[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-11682":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":9,"totalLinesOfCode":9,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":9,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":9,"rankLanguage":9,"license":9,"archived":22,"fork":22,"defaultBranch":23,"hasWiki":22,"hasPages":22,"topics":24,"createdAt":9,"pushedAt":9,"updatedAt":27,"readmeContent":28,"aiSummary":29,"trendingCount":16,"starSnapshotCount":16,"syncStatus":30,"lastSyncTime":31,"discoverSource":32},11682,"ViMax","HKUDS\u002FViMax","HKUDS","\"ViMax: Agentic Video Generation (Director, Screenwriter, Producer, and Video Generator All-in-One)\"",null,"https:\u002F\u002Fgithub.com\u002FHKUDS\u002FViMax","Python",9627,1432,73,27,0,717,1196,2718,2151,112.47,false,"main",[25,26],"agentic-aigc","video-generation","2026-06-12 04:00:55","\u003Cdiv align=\"center\">\n  \u003Cimg src=\".\u002Fassets\u002Fvimax.png\"> \n\t\u003Cbr>\n  \u003Cbr>\n\u003Ca href=\"https:\u002F\u002Ftrendshift.io\u002Frepositories\u002F15299\" target=\"_blank\">\u003Cimg src=\"https:\u002F\u002Ftrendshift.io\u002Fapi\u002Fbadge\u002Frepositories\u002F15299\" alt=\"HKUDS%2FViMax | Trendshift\" style=\"width: 250px; height: 55px;\" width=\"250\" height=\"55\"\u002F>\u003C\u002Fa>\n  \u003Ch1 align=\"center\">ViMax: Agentic Video Generation\u003C\u002Fh1>\n\n  \u003Cdiv align=\"center\">\n  \u003C\u002Fdiv>\n\n  \u003Cp align=\"center\">\n    \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F🐍Python-3.12-00d9ff?style=for-the-badge&logo=python&logoColor=white&labelColor=1a1a2e\">\n\t\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fastral-sh\u002Fuv\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F⚡uv-Ready-ff6b6b?style=for-the-badge&logo=python&logoColor=white&labelColor=1a1a2e\">\u003C\u002Fa>\n\t\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-MIT-4ecdc4?style=for-the-badge&logo=opensourceinitiative&logoColor=white\" alt=\"MIT License\">\n  \u003C\u002Fp>\n\n  \u003Cp align=\"center\">\n    \u003Ca href=\".\u002FCommunication.md\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F💬Feishu-Group-07c160?style=for-the-badge&logoColor=white&labelColor=1a1a2e\">\u003C\u002Fa>\n    \u003Ca href=\".\u002FCommunication.md\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FWeChat-Group-07c160?style=for-the-badge&logo=wechat&logoColor=white&labelColor=1a1a2e\">\u003C\u002Fa>\n  \u003C\u002Fp>\n\n  \u003Cp align=\"center\">\n    \u003Ca href='https:\u002F\u002Fwww.youtube.com\u002F@AI-Creator-is-here'>\u003Cimg src='https:\u002F\u002Fbadges.aleen42.com\u002Fsrc\u002Fyoutube.svg' \u002F>\u003C\u002Fa>\n  \u003C\u002Fp>\n\n\u003C\u002Fdiv>\n\u003Cdiv align=\"center\">\n\t\n\u003Cp>\n\t\u003Ca href=\"readme.md\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FEnglish-1a1a2e?style=for-the-badge\">\u003C\u002Fa>\n    \u003Ca href=\"README_ZH.md\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F中文版-1a1a2e?style=for-the-badge\">\u003C\u002Fa>\n\u003C\u002Fp>\n    \u003Ca href=\"#quick-start\" style=\"text-decoration: none;\">\n      \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FQuick%20Start-Get%20Started%20Now-FFC107?style=for-the-badge&logo=rocket&logoColor=white&labelColor=1a1a2e\">\n    \u003C\u002Fa>\n\n\u003C\u002Fdiv>\n\n---\n\n### 🚨 Current Video Generation Limitations:\n- ❌ **Limited to Short Clips** - Most AI tools generate only seconds of footage. \u003Cbr>\n- ❌ **Consistency Chaos** - Characters and scenes change unpredictably across frames. \u003Cbr>\n- ❌ **Visual-Only Focus** - Missing scripts, audio, narrative structure, and storytelling depth. \u003Cbr>\n\n### 💡 ViMax Solution:\n🎬 **Director**, **Screenwriter**, **Producer**, and **Video Generator** **All-in-One**! We're exploring a future where AI becomes a complete creative powerhouse. 