images to Video with LTX-Video
    Open In ColabLTXV-0.9.7-13B_Distilled_GGUF_Q6 for Image to Video Generation

    Wan

    NotebooksInfo
    Open In ColabFirst-Last Frame to Video with Wan2.2
    Open in ColabInfinite Image to Video with Wan2.2 (by @know1234567)
    Open In ColabI2V with Wan2.2 using Lightx2v LoRA
    Open In ColabT2V with Wan2.2 using Lightx2v LoRA
    Open In ColabComfyUI - Img+Vid2Vid with Wan2.2 Animate (Tested on the L4)
    Open In ColabT2V & T2I with Wan2.1_T2V_1.3B (Compute units Required)
    Open In ColabT2V & T2I with Wan2_1_T2V_14B (Compute units Required)
    Open In ColabImage to Video with Wan2_1_I2V_14B-480P (Compute units Required)
    Open In ColabT2V & T2I with Wan2.1_T2V_1.3B
    Open In ColabT2V & T2I with Wan2.1_T2V_14B GGUF Models
    Open In ColabImage to Video with Wan2.1_I2V_14B-480p GGUF Models
    Open In ColabI2V with Wan2.1_I2V_14B-480p GGUF Models & LoRA
    Open In ColabFaster I2V with Wan2.1_I2V_14B-480p GGUF Models, LoRA & Teacache
    Open In ColabWan 2.1 VACE 14B & CausVid LoRA for faster Text to Video Generation
    Open In ColabWan 2.1 VACE 14B & CausVid LoRA for faster Image to Video Generation
    Open In ColabWan 2.1 VACE 14B & CausVid LoRA for Video to Video Generation
    Open In ColabWan 2.1 VACE 14B & CausVid LoRA for Image to Image Pose Transfer (Experimental)
    Open In ColabFaster I2V with Wan2.1 using Causvid, Lightx2v & Fusionx LoRAs

    Other Video Notebooks

    NotebooksInfo
    Open In ColabComfyUI-HunyuanVideo-1.5 for Video Generation
    Open In ColabComfyUI-LongCat for long Video Generation (Tested on the L4)
    Open In ColabComfyUI-Ditto for video Editing (Tested on the L4)
    Open In ColabComfyUI-Ovi for Text/Image to Video with Audio (Tested on the L4)
    Open In ColabComfyUI - Img+Vid2Vid with VACE Fun (Compute units Required)
    Open In ColabFramePack_fp8 for Image to Video Generation (Compute units Required)
    Open In ColabStable-Video-Infinity 2.0 Pro for Image to long Video Generation

    Qwen-Image

    NotebooksInfo
    Open In ColabComfyUI - Qwen-Image 2.1 for Generating & Editing Images
    Open In ColabComfyUI - 1 to 3 Images to 1 Image with Qwen Image Edit 2509
    Open In ColabComfyUI - Img2Img with Qwen + DiffSynth-Control-LoRA
    Open In ColabComfyUI - Img2Img with Qwen + DiffSynth-ControlNet (Depth, Canny, Inpaint) (Compute units Required)
    Open In ColabComfyUI - Img2Img with Qwen + InstantX-ControlNet-Union
    Open In ColabQwen-Image for Generating & Editing Images
    Open In ColabQwen-Image-Edit 2509 for 1-3 Images to 1 Image
    Open In ColabImproved Qwen-Image-Edit-2509 (with Mask Editor)
    Open In ColabQwen-Image 2.1 for Generating & Editing Images

    Other Image Notebooks

    NotebooksInfo
    Open In ColabComfyUI - Style and Subject-Driven Image Generation with Flux.1Dev-USO
    Open In ColabHidream_fp8 for Text to Image Generation (Compute units Required)
    Open In ColabHidream_GGUF_Q5 for Text to Image Generation
    Open In ColabUse Prompts to Edit Images with In-Context Edit
    Open In ColabUse Prompts to Edit Images with Flux.1 Kontext Dev
    Open In ColabFlux1 Kontext Dev with Mask Editor for Inpainting
    Open In ColabChroma1-HD for text to Image
    Open In ColabZ-Image Turbo for Text to Image

    Miscellaneous

    NotebooksInfo
    Open In ColabText to Speech with Ming-3.0-tts
    Open In ColabComfyUI-Scail2 for Motion Transfer & Character Swap (Tested on the L4)
    Open In ColabComfyUI-Ace-Step V1.5 for Music Generation
    Open In ColabVideo to Gif (basic)
    Open In ColabLip Sync with LatentSync
    Open In ColabAnimation with Animate-X
    Open In ColabTTS with ZonosTTS
    Open In ColabFrame Interpolation with RIFE
    Open In ColabUpscale Images & Videos with Flux Upscaler
    Open In ColabAudio-driven Portrait Animation with Sonic
    Open In ColabAudio-driven Animation with InfiniteTalk & MultiTalk (Compute units Required)
    Open In ColabText to Speech with Dots.TTS
    Open In ColabSpeech to Text with CrisperWhisper2.0

    You can find more notebooks here

    Find free web apps here

    Some of the comfyUI workflows are modifications of Kijai's workflows which you can find here

    Support

    If you find these notebooks helpful, you can support me here

    Contributing

    You can contribute your notebooks to this repository by adding them to the contributions folder and submitting a pull request (PR). Please note that PR reviews and merges may take some time due to current professional and personal commitments. Thank you for your contribution and patience!

    相关项目

    同分类里 star 最高的项目
    对比全部 →
    stable-diffusion-webui
    AUTOMATIC1111·Python

    基于 Gradio 的 Stable Diffusion 网页界面，把文生图、图生图、局部重绘等能力做成可视化操作面板，不用写代码就能跑图像生成。

    图像生成+4图像生成
    165279+3331kv1.10.12026-03-02 07:00 UTC
    ComfyUI
    Comfy-Org·Python

    基于节点图的扩散模型图形界面与后端，支持本地快速推理和 API 调用，方便搭建和调试图像生成工作流。

    扩散模型+4图像生成
    146089+60317kv0.44.02026-11-10 08:24 UTC
    OpenMontage
    OpenMontageInc·Python

    把 Claude、Cursor 等 AI 编程助手变成完整视频制作工作室，内置 12 条制作流水线和 100+ 工具，覆盖脚本、配音、图像生成到剪辑全流程。

    视频制作+4图像生成
    79288+63411k2026-11-09 06:23 UTC
    OpenMontage
    calesthio·Python

    把 Claude、Cursor 等 AI 编程助手变成完整的视频制作工作室，内置 12 条制作流水线和 100+ 工具，覆盖从生成到剪辑的全流程。

    视频制作+4图像生成
    7786710k2026-11-03 17:42 UTC