runcomfy-cli
RunComfy CLI is a single binary that connects you to hundreds of AI model endpoints—image generation, video creation, editing, face swap, lip-sync, and more—all from the command line. Install once, authenticate once, then invoke any model with `runcomfy run` and JSON inputs. This skill teaches installation, login, model discovery, invocation modes (sync, poll, no-wait), JSON scripting, and error handling.
RunComfy CLI installs a single command-line tool for accessing hundreds of AI model endpoints with one authentication.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-05-15
RunComfy CLI installs a single command-line tool for accessing hundreds of AI model endpoints with one authentication. RunComfy CLI is a single binary that connects you to hundreds of AI model endpoints—image generation, video creation, editing, face swap, lip-sync, and more—all from the command line. Install once, authenticate once, then invoke any model with `runcomfy run` and JSON inputs. This skill teaches installation, login, model discovery, invocation modes (sync, poll, no-wait), JSON scripting, and error handling.
Use it when
- RunComfy CLI lets you invoke image generation models via `runcomfy run` with JSON inputs.
- Yes.
Verify before relying
Read SKILL.md below before installing (1 file). Open directory: indexed for reading, not audited.
Install
prime-skills/runcomfy-agent-skills/runcomfy-cli
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How to install runcomfy CLI?
RunComfy CLI is a single binary that installs in seconds. Download the appropriate release for your OS from the official repository, make it executable, and add it to your PATH. Once installed, authenticate with `runcomfy login` using your API key, then verify with `runcomfy whoami`. You're ready to invoke hundreds of AI models from the command line.
How do I run an image generation model from the command line?
RunComfy CLI lets you invoke image generation models via `runcomfy run` with JSON inputs. Discover available models and their schemas using `runcomfy model discovery` or by browsing the RunComfy catalog. Pass your prompt and parameters as JSON, and the CLI returns results—either synchronously or asynchronously depending on your flags.
Can I submit a job to runcomfy without waiting for results?
Yes. RunComfy CLI supports async submission with the `--no-wait` flag, which returns a job ID immediately without blocking. Poll the status later using `runcomfy status <job-id>` to check progress, or set up a polling loop in your script. This pattern is ideal for batch processing and automation workflows.
How does runcomfy CLI handle batch image generation and JSON scripting?
RunComfy CLI outputs JSON by default, making it perfect for piping to tools like `jq` and scripting. Batch process multiple requests by looping over inputs, submitting each with `runcomfy run`, and collecting results. Parse JSON output to extract model results, job IDs, or error codes, then automate downstream tasks like filtering or uploading.
What models can runcomfy CLI invoke beyond image generation?
RunComfy CLI connects to hundreds of endpoints including video creation, face swap, lip-sync, and video editing models. Use `runcomfy model discovery` to explore the full catalog and retrieve schemas for each model. Every model accepts the same CLI invocation pattern: `runcomfy run <model-name>` with JSON parameters.
How do I authenticate and set up my API key for runcomfy?
RunComfy CLI authenticates via `runcomfy login`, which prompts for your API key. Store it securely—the CLI caches credentials locally. Verify authentication anytime with `runcomfy whoami`. If you need to switch accounts or reset, simply run `runcomfy login` again. The MIT license covers all CLI usage.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
RunComfy CLI
One binary, one auth, every RunComfy model. Install
(truncated - see the full file via the links below)
File tree — 1 file
runcomfy-cli/SKILL.md
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Install and authenticate the runcomfy CLI to access model endpoints”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
Route text and image prompts to the right AI video model via RunComfy's CLI. The skill handles model selection across HappyHorse, Kling, Seedance, Veo, Wan, and others—each optimized for different outputs like in-pass audio, multi-shot character consistency, or physics-accurate motion. Get the exact `runcomfy run` command and prompt patterns for your use case.
Create and edit images using RunComfy's CLI with access to over a dozen AI models including FLUX 2, Google Nano Banana, OpenAI GPT Image 2, ByteDance Seedream, and others. The skill intelligently routes your request to the right model based on your intent—whether you need photoreal portraits, fast iteration, precise typography, or open-weights workflows—and provides the exact command to run.
Route your audio and image inputs across RunComfy's avatar models to generate talking-head videos with natural lip-sync and gestures. The skill picks the right model for your intent—whether you need a photoreal presenter, stylized character animation, or cinematic multi-modal composition—and provides the exact CLI command and prompting pattern for each.
Execute lightweight validation across 18 Aliyun Model Studio capabilities—text-to-image, video generation, TTS, ASR, speech translation, voice cloning, omni multimodal, visual reasoning, embedding, and reranking. Run one small request per skill, record results, and verify API connectivity and model availability.
This skill enables you to execute and automate command-line operations directly through a native agent interface. Streamline your workflow by running terminal commands programmatically, making it ideal for scripting, system administration, and task automation across your environment.
Launch agents with flexible LLM provider selection across Claude, OpenAI, CrewAI, Lyzr, GitHub Models, and other adapters. Supports local directories, remote git repositories, and one-shot prompts for immediate execution. Auto-detection identifies the best adapter from your repo's configuration.