[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tool-jaketae--storyteller":3,"similar-jaketae--storyteller":106},{"id":4,"github_repo":5,"name":6,"description_en":7,"description_zh":8,"ai_summary_zh":9,"readme_en":10,"readme_zh":11,"quickstart_zh":12,"use_case_zh":13,"hero_image_url":14,"owner_login":15,"owner_name":16,"owner_avatar_url":17,"owner_bio":18,"owner_company":18,"owner_location":18,"owner_email":19,"owner_twitter":20,"owner_website":21,"owner_url":22,"languages":23,"stars":28,"forks":29,"last_commit_at":30,"license":31,"difficulty_score":32,"env_os":33,"env_gpu":34,"env_ram":35,"env_deps":36,"category_tags":44,"github_topics":51,"view_count":63,"oss_zip_url":18,"oss_zip_packed_at":18,"status":64,"created_at":65,"updated_at":66,"faqs":67,"releases":95},484,"jaketae\u002Fstoryteller","storyteller","Multimodal AI Story Teller, built with Stable Diffusion, GPT, and neural text-to-speech","Storyteller 是一个结合文本生成、图像创作与语音合成的多模态 AI 工具，能够根据用户输入的初始提示自动生成完整的动画短片。它通过 GPT 模型续写故事情节，用 Stable Diffusion 为每句话生成对应画面，并通过神经网络文本转语音技术生成旁白，最终整合为包含音频、视觉与动态效果的完整视频。例如输入“从前有只贪吃猫策划潜入鱼市”即可生成从剧本创作到动画渲染的一站式输出。\n\n这个工具解决了传统动画制作流程复杂、跨领域协作成本高的痛点。创作者无需掌握编程、设计或配音技能，即可快速将文字创意转化为视觉化叙事作品。对于教育工作者、儿童内容创作者或社交媒体运营者来说，它能显著降低制作故事类视频的门槛，同时为研究人员提供了一个探索多模态 AI 协同创作的实验平台。\n\n开发者可通过 PyPI 安装核心模块，或通过源码获取完整功能。工具默认提供 CLI 操作界面，支持自定义提示词、画面风格前缀等参数调整。技术亮点在于将三大主流 AI 模型（GPT、Stable Diffusion、TTS）进行时序同步与空间对齐，实现文本-图像-语音的精准匹配。特别适合需要快速验证创意、制作原型动画","Storyteller 是一个结合文本生成、图像创作与语音合成的多模态 AI 工具，能够根据用户输入的初始提示自动生成完整的动画短片。它通过 GPT 模型续写故事情节，用 Stable Diffusion 为每句话生成对应画面，并通过神经网络文本转语音技术生成旁白，最终整合为包含音频、视觉与动态效果的完整视频。例如输入“从前有只贪吃猫策划潜入鱼市”即可生成从剧本创作到动画渲染的一站式输出。\n\n这个工具解决了传统动画制作流程复杂、跨领域协作成本高的痛点。创作者无需掌握编程、设计或配音技能，即可快速将文字创意转化为视觉化叙事作品。对于教育工作者、儿童内容创作者或社交媒体运营者来说，它能显著降低制作故事类视频的门槛，同时为研究人员提供了一个探索多模态 AI 协同创作的实验平台。\n\n开发者可通过 PyPI 安装核心模块，或通过源码获取完整功能。工具默认提供 CLI 操作界面，支持自定义提示词、画面风格前缀等参数调整。技术亮点在于将三大主流 AI 模型（GPT、Stable Diffusion、TTS）进行时序同步与空间对齐，实现文本-图像-语音的精准匹配。特别适合需要快速验证创意、制作原型动画的用户，以及希望探索 AI 多模态协同潜力的研究者使用。","# StoryTeller\n\n[![Open In Colab](https:\u002F\u002Fcolab.research.google.com\u002Fassets\u002Fcolab-badge.svg)](https:\u002F\u002Fcolab.research.google.com\u002Fdrive\u002F17C284MOUDQMxV6bRbgVRH4GXsb87iADW?usp=sharing)\n[![Code style: black](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcode%20style-black-000000.svg)](https:\u002F\u002Fgithub.com\u002Fpsf\u002Fblack)\n[![pre-commit](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fpre--commit-enabled-green?logo=pre-commit&logoColor=white)](https:\u002F\u002Fgithub.com\u002Fpre-commit\u002Fpre-commit)\n[![License: MIT](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-MIT-yellow.svg)](https:\u002F\u002Fopensource.org\u002Flicenses\u002FMIT)\n\nA multimodal AI storyteller, built with [Stable Diffusion](https:\u002F\u002Fhuggingface.co\u002Fspaces\u002Fstabilityai\u002Fstable-diffusion), GPT, and neural text-to-speech (TTS).\n\nGiven a prompt as an opening line of a story, GPT writes the rest of the plot; Stable Diffusion draws an image for each sentence; a TTS model narrates each line, resulting in a fully animated video of a short story, replete with audio and visuals.\n\n\u003Cimg id=\"default-output\" src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjaketae_storyteller_readme_a7afc0b17c0c.gif\" alt=\"Example output generated with the default prompt.