💡 Simply input your concept. ViMax autonomously handles the rest. It orchestrates scriptwriting, storyboarding, character creation, and final video generation—all end-to-end. 🚀\n\nhttps:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F5bad46b2-8276-4e1d-9480-3522640744b2\n\n\n\n\u003C\u002Fdiv>\n\n---\n\n\n## 📑 Table of Contents\n\n- [💡 Key Features](#key-features)\n- [🔮 Demos](#Video-Demos-Generated-from-Scratch)\n- [🏗️ Architecture](#️-architecture)\n- [🚀 Quick Start](#quick-start)\n\n---\n## 💡Key Features\n\n\u003Cbr\u002F>\n\n\u003Ctable align=\"center\" width=\"100%\" style=\"border: none; table-layout: fixed;\">\n\u003Ctr>\n\u003Ctd width=\"25%\" align=\"center\" style=\"vertical-align: top; padding: 20px;\">\n\n\u003Cdiv style=\"height: 80px; display: flex; align-items: center; justify-content: center;\">\n\u003Ch3 style=\"margin: 0; padding: 0;\">🌟 \u003Cstrong>Idea2Video\u003C\u002Fstrong>\u003C\u002Fh3>\n\u003C\u002Fdiv>\n\n\u003Cdiv align=\"center\" style=\"margin: 15px 0;\">\n  \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FIDEA-GENERATION-ff6b6b?style=for-the-badge&logo=algorithm&logoColor=white\" alt=\"Algorithm Badge\" \u002F>\n\u003C\u002Fdiv>\n\n\u003Cdiv style=\"height: 80px; display: flex; align-items: center; justify-content: center;\">\n\u003Cp align=\"center\">\u003Cstrong>From Spark to Screen\u003C\u002Fstrong>\u003C\u002Fp>\n\u003C\u002Fdiv>\n\n\u003Cdiv style=\"height: 60px; display: flex; align-items: center; justify-content: center;\">\n\u003Cp align=\"center\">Transform \u003Cstrong> raw ideas \u003C\u002Fstrong> into complete video stories through intelligent multi-agent workflows automating \u003Cstrong> storytelling, character design, and production \u003C\u002Fstrong>.\n\u003C\u002Fp>\n\u003C\u002Fdiv>\n\n\n\n\u003C\u002Ftd>\n\u003Ctd width=\"25%\" align=\"center\" style=\"vertical-align: top; padding: 20px;\">\n\n\u003Cdiv style=\"height: 80px; display: flex; align-items: center; justify-content: center;\">\n\u003Ch3 style=\"margin: 0; padding: 0;\">🎨 \u003Cstrong>Novel2Video\u003C\u002Fstrong>\u003C\u002Fh3>\n\u003C\u002Fdiv>\n\n\u003Cdiv align=\"center\" style=\"margin: 15px 0;\">\n  \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FNOVEL-ADAPTATION-4ecdc4?style=for-the-badge&logo=book&logoColor=white\" alt=\"Frontend Badge\" \u002F>\n\u003C\u002Fdiv>\n\n\u003Cdiv style=\"height: 80px; display: flex; align-items: center; justify-content: center;\">\n\u003Cp align=\"center\">\u003Cstrong>Smart Literary Adaptation Engine\u003C\u002Fstrong>\u003C\u002Fp>\n\u003C\u002Fdiv>\n\n\u003Cdiv style=\"height: 60px; display: flex; align-items: center; justify-content: center;\">\n\u003Cp align=\"center\">Transform \u003Cstrong>complete novels\u003C\u002Fstrong> into \u003Cstrong>episodic video content\u003C\u002Fstrong> with intelligent narrative compression, character tracking, and scene-by-scene visual adaptation\u003C\u002Fp>\n\u003C\u002Fdiv>\n\n\n\n\u003C\u002Ftd>\n\u003Ctd width=\"25%\" align=\"center\" style=\"vertical-align: top; padding: 20px;\">\n\n\u003Cdiv style=\"height: 80px; display: flex; align-items: center; justify-content: center;\">\n\u003Ch3 style=\"margin: 0; padding: 0;\">⚙️ \u003Cstrong>Script2Video\u003C\u002Fstrong>\u003C\u002Fh3>\n\u003C\u002Fdiv>\n\n\u003Cdiv align=\"center\" style=\"margin: 15px 0;\">\n  \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FSCRIPT-ADAPTATION-9b59b6?style=for-the-badge&logo=server&logoColor=white\" alt=\"Backend Badge\" \u002F>\n\u003C\u002Fdiv>\n\n\u003Cdiv style=\"height: 80px; display: flex; align-items: center; justify-content: center;\">\n\u003Cp align=\"center\">\u003Cstrong>Unlimited Screenplay Video Creation\u003C\u002Fstrong>\u003C\u002Fp>\n\u003C\u002Fdiv>\n\n\u003Cdiv style=\"height: 60px; display: flex; align-items: center; justify-content: center;\">\n\u003Cp align=\"center\">Unleash your creativity by writing \u003Cstrong>any screenplay\u003C\u002Fstrong> from personal stories to epic adventures, giving you complete control over every aspect of your visual storytelling.\u003C\u002Fp>\n\u003C\u002Fdiv>\n\n\n\n\n\n\u003C\u002Ftd>\n\u003Ctd width=\"25%\" align=\"center\" style=\"vertical-align: top; padding: 20px;\">\n\n\u003Cdiv style=\"height: 80px; display: flex; align-items: center; justify-content: center;\">\n\u003Ch3 style=\"margin: 0; padding: 0;\">🤳 \u003Cstrong>AutoCameo\u003C\u002Fstrong>\u003C\u002Fh3>\n\u003C\u002Fdiv>\n\n\u003Cdiv align=\"center\" style=\"margin: 15px 0;\">\n  \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FINTERACTIVE-GENERATION-FFC107?style=for-the-badge&logo=server&logoColor=white\" alt=\"Backend Badge\" \u002F>\n\u003C\u002Fdiv>\n\n\u003Cdiv style=\"height: 80px; display: flex; align-items: center; justify-content: center;\">\n\u003Cp align=\"center\">\u003Cstrong>Generate Video from Your Photo\u003C\u002Fstrong>\u003C\u002Fp>\n\u003C\u002Fdiv>\n\n\u003Cdiv style=\"height: 60px; display: flex; align-items: center; justify-content: center;\">\n\u003Cp align=\"center\"> \u003Cstrong>Create your own cameo\u003C\u002Fstrong> video, transforming yourself\u002Fpet into a guest star who appears across limitless creative scripts, cinematic sequences, and interactive storylines.\u003C\u002Fp>\n\u003C\u002Fdiv>\n\n\n\n\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003C\u002Ftable>\n\n\u003Cbr\u002F>\n\n---\n\n## 🔮Video Demos Generated from Scratch\n\n\u003Ctable>\n\u003Ctr>\n\n\u003Ctd align=\"center\" width=\"33%\">\n  \u003Cvideo src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Fc2fb27b0-218c-4976-b3d6-2abf8ea06be7\" controls width=\"100%\">\u003C\u002Fvideo>\n\u003C\u002Ftd>\n\u003Ctd align=\"center\" width=\"33%\">\n  \u003Cvideo src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Fbfa566a8-688d-4d53-a9e2-6cedeb4a399d\" controls width=\"100%\">\u003C\u002Fvideo>\n\u003C\u002Ftd>\n\u003Ctd align=\"center\" width=\"33%\">\n  \u003Cvideo src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F49f61134-4f78-4285-9a9e-bb5e3e0c4abf\" controls width=\"100%\">\u003C\u002Fvideo>\n\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd align=\"center\" width=\"33%\">\n  \u003Cvideo src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Fa950f449-a15c-449b-a1b8-c393951aa9be\" controls width=\"100%\">\u003C\u002Fvideo>\n\u003C\u002Ftd>\n\u003Ctd align=\"center\" width=\"33%\">\n  \u003Cvideo src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Fbb3ff0fd-9433-4806-886a-3f77b61d06ec\" controls width=\"100%\">\u003C\u002Fvideo>\n\u003C\u002Ftd>\n\u003Ctd align=\"center\" width=\"33%\">\n  \u003Cvideo src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F2624a3f0-9f66-4fa4-b527-45c0ea0353fc\" controls width=\"100%\">\u003C\u002Fvideo>\n\u003C\u002Ftd>\n\u003C\u002Ftr>\n\n\u003Ctr>\n\u003Ctd align=\"center\" width=\"33%\">\n  \u003Cvideo src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F5dbb80f7-aff0-4211-940c-a898f91fb80c\" controls width=\"100%\">\u003C\u002Fvideo>\n\u003C\u002Ftd>\n\u003Ctd