# Astorie

> The ultimate AI creative canvas for filmmakers and professionals

Astorie is an AI-powered creative platform that transforms filmmaking workflows from script to screen. It combines a node-based visual editor with an infinite canvas interface, bridging the gap between prompt-only tools (Runway, Pika) and complex technical systems (ComfyUI, Nuke) with an intuitive yet powerful approach to AI content creation.

## Core Capabilities

- **Node-Based Visual Editor**: Drag-and-drop workflow system where each node represents a generation step — image, video, audio, text, 3D, or tool. Chain multiple AI models together for complex creative pipelines.
- **Infinite Canvas**: Unlimited workspace to organize, pan, zoom, and arrange nodes freely. Think Figma meets AI filmmaking.
- **Multi-Model Support**: Model-agnostic platform supporting all leading AI models in a single workflow — Sora, Runway, Kling, Veo 3.1, Hailuo for video; FLUX, Midjourney, DALL-E, Ideogram for images; ElevenLabs, OpenAI TTS for audio.
- **Studio Production Suite**: Professional tools for video, image, and audio creation with upscaling, repair, lipsync, and more.
- **Workflow Automation**: Streamline creative processes with automated node connections and reusable templates.
- **Team Collaboration**: Share projects, prompts, and feedback with your team in real time.

## Node Types

- **Text Node** — Write prompts, @mention other nodes for context-aware generation
- **Image Node** — AI image generation (text-to-image, image-to-image, AI editing)
- **Video Node** — AI video generation (image-to-video, text-to-video)
- **Audio Node** — Voice synthesis, sound effects, music generation
- **3D Node** — 3D model generation
- **Tool Node** — Upscale, repair, lipsync, and post-processing utilities
- **Note Node** — Annotations and project notes

## Key Differentiators

- Only platform combining deep node-based control + infinite canvas + multi-model AI generation + cloud-native collaboration
- Founded by Vincent Zhan
- 200+ AI films produced on the platform
- Used by filmmakers, ad agencies, studios, and creative teams worldwide

## Use Cases

- AI filmmaking and short film production
- Commercial and advertising video creation
- Motion graphics and VFX pre-visualization
- Social media video content at scale
- Storyboard-to-video workflows
- Multi-model AI video comparison and iteration

## Supported Models

Astorie integrates 100+ AI models from leading providers. All models are accessible through a unified node-based interface — no API keys or setup required.

### Image Generation

| Provider | Models |
|----------|--------|
| Midjourney | Midjourney v7 (incl. Niji 7) |
| Black Forest Labs | FLUX.2, FLUX.2 Pro, FLUX1.1 Pro, FLUX Kontext (Pro/Max) |
| Google | Imagen 4 (Fast/Standard/Ultra), Nano Banana Pro |
| Ideogram | Ideogram V3, Ideogram Character |
| OpenAI | GPT Image 1, GPT Image 1.5 |
| Kling | Omni Image O1 |
| Runway | Gen4 Image |
| ByteDance | Seedream v4.0 / v4.5 (text & edit) |
| Alibaba | Qwen Image Edit, Qwen Image Edit Plus, Z-Image |
| Vidu | Vidu Reference-to-Image |
| xAI | Grok Imagine |

**Capabilities**: text-to-image, image-to-image, AI editing, reference-based generation, multi-image input, batch generation (up to 9 images)

### Video Generation

| Provider | Models |
|----------|--------|
| Google | Veo 3.1 (Fast/Standard), Veo 3.1 Extend |
| Kling | Kling O3, Kling O1, Kling 3.0, Kling 2.6, Kling 2.5 Turbo, Kling 2.1 (+ motion control, video edit, reference variants) |
| OpenAI | Sora 2, Sora 2 Pro, Sora 2 Pro Storyboard |
| ByteDance | SeedDance v1 / v1.5 Pro, OmniHuman v1 / v1.5 |
| Minimax | Hailuo 02, Hailuo 2.3 |
| Runway | Gen4 Turbo, Aleph |
| Alibaba | Wan 2.6, Wan 2.2 Animate Move / Character Swap, Wan VACE Video Edit |
| Luma | Ray 2, Ray Flash 2 |
| Vidu | Vidu Q1, Q2, Q3 (+ subject/image/video reference) |
| Moonvalley | Marey |
| xAI | Grok Imagine Video |