\">\n\n## Installation\n\n### PyPI\n\nStory Teller is available on [PyPI](https:\u002F\u002Fpypi.org\u002Fproject\u002Fstoryteller-core\u002F).\n\n```\n$ pip install storyteller-core\n```\n\n### Source\n\n1. Clone the repository.\n\n```\n$ git clone https:\u002F\u002Fgithub.com\u002Fjaketae\u002Fstoryteller.git\n$ cd storyteller\n```\n\n2. Install dependencies.\n\n```\n$ pip install .\n```\n\n> [!NOTE]\n> For Apple Silicon users, [`mecab-python3`](https:\u002F\u002Fgithub.com\u002FSamuraiT\u002Fmecab-python3) is not available. You need to install `mecab` before running `pip install`. You can do this with [Hombrew](https:\u002F\u002Fwww.google.com\u002Fsearch?client=safari&rls=en&q=homebrew&ie=UTF-8&oe=UTF-8) via `brew install mecab`. For more information, refer to https:\u002F\u002Fgithub.com\u002FSamuraiT\u002Fmecab-python3\u002Fissues\u002F84.\n\n3. (Optional) To develop locally, install `dev` dependencies and install pre-commit hooks. This will automatically trigger linting and code quality checks before each commit.\n\n```\n$ pip install -e .[dev]\n$ pre-commit install\n```\n\n## Quickstart\n\nThe quickest way to run a demo is by using the command line interface (CLI). To get started, simply type:\n\n```\n$ storyteller\n```\n\nThis command will initialize the story with the default prompt of `Once upon a time, unicorns roamed the Earth`. An\nexample of the output that will be generated [can be seen in the animation above](#default-output).\nYou can customize the beginning of your story by using the `--writer_prompt` argument. For example, if you would like to\nstart your story with the text `The ravenous cat, driven by an insatiable craving for tuna, devised a daring plan to break into the local fish market's coveted tuna reserve.`,\nyour CLI command would look as follows:\n\n```\nstoryteller --writer_prompt \"The ravenous cat, driven by an insatiable craving for tuna, devised a daring plan to break into the local fish market's coveted tuna reserve.\"\n```\n\nThe final video will be saved in the `\u002Fout\u002Fout.mp4` directory, along with other intermediate files such as images,\naudio files, and subtitles.\n\nTo adjust the default settings with custom parameters, you can use the different CLI flags as needed. To see a list of\nall available options, type:\n\n```\n$ storyteller --help\n```\n\nThis will provide you with a list of the options, their descriptions and their defaults.\n\n\n```\noptions:\n  -h, --help            show this help message and exit\n  --writer_prompt WRITER_PROMPT\n                        The prompt to be used for the writer model. This is the text with which your story will begin. Default:\n                        'Once upon a time, unicorns roamed the Earth.'\n  --painter_prompt_prefix PAINTER_PROMPT_PREFIX\n                        The prefix to be used for the painter model's prompt. Default: 'Beautiful painting'\n  --num_images NUM_IMAGES\n                        The number of images to be generated. Those images will be composed in sequence into a video. Default:\n                        10\n  --output_dir OUTPUT_DIR\n                        The directory to save the generated files to. Default: 'out'\n  --seed SEED           The seed value to be used for randomization. Default: 42\n  --max_new_tokens MAX_NEW_TOKENS\n                        