align=\"center\" width=\"33%\">\n  \u003Cvideo src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Fcc0b0bcd-e7db-4839-950b-0b03949637bd\" controls width=\"100%\">\u003C\u002Fvideo>\n\u003C\u002Ftd>\n\u003Ctd align=\"center\" width=\"33%\">\n  \u003Cvideo src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F85919b59-80f0-461a-af7e-a93d3fb412fc\" controls width=\"100%\">\u003C\u002Fvideo>\n\u003C\u002Ftd>\n\u003C\u002Ftr>\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\u003C\u002Ftable>\n\n---\n\n\n\n### 🎯 **End-to-End Video Creation Engine**\n\n**The Challenges**:\n\n- 🌅 **Reference Images**: Time-consuming acquisition, organization, and alignment of reference frames that accurately capture characters, objects, positions, and environments.\n\n- 🫠 **Consistency Check**: Sometimes, the image generator may generate unusable images even if it is given the correct characters, position, environment reference image and prompts.\n\n- 📄 **Scripts Generation**: Professional and high-quality videos need to have rich information density and structured design.\n\n- 📝 **Storyboard Design**: Converting stories into visual narratives requires expertise in cinematography, scene composition, and visual storytelling that most creators lack.\n\n- 🎬 **Shot Design**: Creating coherent camera sequences with proper angles, transitions, and pacing while maintaining narrative flow across complex scenes.\n\n- 🎨 **Development Delays**: Ensuring character appearances, environments, and artistic style remain consistent across hundreds of shots in long-form content.\n\n- ⏱️ **Production Efficiency**: Traditional video creation involves multiple specialists and lengthy workflows, creating barriers for independent creators and rapid prototyping.\n\n- 🎥 **Scaling AI Generated Video**: AI-generated videos are usually only a few seconds long, high-quality long videos at the minute or even hour level require complex cross-scene continuity and multi-storyboards design and processing capabilities.\n\n\n**ViMAX**: eliminates these production bottlenecks by automating the entire video creation pipeline from narrative input to final video output.\n\n---\n\n\n### 🔥 **Why ViMax?**\n\n| 🧠 **Effortless Production** | 🚀 **Complete Creative Freedom** | 🔊 **Audio and Video Binding** | 🎨 **Professional Quality** | 🤩 **Interactive Video** \n|:---:|:---:|:---:|:---:|:---:|\n| One-Prompt to Finished Video | From Any Narrative to Reality | Synchronized Storytelling | Movie-Grade Output | Make Your Own Cameo Video\n| Skip the technical complexity—just describe your vision and let ViMax handle script generation, storyboarding, shot design, reference management, and consistency validation | No creative limits—whether it's a trailer, short story, novel chapter, or original concept, ViMax intelligently structures narratives and designs cinematography to bring any idea to life | Seamlessly integrate character voice, and sound effects with visual content to create immersive experiences where audio and video work in perfect harmony | Automated quality control ensures character consistency, proper scene composition, and professional visual standards across every frame of your video | Interact in your own short stories by uploading your photo—ViMax intelligently integrates you as a character with consistent appearance and natural interactions throughout the entire video\n\n\n\n---\n\n### ☄️ **Coming Soon**\n\n- 👨‍💻 **Google AI Studio API config✅**\n- 📹 **Dev mode branch**\n- 🤳 **AutoCameo integrate**\n- 📺 **More demos**\n- 🎞️ **Shot planning**\n- 🤖 **New features**\n\n---\n\n\n## 🏗️ Architecture\n\n### 📊 **System Overview**\n\n**ViMax** is a multi-agent video framework that enables automated multi-shot video generation while ensuring character and scene consistency. Our system seamlessly translates your ideas into corresponding videos, allowing you to focus on storytelling rather than technical implementation.