AI design agent. Local and free alternative for Lovart. AI agent with ability to design, edit and generate images, posters, storyboards, etc. with a creative canvas board for fast iterations and layout publishing



- AI designer agent powered by LLM that can smartly write prompt and batch generate images or even a whole storyboard!
- Support Ollama for local LLM
- Support ComfyUI for free local image generations: Stable Diffusion, Flux Dev, etc.
- Edit images in conversation using Flux Kontext: object removal, style transfer, edit specific elements in image, consistent character generation etc. All through chat!
- Canvas and storyboard: unleash your creativity using our infinite canvas!
- [Upcoming] Video generations through Wan2.1, Kling, and video creation and editing agent
- Use Claude, OpenAI, Gemini via API key, or run locally with Ollama for 100% free usage
- Use image generation models like GPT-4O, Recraft, Flux, Google Imagen, etc. through Replicate API key
- Add LLM API key like OpenAI or Claude, or install Ollama to use local models
- Add image generations API key like Replicate

- Start chatting with agent to generate stories or storyboards!

- Prompt: 帮我把这个角色放到6张不同的场景里,都是世界各地的地标建筑前,灯光和谐,他在世界各地拍照,写实,温暖的光线,高画质,画面比例9:16
To use deepseek as a provider, setup as below

First git clone this repo:
git clone https://github.com/11cafe/localart
cd server
pip install -r requirements.txt
python main.py
cd react
npm i && npm run dev
cd server
pip install -r requirements.txt
python main.py