Maximum number of new tokens to generate in the writer model. Default: 50\n  --writer WRITER       Text generation model to use. Default: 'gpt2'\n  --painter PAINTER     Image generation model to use. Default: 'stabilityai\u002Fstable-diffusion-2'\n  --speaker SPEAKER     Text-to-speech (TTS) generation model. Default: 'tts_models\u002Fen\u002Fljspeech\u002Fglow-tts'\n  --writer_device WRITER_DEVICE\n                        Text generation device to use. Default: 'cpu'\n  --painter_device PAINTER_DEVICE\n                        Image generation device to use. Default: 'cpu'\n  --writer_dtype WRITER_DTYPE\n                        Text generation dtype to use. Default: 'float32'\n  --painter_dtype PAINTER_DTYPE\n                        Image generation dtype to use. Default: 'float32'\n  --enable_attention_slicing ENABLE_ATTENTION_SLICING\n                        Whether to enable attention slicing for diffusion. Default: 'False'\n```\n\n## Usage\n\n### Command Line Interface\n\n#### CUDA\n\nIf you have a CUDA-enabled machine, run\n\n```\n$ storyteller --writer_device cuda --painter_device cuda\n```\n\nto utilize GPU.\n\nYou can also place each model on separate devices if loading all models on a single device exceeds available VRAM.\n\n```\n$ storyteller --writer_device cuda:0 --painter_device cuda:1\n```\n\n$ For faster generation, consider using half-precision.\n\n```\n$ storyteller --writer_device cuda --painter_device cuda --writer_dtype float16 --painter_dtype float16\n```\n\n#### Apple Silicon\n\n> [!NOTE]\n> PyTorch support for Apple Silicon ([MPS](https:\u002F\u002Fpytorch.org\u002Fdocs\u002Fstable\u002Fnotes\u002Fmps.html)) is work in progress. At the time of writing, `torch.cumsum` does not work with `torch.int64` ([issue](https:\u002F\u002Fgithub.com\u002Fpytorch\u002Fpytorch\u002Fissues\u002F96610)) on PyTorch stable 2.0.1; it works on nightly only.\n\nIf you are on an Apple Silicon machine, run\n\n```\n$ storyteller --writer_device mps --painter_device mps\n```\n\nif you want to use MPS acceleration for both models.\n\nFor faster generation, consider enabling [attention-slicing](https:\u002F\u002Fhuggingface.co\u002Fdocs\u002Fdiffusers\u002Foptimization\u002Ffp16#sliced-attention-for-additional-memory-savings) to save on memory.\n\n```\n$ storyteller --enable_attention_slicing true\n```\n\n### Python\n\nFor more advanced use cases, you can also directly interface with Story Teller in Python code.\n\n1. Load the model with defaults.\n\n```python\nfrom storyteller import StoryTeller\n\nstory_teller = StoryTeller.from_default()\nstory_teller.generate(...)\n```\n\n2. Alternatively, configure the model with custom settings.\n\n```python\nfrom storyteller import StoryTeller, StoryTellerConfig\n\nconfig = StoryTellerConfig(\n    writer=\"gpt2-large\",\n    painter=\"CompVis\u002Fstable-diffusion-v1-4\",\n    max_new_tokens=100,\n)\n\nstory_teller = StoryTeller(config)\nstory_teller.generate(...)\n```\n\n## License\n\nReleased under the [MIT License](LICENSE).