NodeTool gives you the flexibility to run AI models locally on your hardware or through cloud APIs — or both at the same time. This guide helps you choose the right approach and get set up.
Local vs. Cloud
NodeTool runs AI models locally or through cloud APIs. Here’s how they compare:
Local Models
Pros:
- 🔒 Private – Data stays local
- 💰 Free – No usage costs
- 📶 Offline – Works without internet
Cons:
- 💾 Requires space – 4-20 GB per model
- ⚡ Needs hardware – Faster with GPU
- ⏳ Initial download – One-time setup
Cloud Models
Pros:
- 🚀 Fast – No downloads
- 💻 Any hardware – Works on older machines
- 🆕 Latest models – Access newest capabilities
Cons:
- 💵 Usage costs – Pay per task
- 🌐 Requires internet
- 📤 Data sent externally
Mixed Approach (Recommended)
Combine local and cloud:
- Speech recognition – local for privacy
- Image generation – cloud for quality
- Document processing – local for confidential files
Cloud Models for Creative Workflows
NodeTool provides access to high-quality generative AI models through cloud providers:
Top 3D Generation Models
| Model | Provider | Capabilities | Key Features |
|---|---|---|---|
| Hunyuan3D V2/3.0 | Hunyuan | T2M/I2M | High-quality 3D meshes and textures |
| Trellis 2 | Trellis | T2M/I2M | Consistent geometry with textured output |
| TripoSR | Tripo | I2M | Fast image-to-3D reconstruction |
| Shap-E | OpenAI | T2M/I2M | Text or image prompt to 3D assets |
| Point-E | OpenAI | T2M | Point cloud generation |
| Meshy AI | Meshy | T2M/I2M | Textured mesh generation |
| Rodin AI | Rodin | T2M/I2M | High fidelity 3D creation |
Top Video Generation Models
| Model | Provider | Capabilities | Key Features |
|---|---|---|---|
| OpenAI Sora 2 Pro |  OpenAI |
T2V/I2V up to 15s | Realistic motion, refined physics, synchronized native audio, 1080p output |
| Google Veo 3.1 |  Google |
T2V/I2V with references | Upgraded realistic motion, extended clip length, multi-image references, native 1080p with synced audio |
| xAI Grok Imagine |  xAI |
T2V/I2V/T2I | Multimodal text/image to short video with coherent motion and synchronized audio; also text-to-image |
| Alibaba Wan 2.6 |  Alibaba |
Multi-shot T2V/I2V | Affordable 1080p with stable characters and native audio; reference-guided generation |
| MiniMax Hailuo 2.3 |  MiniMax |
High-fidelity T2V/I2V | Expressive characters, complex motion and lighting effects |
| Kling 2.6 |  Kling |
T2V/I2V with audio | Text/image to synchronized video with speech, ambient sound, and effects; strong audio-visual coherence |
Top Image Generation Models
| Model | Provider | Capabilities | Key Features |
|---|---|---|---|
| Black Forest Labs FLUX.2 |  BFL |
T2I with control | Photoreal images, multi-reference consistency, accurate text rendering, flexible control |
| Google Nano Banana Pro | Google |
High-res T2I | Sharper 2K output, 4K upscaling, improved text rendering, better character consistency |
Using These Models
Access these models through NodeTool’s generic nodes:
- For Video: Use
nodetool.video.TextToVideoornodetool.video.ImageToVideo - For Images: Use
nodetool.image.TextToImage - For 3D: Use
nodetool.3d.TextTo3Dornodetool.3d.ImageTo3D - Select Provider: Click the model dropdown in the node properties
- Configure API: Add provider API keys in
Settings → Providers
Access via kie.ai (recommended for broad model support): Many of these models are available through kie.ai, an AI provider aggregator that often offers competitive or lower pricing compared to upstream providers.
- Configure using
KIE_API_KEYinSettings → Providers
Access via fal.ai:
- Configure using
FAL_API_KEYinSettings → Providers
Cost Considerations: Cloud models typically charge per generation. Check each provider’s pricing before extensive use. Local models are free after download but require capable hardware.
Getting Started
Option 1: Start with Local Models (Recommended)
- Open Models → Model Manager in NodeTool
- Install these starter models:
- GPT-OSS (~4 GB) – Text generation and chat
- Flux (~12 GB) – High-quality image generation
- Wait for downloads to complete
- Run templates – they’ll work offline!
Option 2: Start with Cloud Providers
- Get an API key from a provider:
- In NodeTool, go to Settings → Providers
- Paste your API key
- Select the provider when using AI nodes
Detailed Guides
General
- Models Manager – Download and manage AI models
- Getting Started – First workflow
Local AI
- Supported Models – List of local models (llama.cpp, MLX, Whisper, Flux)
Cloud AI
- Providers Guide – Set up OpenAI, Anthropic, Google
- HuggingFace Integration – Access 500,000+ models
Advanced
- Proxy & Self-Hosted – Secure deployments
- Deployment Guide – Cloud infrastructure