**Capabilities**: text-to-video, image-to-video, video-to-video editing, video extension, motion control, audio-driven animation, storyboard mode, reference-based generation

### Audio & Music

| Provider | Models |
|----------|--------|
| ElevenLabs | TTS Eleven v3, TTS Turbo v2.5, TTS Multilingual v2, Dialogue v3, Sound Effects v2 |
| OpenAI | TTS-1, TTS-1-HD |
| Minimax | Speech 2.5 (HD/Turbo), Speech 02 (HD/Turbo), Music v1.5, Voice Design |
| Suno | Suno V4.5 / V5 (music generation) |
| LMNT | Aurora, Blizzard |
| Hume AI | Emotional speech synthesis |
| Mirelo | Video-to-audio SFX |

**Capabilities**: text-to-speech (50+ voices), music generation, sound effects, voice design, video-to-audio, emotional speech

### 3D Generation

| Provider | Models |
|----------|--------|
| Tripo3D | Tripo v2.5 (Standard/Pro/Max) — GLB, FBX export, PBR materials |
| Tencent | Hunyuan3D v2.1 — GLB export, octree-based generation |

### Text / LLM (Script & Prompt Assistance)

| Provider | Models |
|----------|--------|
| OpenAI | GPT-4o, GPT-4.1, GPT-4.1 Mini/Nano, O1, O3, O3 Mini, O4 Mini |
| Anthropic | Claude 3.5 Haiku, Claude 3.7 Sonnet, Claude 3 Opus |
| Google | Gemini 2.0 Flash, Gemini 2.5 Flash, Gemini 1.5 Pro, Gemini 3.0 Pro |
| DeepSeek | DeepSeek Chat, DeepSeek Reasoner |

### Post-Production Tools

| Category | Tools |
|----------|-------|
| Upscale | Recraft Crisp, Topaz (Image & Video), Magnific V2, Magnific Creative, SeedVR |
| Lipsync | Pixverse, Kling LipSync, InfiniteTalk, Veed, Creatify, Sync Pro |
| Background Removal | Bria RMBG 2.0 |
| Camera Control | Multi-angle camera positioning |
| Layer Processing | Layer Decomposition, Layer Compositor |
| Drawing & Masking | Integrated draw editor, mask editor |
| Cropping | Single crop, grid crop |
| Transcription | OpenAI Whisper, GPT-4o Transcribe |
| Vision / Understanding | GPT-4.1, GPT-4o, O3, O4 Mini |

## Pricing

- **Free** ($0/mo) — 200 credits/month, basic models, personal projects
- **Standard** ($20/mo) — 1,600 credits/month, all advanced AI models, up to 2 concurrent videos
- **Pro** ($50/mo) — 5,400 credits/month, up to 4 concurrent videos, early access to new AI features
- **Ultimate** ($150/mo) — 17,000 credits/month, up to 8 concurrent videos, 15% discount on top-ups, unlimited premium models
- All plans: 40% discount with annual billing. On-demand credit top-ups available without upgrading.

## Documentation

- [Getting Started](https://astorie.ai/docs/getting-started/quickstart)
- [Canvas Basics](https://astorie.ai/docs/getting-started/canvas-basics)
- [Image Node Guide](https://astorie.ai/docs/nodes/image)
- [Video Node Guide](https://astorie.ai/docs/nodes/video)
- [Audio Node Guide](https://astorie.ai/docs/nodes/audio)
- [Workflows](https://astorie.ai/docs/workflows)
- [FAQ](https://astorie.ai/docs/faq)

## Links

- Website: https://astorie.ai
- Pricing: https://astorie.ai/pricing
- Documentation: https://astorie.ai/docs
- X: https://x.com/astorie_ai
- Discord: https://discord.gg/BhF3FgKRw6
- LinkedIn: https://linkedin.com/company/astorie
- Instagram: https://www.instagram.com/astorie_ai/
- YouTube: https://www.youtube.com/@astorie_ai
- Support: support@astorie.ai