\n","# StoryTeller\n\n[![Open In Colab](https:\u002F\u002Fcolab.research.google.com\u002Fassets\u002Fcolab-badge.svg)](https:\u002F\u002Fcolab.research.google.com\u002Fdrive\u002F17C284MOUDQMxV6bRbgVRH4GXsb87iADW?usp=sharing)\n[![Code style: black](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcode%20style-black-000000.svg)](https:\u002F\u002Fgithub.com\u002Fpsf\u002Fblack)\n[![pre-commit](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fpre--commit-enabled-green?logo=pre-commit&logoColor=white)](https:\u002F\u002Fgithub.com\u002Fpre-commit\u002Fpre-commit)\n[![License: MIT](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-MIT-yellow.svg)](https:\u002F\u002Fopensource.org\u002Flicenses\u002FMIT)\n\n一个多模态 AI 故事讲述器，基于 [Stable Diffusion](https:\u002F\u002Fhuggingface.co\u002Fspaces\u002Fstabilityai\u002Fstable-diffusion)、GPT 和神经文本转语音 (TTS) 构建。\n\n给定一个作为故事开场的提示词 (Prompt)，GPT 负责撰写其余情节；Stable Diffusion 为每个句子绘制图像；TTS 模型朗读每一行，最终生成一部配有音频和视觉效果的完整动画短片。\n\n\u003Cimg id=\"default-output\" src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjaketae_storyteller_readme_a7afc0b17c0c.gif\" alt=\"Example output generated with the default prompt.\">\n\n## 安装\n\n### PyPI\n\nStory Teller 可在 [PyPI](https:\u002F\u002Fpypi.org\u002Fproject\u002Fstoryteller-core\u002F) 上获取。\n\n```\n$ pip install storyteller-core\n```\n\n### 源码\n\n1. 克隆仓库。\n\n```\n$ git clone https:\u002F\u002Fgithub.com\u002Fjaketae\u002Fstoryteller.git\n$ cd storyteller\n```\n\n2. 安装依赖。\n\n```\n$ pip install .\n```\n\n> [!NOTE]\n> 对于 Apple Silicon 用户，[`mecab-python3`](https:\u002F\u002Fgithub.com\u002FSamuraiT\u002Fmecab-python3) 不可用。在运行 `pip install` 之前你需要先安装 `mecab`。你可以通过 [Homebrew](https:\u002F\u002Fwww.google.com\u002Fsearch?client=safari&rls=en&q=homebrew&ie=UTF-8&oe=UTF-8) 执行 `brew install mecab` 来完成此操作。更多信息请参阅 https:\u002F\u002Fgithub.com\u002FSamuraiT\u002Fmecab-python3\u002Fissues\u002F84。\n\n3. (可选) 若要本地开发，请安装 `dev` 依赖并安装 pre-commit 钩子。这将在每次提交前自动触发代码检查和代码质量检查。\n\n```\n$ pip install -e .[dev]\n$ pre-commit install\n```\n\n## 快速开始\n\n运行演示最快的方法是使用命令行界面 (CLI)。开始只需输入：\n\n```\n$ storyteller\n```\n\n该命令将使用默认提示词 `Once upon a time, unicorns roamed the Earth` 初始化故事。生成的输出示例 [可在上方的动画中看到](#default-output)。你可以使用 `--writer_prompt` 参数自定义故事的开头。例如，如果你希望故事以文本 `The ravenous cat, driven by an insatiable craving for tuna, devised a daring plan to break into the local fish market's coveted tuna reserve.` 开始，你的 CLI 命令如下所示：\n\n```\nstoryteller --writer_prompt \"The ravenous cat, driven by an insatiable craving for tuna, devised a daring plan to break into the local fish market's coveted tuna reserve.\"\n```\n\n最终视频将保存在 `\u002Fout\u002Fout.mp4` 目录中，以及其他中间文件如图像、音频文件和字幕。\n\n如需使用自定义参数调整默认设置，你可以根据需要使用不同的 CLI 标志。要查看所有可用选项列表，请输入：\n\n```\n$ storyteller --help\n```\n\n这将为你提供选项列表、描述及其默认值。\n\n```\noptions:\n  -h, --help            show this help message and exit\n  --writer_prompt WRITER_PROMPT\n                        The prompt to be used for the writer model. This is the text with which your story will begin. Default:\n                        'Once upon a time, unicorns roamed the Earth.'\n  --painter_prompt_prefix PAINTER_PROMPT_PREFIX\n                        The prefix to be used for the painter model's prompt. Default: 'Beautiful painting'\n  --num_images NUM_IMAGES\n                        The number of images to be generated. Those images will be composed in sequence into a video. Default:\n                        10\n  --output_dir OUTPUT_DIR\n                        The directory to save the generated files to. Default: 'out'\n  --seed SEED           The seed value to be used for