\n\n🎯 **Technical Capabilities**:\n\n🧬 **Intelligent Long Script Generation**\n\nRAG-based long script design engine that intelligently analyzes lengthy, novel-like stories and automatically segments them into a multi-scene script format. The process meticulously ensures that all key plot developments and character dialogues are accurately retained within the new structure.\n\n🪄 **Expressive Storyboard Design**\n\nShot-level storyboard design system that create expressive storyboards through cinematography language based on user requirements and target audiences, which establishs the narrative rhythm for subsequent video generation.\n\n🔮 **Multi-camera Filming Simulation**\n\nSimulates multi-camera filming to deliver an immersive viewing experience while maintaining consistent character positioning and backgrounds within the same scene.\n\n🧸 **Intelligent Reference Images Selection**\n\nIntelligently select the reference image required for the first frame of the current video, including the storyboards that occurred in the previous timeline, to ensure the accuracy of multiple characters and environmental elements as the video becomes longer.\n\n⚙️ **Automated Images Generation**\n\nBased on the selected reference image and the visual logical order on the previous timeline, the prompt of the image generator is automatically generated to reasonably arrange the spatial interaction position between the character and the environment.\n\n✅ **Automated Image Generation Consistency Check**\n\nGenerate multiple images in parallel and select the best consistent image as the first frame through MLLM\u002FVLM to imitate the workflow of human creators.\n\n⚡ **High-efficiency Parallel Shot Generation**\n\nParallel processing for sequential shots captured from the same camera enables highly efficient video production.\n\n\n\n\n\n### 🤖 \u003Cstrong>Multi-Agent Video Generation Pipeline\u003C\u002Fstrong>\n\n\u003Cdiv align=\"center\">\n  \u003Ctable align=\"center\" width=\"100%\" style=\"border: none; border-collapse: collapse;\">\n    \u003Ctr>\n      \u003Ctd colspan=\"3\" align=\"center\" style=\"padding: 20px; background: linear-gradient(135deg, #667eea 0%, #764ba2 100%); border-radius: 15px; color: white; font-weight: bold;\">\n        🧠 \u003Cstrong>INPUT LAYER\u003C\u002Fstrong>\u003Cbr\u002F>\n        📝 Idea & Scripts & Novels • 💭 Natural Language Prompts • 🖼️ Reference Images • 🎨 Style Directives • 🧩 Configs\n      \u003C\u002Ftd>\n    \u003C\u002Ftr>\n    \u003Ctr>\u003Ctd colspan=\"3\" height=\"20\">\u003C\u002Ftd>\u003C\u002Ftr>\n    \u003Ctr>\n      \u003Ctd colspan=\"3\" align=\"center\" style=\"padding: 15px; background: linear-gradient(135deg, #ff6b6b 0%, #ee5a24 100%); border-radius: 12px; color: white; font-weight: bold;\">\n        🧭 \u003Cstrong>CENTRAL ORCHESTRATION\u003C\u002Fstrong>\u003Cbr\u002F>\n        Agent Scheduling • Stage Transitions • Resource Management • Retry\u002FFallback Logic\n      \u003C\u002Ftd>\n    \u003C\u002Ftr>\n    \u003Ctr>\u003Ctd colspan=\"3\" height=\"15\">\u003C\u002Ftd>\u003C\u002Ftr>\n    \u003Ctr>\n      \u003Ctd align=\"center\" style=\"padding: 12px; background: linear-gradient(135deg, #3742fa 0%, #2f3542 100%); border-radius: 10px; color: white; width: 50%;\">\n        🧾 \u003Cstrong>SCRIPT UNDERSTANDING\u003C\u002Fstrong>\u003Cbr\u002F>\n        \u003Csmall>Character\u002FEnvironment Extraction • Scene Boundaries • Style Intent\u003C\u002Fsmall>\n      \u003C\u002Ftd>\n      \u003Ctd width=\"10\">\u003C\u002Ftd>\n      \u003Ctd align=\"center\" style=\"padding: 12px; background: linear-gradient(135deg, #8c7ae6 0%, #9c88ff 100%); border-radius: 10px; color: white; width: 50%;\">\n        🎥 \u003Cstrong>SCENE & SHOT PLANNING\u003C\u002Fstrong>\u003Cbr\u002F>\n        \u003Csmall>Storyboard Steps • Shot List • Key Frames & Beats\u003C\u002Fsmall>\n      \u003C\u002Ftd>\n    \u003C\u002Ftr>\n    \u003Ctr>\u003Ctd colspan=\"3\" height=\"15\">\u003C\u002Ftd>\u003C\u002Ftr>\n    \u003Ctr>\n      \u003Ctd colspan=\"3\" align=\"center\" style=\"padding: 15px; background: linear-gradient(135deg, #00d2d3 0%, #54a0ff 100%); border-radius: 12px; color: white; font-weight: bold;\">\n        🧪 \u003Cstrong>VISUAL ASSET PLANNING\u003C\u002Fstrong>\u003Cbr\u002F>\n        Reference Image Selection • Look\u002FStyle Guidance • Prompt Conditioning\n      \u003C\u002Ftd>\n    \u003C\u002Ftr>\n    \u003Ctr>\u003Ctd colspan=\"3\" height=\"15\">\u003C\u002Ftd>\u003C\u002Ftr>\n    \u003Ctr>\n      \u003C!-- Swapped: ASSET INDEXING is now on the left -->\n      \u003Ctd align=\"center\" style=\"padding: 12px; background: linear-gradient(135deg, #e056fd 0%, #f368e0 100%); border-radius: 10px; color: white; width: 50%;\">\n        🗂️ \u003Cstrong>ASSET INDEXING\u003C\u002Fstrong>\u003Cbr\u002F>\n        \u003Csmall>Frames\u002FRefs Catalog • Embeddings • Retrieval for Reuse\u003C\u002Fsmall>\n      \u003C\u002Ftd>\n      \u003Ctd width=\"10\">\u003C\u002Ftd>\n      \u003C!-- Swapped: CONSISTENCY & CONTINUITY is now on the right -->\n      \u003Ctd align=\"center\" style=\"padding: 12px; background: linear-gradient(135deg, #ffa726 0%, #ff7043 100%); border-radius: 10px; color: white; width: 50%;\">\n        ♻️ \u003Cstrong>CONSISTENCY & CONTINUITY\u003C\u002Fstrong>\u003Cbr\u002F>\n        \u003Csmall>Character\u002FEnvironment Tracking • Ref Matching • Temporal Coherence\u003C\u002Fsmall>\n      \u003C\u002Ftd>\n    \u003C\u002Ftr>\n    \u003Ctr>\u003Ctd colspan=\"3\" height=\"15\">\u003C\u002Ftd>\u003C\u002Ftr>\n    \u003Ctr>\n      \u003Ctd colspan=\"3\" align=\"center\" style=\"padding: 15px; background: linear-gradient(135deg, #26de81 0%, #20bf6b 100%); border-radius: 12px; color: white; font-weight: bold;\">\n        ✂️ \u003Cstrong>VISUAL SYNTHESIS & ASSEMBLY\u003C\u002Fstrong>\u003Cbr\u002F>\n        Image Generation • Best-Frame Selection • First\u002FLast-Frame→Video • Cut & Timeline Assembly\n      \u003C\u002Ftd>\n    \u003C\u002Ftr>\n    \u003Ctr>\u003Ctd colspan=\"3\" height=\"15\">\u003C\u002Ftd>\u003C\u002Ftr>\n    \u003Ctr>\n      \u003Ctd colspan=\"3\" align=\"center\" style=\"padding: 20px; background: linear-gradient(135deg, #045de9 0%, #09c6f9 100%); border-radius: 15px; color: white; font-weight: bold;\">\n        🚀 \u003Cstrong>OUTPUT LAYER\u003C\u002Fstrong>\u003Cbr\u002F>\n        🖼️ Frames • 🎞️ Clips & Final Videos • 📜 Logs • 📦 Working Directory Artifacts\n      \u003C\u002Ftd>\n    \u003C\u002Ftr>\n  \u003C\u002Ftable>\n\u003C\u002Fdiv>\n\n\n\n\n\n\n## 🚀Quick Start\n\n### 🖥️ **Environment**\n\n```\nOS: Linux, Windows\n```\n\n### 📥 **Clone and Install**\nWe use uv to manage the environment. For uv installation, please refer to the https:\u002F\u002Fdocs.astral.sh\u002Fuv\u002Fgetting-started\u002Finstallation\u002F.\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002FHKUDS\u002FViMax.git\ncd ViMax\nuv sync\n```\n\n\n### 🎯 **Usage**\nmain_idea2video.py is used to convert your ideas into videos.