The world's first open-source multimodal creative assistant
This is a substitute for Canva and Manus that prioritizes privacy and is usable locally.
Create Viral Shorts with a Single Sentence
Create.Viral.Shorts.with.a.Single.Sentence.mp4
Star us, and you will receive all release notifications from GitHub without any delay!
Turn a single prompt into a complete image or video in seconds.
- Supports top models: GPT-4o, Flux Kontext, Midjourney, etc.
- Advanced video generation with VEO3, Kling, Hailuo, and more
- Auto-optimized prompts for professional-quality output
- Multi-turn conversational iteration and refinement
A revolutionary, prompt-free interface — build your scene like Lego.
- Drag and drop characters, backgrounds, layouts
- AI understands your actions and generates instantly
- No prompt writing required — intuitive for all users
- Lowers creation barriers and forms a defensible UX moat
Visually plan and execute creative workflows.
- Unlimited canvas with scene linking and layout flow
- Drag-and-drop design with media asset management
- Real-time collaboration for teams and co-creators
Control creative tasks via conversation — no manual clicking required.
- Chat-based editing: object insertion, style transfer, scene logic
- Supports multi-character coherence and image-to-image control
- Smart routing across local (ComfyUI) and cloud (OpenAI, Claude) models
Run locally or in the cloud — your data, your choice.
- Fully offline mode: nothing leaves your device
- Hybrid setup: combine Ollama, ComfyUI, and external APIs
- Built-in local asset library for managing images, videos, and prompts
- Cross-platform support: Windows & macOS with one-click setup
Creative freedom with enterprise-grade data control.
- Local-first processing with full privacy control
- Open-source and transparent — no tracking or backdoors
- Suitable for commercial and sensitive workflows
- No vendor lock-in — you own your tools and data
Download here: https://jaaz.app/
Click the "Log In" button at the top right of the homepage to access API models. With a low-cost plan, you can seamlessly use a variety of powerful APIs.
Start chatting with agent to generate stories or storyboards!
- Prompt: Help me place this character in six different scenes, all in front of landmark buildings from around the world. The lighting is harmonious. He takes photos from all over the world, realistic, with warm light, high picture quality, and a picture ratio of 9:16
Support for multi-user private deployment of enterprise teams, ensuring privacy and security.
Please contact via email: [email protected]
WeChat: aifox1
🟠 Need Python version >=3.12
First git clone this repo:
git clone https://github.com/11cafe/localart
cd react
npm install --force
npx vite build
cd ../server
pip install -r requirements.txt
python main.py
🟠 Need Python version >=3.12
VSCode/Cursor Install Extensions：
- Black Formatter by ms-python (ms-python.black-formatter)
cd react
npm install --force && npm run dev
cd server
pip install -r requirements.txt
python main.py