randomization. Default: 42\n  --max_new_tokens MAX_NEW_TOKENS\n                        Maximum number of new tokens to generate in the writer model. Default: 50\n  --writer WRITER       Text generation model to use. Default: 'gpt2'\n  --painter PAINTER     Image generation model to use. Default: 'stabilityai\u002Fstable-diffusion-2'\n  --speaker SPEAKER     Text-to-speech (TTS) generation model. Default: 'tts_models\u002Fen\u002Fljspeech\u002Fglow-tts'\n  --writer_device WRITER_DEVICE\n                        Text generation device to use. Default: 'cpu'\n  --painter_device PAINTER_DEVICE\n                        Image generation device to use. Default: 'cpu'\n  --writer_dtype WRITER_DTYPE\n                        Text generation dtype to use. Default: 'float32'\n  --painter_dtype PAINTER_DTYPE\n                        Image generation dtype to use. Default: 'float32'\n  --enable_attention_slicing ENABLE_ATTENTION_SLICING\n                        Whether to enable attention slicing for diffusion. Default: 'False'\n```\n\n## 使用\n\n### 命令行界面\n\n#### CUDA\n\n如果你拥有支持 CUDA 的机器，请运行\n\n```\n$ storyteller --writer_device cuda --painter_device cuda\n```\n\n以利用 GPU。\n\n如果将所有模型加载到单个设备上超过可用显存 (VRAM)，你也可以将每个模型放置在单独的设备上。\n\n```\n$ storyteller --writer_device cuda:0 --painter_device cuda:1\n```\n\n为了更快的生成速度，建议使用半精度。\n\n```\n$ storyteller --writer_device cuda --painter_device cuda --writer_dtype float16 --painter_dtype float16\n```\n\n#### Apple Silicon\n\n> [!NOTE]\n> PyTorch 对 Apple Silicon ([MPS](https:\u002F\u002Fpytorch.org\u002Fdocs\u002Fstable\u002Fnotes\u002Fmps.html)) 的支持仍在进行中。编写本文时，`torch.cumsum` 在 PyTorch stable 2.0.1 版本上与 `torch.int64` 不兼容 ([issue](https:\u002F\u002Fgithub.com\u002Fpytorch\u002Fpytorch\u002Fissues\u002F96610))；仅在 nightly 版本上有效。\n\n如果你使用的是 Apple Silicon 机器，并且想要为两个模型都启用 MPS 加速，请运行\n\n```\n$ storyteller --writer_device mps --painter_device mps\n```\n\n为了更快的生成速度，建议启用 [attention-slicing](https:\u002F\u002Fhuggingface.co\u002Fdocs\u002Fdiffusers\u002Foptimization\u002Ffp16#sliced-attention-for-additional-memory-savings) 以节省内存。\n\n```\n$ storyteller --enable_attention_slicing true\n```\n\n### Python\n\n对于更高级的使用场景，您也可以直接使用 Python 代码与 Story Teller 进行交互。\n\n1. 使用默认参数加载模型。\n\n```python\nfrom storyteller import StoryTeller\n\nstory_teller = StoryTeller.from_default()\nstory_teller.generate(...)\n```\n\n2. 或者，使用自定义配置对模型进行设置。\n\n```python\nfrom storyteller import StoryTeller, StoryTellerConfig\n\nconfig = StoryTellerConfig(\n    writer=\"gpt2-large\",\n    painter=\"CompVis\u002Fstable-diffusion-v1-4\",\n    max_new_tokens=100,\n)\n\nstory_teller = StoryTeller(config)\nstory_teller.generate(...)\n```\n\n## 许可证\n\n本项目依据 [MIT 许可证](LICENSE) 发布。","# StoryTeller 快速上手指南\n\n**StoryTeller** 是一款多模态 AI 故事生成工具。它结合 Stable Diffusion、GPT 和神经文本转语音（TTS）技术，根据输入的故事开头自动生成后续剧情、绘制对应画面并合成配音，最终输出包含音频和视觉的动画短片。\n\n## 环境准备\n\n- **系统要求**：支持 Linux、macOS、Windows。\n- **Python 版本**：Python 3.x。\n- **硬件建议**：\n  - **CPU**：可运行但速度较慢。\n  - **GPU (NVIDIA)**：推荐使用 CUDA 加速（需安装 NVIDIA 驱动及 CUDA Toolkit）。\n  - **Apple Silicon (M1\u002FM2\u002FM3)**：支持 MPS 加速，但需注意特定依赖问题。\n- **特殊依赖**：\n  - **Apple Silicon 用户**：在运行安装前，需通过 Homebrew 安装 `mecab`，否则可能报错。\n    ```bash\n    brew install mecab\n    ```\n\n## 安装步骤\n\n### 方式一：通过 PyPI 安装（推荐）\n\n直接安装核心包即可使用命令行功能。\n\n```bash\npip install storyteller-core\n```\n\n### 方式二：从源码安装\n\n如需开发或获取最新代码，可克隆仓库并安装。