\nYou need to configure the model and API key information in the configs\u002Fidea2video.yaml file, including three parts—the chat model, the image generator, and the video generator, as shown below\n```yaml\nchat_model:\n  init_args:\n    model: google\u002Fgemini-2.5-flash-lite-preview-09-2025\n    model_provider: openai\n    api_key: \u003CYOUR_API_KEY>\n    base_url: https:\u002F\u002Fopenrouter.ai\u002Fapi\u002Fv1\n\nimage_generator:\n  class_path: tools.ImageGeneratorNanobananaGoogleAPI\n  init_args:\n    api_key: \u003CYOUR_API_KEY>\n\nvideo_generator:\n  class_path: tools.VideoGeneratorVeoGoogleAPI\n  init_args:\n    api_key: \u003CYOUR_API_KEY>\n\nworking_dir: .working_dir\u002Fidea2video\n```\n\nThen, provide a simple yet thoughtful idea and the corresponding creative requirements in main_idea2video.py.\n```bash\nidea = \\\n\"\"\"\nIf a cat and a dog are best friends, what would happen when they meet a new cat?\n\"\"\"\nuser_requirement = \\\n\"\"\"\nFor children, do not exceed 3 scenes.\n\"\"\"\nstyle = \"Cartoon\"\n```\n\n#### Using MiniMax as Chat Model Provider\n\n[MiniMax](https:\u002F\u002Fwww.minimaxi.com\u002F) models can be used as an alternative chat model provider. MiniMax offers OpenAI-compatible API access to models such as **MiniMax-M2.7** (1M context window) and **MiniMax-M2.5** (204K context).\n\nSimply set `model_provider: minimax` in your config — the base URL is resolved automatically:\n```yaml\nchat_model:\n  init_args:\n    model: MiniMax-M2.7\n    model_provider: minimax\n    api_key: \u003CYOUR_MINIMAX_API_KEY>\n```\n\nOr export the API key as an environment variable and leave `api_key` empty:\n```bash\nexport MINIMAX_API_KEY=\u003CYOUR_KEY>\n```\n\nSee `configs\u002Fidea2video_minimax.yaml` and `configs\u002Fscript2video_minimax.yaml` for complete examples.\n\n| Model | Context | Note |\n|---|---|---|\n| MiniMax-M2.7 | 1M tokens | Latest, recommended |\n| MiniMax-M2.7-highspeed | 1M tokens | Fast variant |\n| MiniMax-M2.5 | 204K tokens | Stable |\n| MiniMax-M2.5-highspeed | 204K tokens | Fast variant |\n\n---\n\nmain_script2video.py generates a video based on a specific script.\nYou similarly need to set up the API configuration in configs\u002Fscript2video.yaml file. Then, provide a scene script and the corresponding creative requirements in main_script2video.py, as shown below.\n```python\nscript = \\\n\"\"\"\nEXT. SCHOOL GYM - DAY\nA group of students are practicing basketball in the gym. The gym is large and open, with a basketball hoop at one end and a large crowd of spectators at the other end. John (18, male, tall, athletic) is the star player, and he is practicing his dribble and shot. Jane (17, female, short, athletic) is the assistant coach, and she is helping John with his practice. The other students are watching the practice and cheering for John.\nJohn: (dribbling the ball) I'm going to score a basket!\nJane: (smiling) Good job, John!\nJohn: (shooting the ball) Yes!\n...\n\"\"\"\nuser_requirement = \\\n\"\"\"\nFast-paced with no more than 20 shots.\n\"\"\"\nstyle = \"Animate Style\"\n```\n\n\n---\n\n**🌟 If this project helps you, please give us a Star!**\n\n\u003Cp align=\"center\">\n  \u003Cem> ❤️ Thanks for visiting ✨ ViMax!\u003C\u002Fem>\u003Cbr>\u003Cbr>\n\u003C\u002Fp>\n\n","ViMax 是一个集导演、编剧、制片人和视频生成于一体的全能型视频创作工具。它利用先进的AI技术，能够从概念输入到最终视频输出全流程自动化处理，包括剧本撰写、分镜头设计、角色创建等关键步骤。项目基于Python语言开发，旨在解决当前AI视频生成中存在的片段长度限制、场景一致性差以及缺乏叙事深度等问题。适用于需要快速高效地生成具有完整故事结构短视频内容的各种场景，如广告制作、教育素材准备或是个人创意表达等。",2,"2026-06-11 03:32:16","trending"]