[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-72532":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":10,"archived":22,"fork":22,"defaultBranch":23,"hasWiki":24,"hasPages":22,"topics":25,"createdAt":10,"pushedAt":10,"updatedAt":34,"readmeContent":35,"aiSummary":36,"trendingCount":16,"starSnapshotCount":16,"syncStatus":37,"lastSyncTime":38,"discoverSource":39},72532,"story-flicks","alecm20\u002Fstory-flicks","alecm20","使用AI大模型，一键生成高清故事短视频。Generate high-definition story short videos with one click using AI large models.","",null,"Python",2408,436,20,24,0,5,16,149,15,84.92,false,"main",true,[26,27,28,29,30,31,32,33],"ai-video","ai-video-generator","chatgpt","moviepy","openai","python","shortvideo","story-generation","2026-06-12 04:01:06","English | [简体中文](.\u002FREADME-CN.md)\n\n## Project Description\n\nThis project allows users to input a story theme and generates a story video using a large language model. The video includes AI-generated images, story content, audio, and subtitles.\n\nThe backend technology stack consists of Python + FastAPI framework, while the frontend is built with React + Ant Design + Vite.\n\n## Video Demonstration\n\n\u003Ctable>\n\u003Cthead>\n\u003Ctr>\n\u003Cth align=\"center\">\u003Cg-emoji class=\"g-emoji\" alias=\"arrow_forward\">▶️\u003C\u002Fg-emoji> The Story of the Rabbit and the Little Fox\u003C\u002Fth>\n\u003Cth align=\"center\">\u003Cg-emoji class=\"g-emoji\" alias=\"arrow_forward\">▶️\u003C\u002Fg-emoji> The Story of the Big Gray Wolf and the Little White Rabbit\u003C\u002Fth>\n\u003C\u002Ftr>\n\u003C\u002Fthead>\n\u003Ctbody>\n\u003Ctr>\n\u003Ctd align=\"center\">\u003Cvideo src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Fe1893b9c-83ed-420c-a29a-1f5f878117c4\">\u003C\u002Fvideo>\u003C\u002Ftd>\n\u003Ctd align=\"center\">\u003Cvideo src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F8868e1b5-a931-4d25-9762-859a4c32d4f4\">\u003C\u002Fvideo>\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003C\u002Ftbody>\n\u003C\u002Ftable>\n\n## Interface Screenshot\n\n![](backend\u002Fexamples\u002Fscreenshot\u002Fusage.jpg)\n\n## Usage Instructions\n\n### 1. Download the project\n\n```\ngit clone https:\u002F\u002Fgithub.com\u002Falecm20\u002Fstory-flicks.git\n```\n\n### 2. Set model information\n\n```\n# First, switch to the project’s backend directory first.\ncd backend\ncp .env.example .env\n\n\ntext_provider = \"openai\"  # Provider of the text generation model. Currently supports openai, aliyun, deepseek, ollama, and siliconflow.  \n                          # Aliyun documentation: https:\u002F\u002Fwww.aliyun.com\u002Fproduct\u002Fbailian\n\nimage_provider = \"aliyun\"  # Provider of the image generation model. Currently supports openai, aliyun, and siliconflow.\n\nopenai_base_url=\"https:\u002F\u002Fapi.openai.com\u002Fv1\" # The base URL for OpenAI\n\naliyun_base_url=\"https:\u002F\u002Fdashscope.aliyuncs.com\u002Fcompatible-mode\u002Fv1\" # The base URL for Aliyun\n\ndeepseek_base_url=\"https:\u002F\u002Fapi.deepseek.com\u002Fv1\" # The base URL for DeepSeek\n\nollama_base_url=\"http:\u002F\u002Flocalhost:11434\u002Fv1\" # The base URL for Ollama\n\nsiliconflow_base_url=\"https:\u002F\u002Fapi.siliconflow.cn\u002Fv1\" # The base URL for SiliconFlow\n\nopenai_api_key= # The API key for OpenAI, only one key needs to be provided\n\naliyun_api_key= # The API key for Aliyun Bailian, only one key needs to be provided\n\ndeepseek_api_key= # The API key for DeepSeek, currently only text generation is supported\n\nollama_api_key= # If you need to use it, please set api_key to “ollama”. Currently, this API key only supports text generation and cannot be used with models that have too few parameters. It is recommended to use qwen2.5:14b or a larger model.\n\nsiliconflow_api_key= # The API key for SiliconFlow, siliconflow's text model currently only supports large models compatible with the OpenAI format, such as Qwen\u002FQwen2.5-7B-Instruct. The image model has only been tested with black-forest-labs\u002FFLUX.1-dev.\n\n\ntext_llm_model=gpt-4o # If text_provider is set to openai, only OpenAI models can be used, such as gpt-4o. If aliyun is selected, Aliyun models like qwen-plus or qwen-max can be used. Ollama models cannot be used with models that have too few parameters. It is recommended to use qwen2.5:14b or a larger model.\n\nimage_llm_model=flux-dev # If image_provider is set to openai, only OpenAI models can be used, such as dall-e-3. If aliyun is selected, Aliyun models like flux-dev are recommended, which are currently available for free trial. More details: https:\u002F\u002Fhelp.aliyun.com\u002Fzh\u002Fmodel-studio\u002Fgetting-started\u002Fmodels#a1a9f05a675m4.\n```\n\n### 3. Start the project\n\n#### 3.1 Manual Startup\n\n**Start the backend project**\n\n```\n# First, switch to the project root directory\ncd backend\nconda create -n story-flicks python=3.10 # Using conda, other virtual environments can also be used\nconda activate story-flicks\npip install -r requirements.txt\nuvicorn main:app --reload\n```\n\nIf the project starts successfully, the following output will appear:\n\n```\nINFO:     Uvicorn running on http:\u002F\u002F127.0.0.1:8000 (Press CTRL+C to quit)\nINFO:     Started reloader process [78259] using StatReload\nINFO:     Started server process [78261]\nINFO:     Waiting for application startup.\nINFO:     Application startup complete.\n```\n\n**Start the frontend project**\n\n```\n# First, switch to the project root directory\ncd frontend\nnpm install\nnpm run dev\n\n# After successful startup, open: http:\u002F\u002Flocalhost:5173\u002F\n```\n\nWhen successfully started, the following output will appear:\n\n```\n  VITE v6.0.7  ready in 199 ms\n\n  ➜  Local:   http:\u002F\u002Flocalhost:5173\u002F\n  ➜  Network: use --host to expose\n  ➜  press h + enter to show help\n```\n\n#### 3.2 Start via Docker\n\nIn the project root directory, run:\n\n```\ndocker-compose up --build\n```\n\nOnce successful, open the frontend project at: http:\u002F\u002Flocalhost:5173\u002F\n\n### 4. Get started\n\nBased on the fields in the interface, select the text generation model provider, image generation model provider, text model, image model, video language, voice, story theme, and story segments. Then click “Generate” to create the video. The number of images generated will correspond to the number of segments specified, with one image per segment. The more segments you set, the longer it will take to generate the video. Once the generation is successful, the video will be displayed on the frontend page.\n","该项目使用AI大模型一键生成高清故事短视频。其核心功能包括基于用户提供的故事主题，自动生成包含AI生成的图像、故事内容、音频及字幕的视频。技术栈方面，后端采用Python + FastAPI框架，前端则基于React + Ant Design + Vite构建。适用于需要快速创作个性化或定制化故事短视频的内容创作者、教育工作者以及娱乐行业从业者等场景。",2,"2026-06-11 03:42:26","high_star"]