\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fjaketae\u002Fstoryteller.git\ncd storyteller\npip install .\n```\n\n> [!NOTE]\n> 若需本地开发调试，可安装开发依赖并配置 pre-commit 钩子：\n> ```bash\n> pip install -e .[dev]\n> pre-commit install\n> ```\n\n## 基本使用\n\n### 默认运行\n\n直接使用命令行启动，将使用默认提示词生成故事视频。\n\n```bash\nstoryteller\n```\n\n生成的视频文件将保存在 `\u002Fout\u002Fout.mp4` 目录中，同时包含中间图片、音频和字幕文件。\n\n### 自定义故事开头\n\n通过 `--writer_prompt` 参数指定故事的起始句子。\n\n```bash\nstoryteller --writer_prompt \"The ravenous cat, driven by an insatiable craving for tuna, devised a daring plan to break into the local fish market's coveted tuna reserve.\"\n```\n\n### 查看帮助选项\n\n查看所有可用参数及其默认值。\n\n```bash\nstoryteller --help\n```\n\n### 硬件加速配置\n\n为了提升生成速度，建议启用 GPU 加速。\n\n**1. NVIDIA CUDA 加速**\n如果您的机器支持 CUDA，请添加以下参数：\n\n```bash\nstoryteller --writer_device cuda --painter_device cuda\n```\n\n若显存不足，可将不同模型分配到不同设备：\n```bash\nstoryteller --writer_device cuda:0 --painter_device cuda:1\n```\n\n开启半精度计算以进一步提升速度：\n```bash\nstoryteller --writer_device cuda --painter_device cuda --writer_dtype float16 --painter_dtype float16\n```\n\n**2. Apple Silicon (MPS) 加速**\nMac M 系列芯片用户可使用 MPS 后端：\n\n```bash\nstoryteller --writer_device mps --painter_device mps\n```\n\n为节省内存，建议开启注意力切片：\n```bash\nstoryteller --enable_attention_slicing true\n```","一位独立教育博主计划为儿童科普频道制作一系列短篇动画视频，但受限于预算无法组建专业团队。\n\n### 没有 storyteller 时\n- 人工撰写脚本需耗费数小时，且难以保证每集剧情逻辑严密。\n- 寻找画师定制分镜图片成本高昂，且不同作者风格难以统一。\n- 配音环节需自行录音或购买版权素材，音画同步调整极其繁琐。\n- 后期将图像与音频合成视频涉及复杂软件操作，学习曲线陡峭。\n\n### 使用 storyteller 后\n- storyteller 基于 GPT 自动续写剧情，几分钟内即可生成完整故事大纲。\n- 利用 Stable Diffusion 为每一句台词实时生成对应的高质量插画。\n- 内置神经网络 TTS 模型自动朗读文本，提供自然流畅的旁白效果。\n- 最终直接输出包含字幕、音频和画面的完整 MP4 文件，无需额外剪辑。\n\nstoryteller 通过全流程自动化，让个人创作者也能零门槛实现多模态故事视频的量产。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjaketae_storyteller_fa07c747.png","jaketae","Jake Tae","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fjaketae_e3edd657.png",null,"jaesungtae@gmail.com","jaesungtae","jaketae.github.io","https:\u002F\u002Fgithub.com\u002Fjaketae",[24],{"name":25,"color":26,"percentage":27},"Python","#3572A5",100,535,70,"2026-03-18T16:44:44","MIT",3,"Linux, macOS, Windows","支持 NVIDIA CUDA 及 Apple Silicon MPS，具体型号与显存要求未说明","未说明",{"notes":37,"python":35,"dependencies":38},"Apple Silicon 用户需通过 Homebrew 安装 mecab；PyTorch MPS 在稳定版 2.0.1 存在兼容性问题，建议使用 nightly 版本；建议开启 attention_slicing 以节省显存；输出文件默认保存至 \u002Fout\u002Fout.mp4",[39,40,41,42,43],"torch>=2.0","transformers","diffusers","TTS","mecab-python3",[45,46,47,48,49,50],"开发框架","视频","图像","Agent","音频","语言模型",[52,53,54,55,56,57,58,59,60,61,62],"gpt","image-generation","pytorch","stable-diffusion","text-to-image","text-to-speech","text-to-video","video-generation","ddpm","diffusion-models","natural-language-generation",6,"ready","2026-03-27T02:49:30.150509","2026-04-06T07:14:26.874252",[68,73,77,82,86,91],{"id":69,"question_zh":70,"answer_zh":71,"source_url":72},1916,"Windows 系统运行时出现 \"Numpy is not available\" 错误怎么办？","维护者表示暂无针对 Windows 的直接修复方案。建议尝试手动重复生成剩余的图像和音频对，然后使用 ffmpeg 或视频编辑器将输出文件拼接在一起。如果熟悉 Python 代码，也可以参考后续的视频拼接脚本进行手动处理。","https:\u002F\u002Fgithub.com\u002Fjaketae\u002Fstoryteller\u002Fissues\u002F4",{"id":74,"question_zh":75,"answer_zh":76,"source_url":72},1917,"如何手动拼接生成的视频片段？","可以通过 Python 脚本调用 StoryTeller 类的 concat_videos 方法来拼接。