Features
Node-based visual workflow editor on infinite canvas
Supports image, video, 3D, and audio generation
App Mode for simplified workflow interaction
Comfy Cloud: cloud GPU execution with usage-based credits
Comfy API: run workflows programmatically with concurrency limits
Comfy MCP: AI agent connectivity via Model Context Protocol (local and cloud)
Comfy CLI: terminal-based generation with partner models (beta, 30+ providers)
60,000+ custom nodes and thousands of community workflows
Pre-installed 900+ models on cloud
Import custom LoRAs and models from CivitAI or Hugging Face (Creator/Pro plans)
Proprietary Partner Nodes for premium models (e.g., Nano Banana)
Workflow queuing up to 100 jobs
Partial execution and subgraph support (Nodes 2.0)
int8 Model Support for Turing GPUs+ (v0.27.0)
Ray 3.2: frame-by-frame video control and continuity across cuts
Uni-1.1: brand intelligence with style and character references
Luma Skills: reusable creative workflows for consistent output
Modify Video: video-to-video editing
Reframe: outpaint images and reframe videos
Camera Motion Concepts: learnable camera controls
Automatic continuity across video cuts
Cinematic quality finishing
Agent-driven research and refinement across video, image, audio, text
Team members and admins management
Fast variant generation: ten directions before standup
API access for Ray 3.2 and Uni-1.1
Third-party model integration (Veo 3.1, Kling Omni, GPT Image 2)
Image generation with GPT Image 2, Nano Banana, Seedream
Audio generation: ElevenLabs TTS, SFX, music