示例代码如下：\n```python\nfrom storyteller import StoryTeller\nstory_teller = StoryTeller.from_default()\nvideo_paths = [\"out\\\\{i}.mp4\" for i in range(10)]\nstory_teller.concat_videos(video_paths)\n```\n注意可能需要根据实际路径调整 video_paths 列表。",{"id":78,"question_zh":79,"answer_zh":80,"source_url":81},1918,"安装时提示找不到 tts 包版本，如何解决？","这是因为 tts 库要求 Python 版本在 `>=3.7, \u003C3.11` 之间。如果你使用的是 Python 3.11 或更高版本，pip 将无法找到匹配的分布。建议创建一个使用允许版本（如 Python 3.10）的虚拟环境后再进行安装。","https:\u002F\u002Fgithub.com\u002Fjaketae\u002Fstoryteller\u002Fissues\u002F10",{"id":83,"question_zh":84,"answer_zh":85,"source_url":81},1919,"storyteller 和 tts 的安装顺序有建议吗？","建议先单独运行 `pip install TTS` 安装语音合成库，然后再安装 `storyteller-core`。这样可以避免因依赖冲突导致的安装失败问题。",{"id":87,"question_zh":88,"answer_zh":89,"source_url":90},1920,"macOS ARM 架构下 MeCab 安装失败或崩溃怎么办？","常规 pip 安装可能因架构不匹配而失败。需要使用特定参数指定 Arm64 架构编译。请尝试运行以下命令安装 mecab-python3：\n`ARCHFLAGS=\"-arch arm64\" pip install -I mecab-python3==1.0.5 --compile --no-cache-dir`","https:\u002F\u002Fgithub.com\u002Fjaketae\u002Fstoryteller\u002Fissues\u002F12",{"id":92,"question_zh":93,"answer_zh":94,"source_url":90},1921,"macOS ARM 架构下 MeCab 基础库如何正确安装？","对于 MeCab 核心库，同样需要构建 Arm64 版本以解决架构问题。请使用以下命令：\n`ARCHFLAGS=\"-arch arm64\" pip3 install -I MeCab --compile --no-cache-dir`",[96,101],{"id":97,"version":98,"summary_zh":99,"released_at":100},101412,"v0.0.4","* Added demo [Colab notebook](https:\u002F\u002Fcolab.research.google.com\u002Fdrive\u002F17C284MOUDQMxV6bRbgVRH4GXsb87iADW?usp=sharing)\r\n* Added [performance optimization](https:\u002F\u002Fhuggingface.co\u002Fdocs\u002Fdiffusers\u002Fstable_diffusion) options\r\n  * Attention slicing\r\n  * DPM solver\r\n  * Flexible data type (`torch.float16`)\r\n  * Fewer painter inference steps\r\n* Detailed annotation of CLI options (thanks @iluxonchik)\r\n* Miscellaneous improvements","2023-08-22T03:40:15",{"id":102,"version":103,"summary_zh":104,"released_at":105},101413,"v0.0.2","* Streamlined code base packaging via [`poetry`](https:\u002F\u002Fpython-poetry.org)\r\n* Added [pre-commit](http:\u002F\u002Fpre-commit.com) integration for linting and code quality checks\r\n* Added CLI functionality in `cli.py` via `storyteller` command\r\n* Decoupled generation arguments from `StoryTellerConfig` fields","2023-01-13T14:23:48",[107,115,124,132,140,151],{"id":108,"name":109,"github_repo":110,"description_zh":111,"stars":112,"difficulty_score":32,"last_commit_at":113,"category_tags":114,"status":64},3808,"stable-diffusion-webui","AUTOMATIC1111\u002Fstable-diffusion-webui","stable-diffusion-webui 是一个基于 Gradio 构建的网页版操作界面，旨在让用户能够轻松地在本地运行和使用强大的 Stable Diffusion 图像生成模型。它解决了原始模型依赖命令行、操作门槛高且功能分散的痛点，将复杂的 AI 绘图流程整合进一个直观易用的图形化平台。\n\n无论是希望快速上手的普通创作者、需要精细控制画面细节的设计师，还是想要深入探索模型潜力的开发者与研究人员，都能从中获益。其核心亮点在于极高的功能丰富度：不仅支持文生图、图生图、局部重绘（Inpainting）和外绘（Outpainting）等基础模式，还独创了注意力机制调整、提示词矩阵、负向提示词以及“高清修复”等高级功能。此外，它内置了 GFPGAN 和 CodeFormer 等人脸修复工具，支持多种神经网络放大算法，并允许用户通过插件系统无限扩展能力。即使是显存有限的设备，stable-diffusion-webui 也提供了相应的优化选项，让高质量的 AI 艺术创作变得触手可及。",162132,"2026-04-05T11:01:52",[45,47,48],{"id":116,"name":117,"github_repo":118,"description_zh":119,"stars":120,"difficulty_score":121,"last_commit_at":122,"category_tags":123,"status":64},1381,"everything-claude-code","affaan-m\u002Feverything-claude-code","everything-claude-code 是一套专为 AI 编程助手（如 Claude Code、Codex、Cursor 等）打造的高性能优化系统。它不仅仅是一组配置文件，而是一个经过长期实战打磨的完整框架，旨在解决 AI 代理在实际开发中面临的效率低下、记忆丢失、安全隐患及缺乏持续学习能力等核心痛点。\n\n通过引入技能模块化、直觉增强、记忆持久化机制以及内置的安全扫描功能，everything-claude-code 能显著提升 AI 在复杂任务中的表现，帮助开发者构建更稳定、更智能的生产级 AI 代理。其独特的“研究优先”开发理念和针对 Token 消耗的优化策略，使得模型响应更快、成本更低，同时有效防御潜在的攻击向量。\n\n这套工具特别适合软件开发者、AI 研究人员以及希望深度定制 AI 工作流的技术团队使用。无论您是在构建大型代码库，还是需要 AI 协助进行安全审计与自动化测试，everything-claude-code 都能提供强大的底层支持。作为一个曾荣获 Anthropic 黑客大奖的开源项目，它融合了多语言支持与丰富的实战钩子（hooks），让 AI 真正成长为懂上",138956,2,"2026-04-05T11:33:21",[45,48,50],{"id":125,"name":126,"github_repo":127,"description_zh":128,"stars":129,"difficulty_score":121,"last_commit_at":130,"category_tags":131,"status":64},2271,"ComfyUI","Comfy-Org\u002FComfyUI","ComfyUI 是一款功能强大且高度模块化的视觉 AI 引擎，专为设计和执行复杂的 Stable Diffusion 图像生成流程而打造。它摒弃了传统的代码编写模式，采用直观的节点式流程图界面，让用户通过连接不同的功能模块即可构建个性化的生成管线。\n\n这一设计巧妙解决了高级 AI 绘图工作流配置复杂、灵活性不足的痛点。用户无需具备编程背景，也能自由组合模型、调整参数并实时预览效果，轻松实现从基础文生图到多步骤高清修复等各类复杂任务。ComfyUI 拥有极佳的兼容性，不仅支持 Windows、macOS 和 Linux 全平台，还广泛适配 NVIDIA、AMD、Intel 及苹果 Silicon 等多种硬件架构，并率先支持 SDXL、Flux、SD3 等前沿模型。\n\n无论是希望深入探索算法潜力的研究人员和开发者，还是追求极致创作自由度的设计师与资深 AI 绘画爱好者，ComfyUI 都能提供强大的支持。其独特的模块化架构允许社区不断扩展新功能，使其成为当前最灵活、生态最丰富的开源扩散模型工具之一，帮助用户将创意高效转化为现实。",107662,"2026-04-03T11:11:01",[45,47,48],{"id":133,"name":134,"github_repo":135,"description_zh":136,"stars":137,"difficulty_score":121,"last_commit_at":138,"category_tags":139,"status":64},3704,"NextChat","ChatGPTNextWeb\u002FNextChat","NextChat 是一款轻量且极速的 AI 助手，旨在为用户提供流畅、跨平台的大模型交互体验。它完美解决了用户在多设备间切换时难以保持对话连续性，以及面对众多 AI 模型不知如何统一管理的痛点。无论是日常办公、学习辅助还是创意激发，NextChat 都能让用户随时随地通过网页、iOS、Android、Windows、MacOS 或 Linux 端无缝接入智能服务。\n\n这款工具非常适合普通用户、学生、职场人士以及需要私有化部署的企业团队使用。对于开发者而言，它也提供了便捷的自托管方案，支持一键部署到 Vercel 或 Zeabur 等平台。\n\nNextChat 的核心亮点在于其广泛的模型兼容性，原生支持 Claude、DeepSeek、GPT-4 及 Gemini Pro 等主流大模型，让用户在一个界面即可自由切换不同 AI 能力。此外，它还率先支持 MCP（Model Context Protocol）协议，增强了上下文处理能力。针对企业用户，NextChat 提供专业版解决方案，具备品牌定制、细粒度权限控制、内部知识库整合及安全审计等功能，满足公司对数据隐私和个性化管理的高标准要求。",87618,"2026-04-05T07:20:52",[45,50],{"id":141,"name":142,"github_repo":143,"description_zh":144,"stars":145,"difficulty_score":121,"last_commit_at":146,"category_tags":147,"status":64},2268,"ML-For-Beginners","microsoft\u002FML-For-Beginners","ML-For-Beginners 是由微软推出的一套系统化机器学习入门课程，旨在帮助零基础用户轻松掌握经典机器学习知识。这套课程将学习路径规划为 12 周，包含 26 节精炼课程和 52 道配套测验，内容涵盖从基础概念到实际应用的完整流程，有效解决了初学者面对庞大知识体系时无从下手、缺乏结构化指导的痛点。\n\n无论是希望转型的开发者、需要补充算法背景的研究人员，还是对人工智能充满好奇的普通爱好者，都能从中受益。课程不仅提供了清晰的理论讲解，还强调动手实践，让用户在循序渐进中建立扎实的技能基础。其独特的亮点在于强大的多语言支持，通过自动化机制提供了包括简体中文在内的 50 多种语言版本，极大地降低了全球不同背景用户的学习门槛。此外，项目采用开源协作模式，社区活跃且内容持续更新，确保学习者能获取前沿且准确的技术资讯。如果你正寻找一条清晰、友好且专业的机器学习入门之路，ML-For-Beginners 将是理想的起点。",84991,"2026-04-05T10:45:23",[47,148,46,149,48,150,50,45,49],"数据工具","插件","其他",{"id":152,"name":153,"github_repo":154,"description_zh":155,"stars":156,"difficulty_score":32,"last_commit_at":157,"category_tags":158,"status":64},3128,"ragflow","infiniflow\u002Fragflow","RAGFlow 是一款领先的开源检索增强生成（RAG）引擎，旨在为大语言模型构建更精准、可靠的上下文层。它巧妙地将前沿的 RAG 技术与智能体（Agent）能力相结合，不仅支持从各类文档中高效提取知识，还能让模型基于这些知识进行逻辑推理和任务执行。\n\n在大模型应用中，幻觉问题和知识滞后是常见痛点。RAGFlow 通过深度解析复杂文档结构（如表格、图表及混合排版），显著提升了信息检索的准确度，从而有效减少模型“胡编乱造”的现象，确保回答既有据可依又具备时效性。其内置的智能体机制更进一步，使系统不仅能回答问题，还能自主规划步骤解决复杂问题。\n\n这款工具特别适合开发者、企业技术团队以及 AI 研究人员使用。无论是希望快速搭建私有知识库问答系统，还是致力于探索大模型在垂直领域落地的创新者，都能从中受益。RAGFlow 提供了可视化的工作流编排界面和灵活的 API 接口，既降低了非算法背景用户的上手门槛，也满足了专业开发者对系统深度定制的需求。作为基于 Apache 2.0 协议开源的项目，它正成为连接通用大模型与行业专有知识之间的重要桥梁。",77062,"2026-04-04T04:44:48",[48,47,45,50,150]]