Hermes + Comfy UI is Insane (FREE)!
The video demonstrates a new ComfyUI skill added to the Hermes AI agent that enables free local generation of AI images, video, and audio without subscriptions or API costs. The presenter walks through installation, local vs. cloud setup options, and shows how Flux and other models can be controlled remotely via phone through Hermes.
Summary
The video introduces a newly added ComfyUI skill for the Hermes AI agent, which the presenter claims makes the agent significantly more powerful by enabling free, local generation of AI images, video, and audio. The presenter emphasizes that this requires no subscriptions, no API costs, and no complicated manual setup, as Hermes handles the installation and configuration automatically.
The presenter begins by walking through how to update Hermes via terminal using the 'hermes update' command to gain access to the new skill. After updating, the skill's markdown file is loaded into Hermes to confirm it can utilize ComfyUI capabilities. A brief warning is given that after updating, the model may switch unexpectedly to Gemma 4, and users should manually switch back to their preferred model.
Two installation paths are covered: a local install and a cloud-based install via Comfy Cloud. For the local option, Hermes automatically downloads and sets up ComfyUI on the user's machine. The presenter walks through the ComfyUI interface, highlighting templates for text-to-video, image-to-video, reference video, image editing, object swaps, upscaling, background removal, and image segmentation. The Flux model is highlighted as a strong local image generation option at only 12 GB in size.
A standout use case presented is the ability to run Flux locally on a computer, connect it through Hermes, and then send generation prompts from a smartphone remotely, effectively creating a free, personal AI creative studio accessible from anywhere. The presenter also notes integrations with third-party tools like ElevenLabs for text-to-speech and UGC video generation within ComfyUI's template system.
The video closes with a promotion for the presenter's paid community, 'AI Profit Boom,' which offers weekly coaching calls, advanced tutorials, courses on Hermes and Open Claw, and a local networking map for AI users.
Key Insights
- The presenter claims that Hermes AI agent can now fully automate the setup and operation of ComfyUI, handling installation, model downloading, and workflow execution without requiring manual configuration from the user.
- The presenter argues that Flux, at only 12 GB, is a practical and capable local image generation model, framing its size as not a significant storage burden for most users.
- The presenter describes a workflow where Flux runs locally on a desktop, Hermes controls ComfyUI, and a user can send image generation prompts from their phone while away from their computer, effectively enabling a remote AI creative studio.
- The presenter notes that after updating Hermes, the agent may automatically switch to Gemma 4 as the default model, which the presenter characterizes as an undesirable behavior users should watch for and manually correct.
- The presenter states that Hermes can analyze a user's local hardware setup and recommend whether they should run models locally or use cloud-hosted models via Comfy Cloud, positioning it as an intelligent configuration advisor.
Topics
Transcript
[0:00] Hermes AI agent just got a new skill and it makes it 10 times more powerful. You can now generate AI images, video, and audio free from your computer. No subscriptions, no API cost, no complicated setup. Hermes AI agent handles it all of for you and we're talking about photo-realistic images, text video, object swaps, etc. And I'm going to show you exactly how it works step-by-step with ComfyUI today. This is all running locally on your machine or you can host it in the cloud as well. I'll show you both options and which one [0:30] is right for you. And this all triggered by using an asking Hermes AI agent. And the wildest part is you…
Full transcript available for MurmurCast members
Sign Up to AccessMore from Julian Goldie SEO
NEW Nvidia Autonomous AI is WILD!! 🤯
Nvidia announced Nemo Clo, a new autonomous AI agent system that operates independently without continuous prompting. Powered by Nemotron 3 Ultra (a 550 billion parameter model), the system is five times faster and cheaper than previous versions, with OpenShell providing secure sandboxed execution.
Laguna XS 2.1: New FREE + Opensource Local AI!
Julian reviews Laguna XS 2.1, a new free open-source local AI coding model from Poolside that performs comparably to Qwen 3.6 and outperforms Claude Haiku on benchmarks. He demonstrates its practical capabilities by building landing pages and functional apps, highlighting its speed, offline functionality, and multiple deployment options through local setup, Claude Code, or OpenRouter's free API.
How to Run Hermes FREE Forever!
The video demonstrates how to run the Hermes AI agent for free using Gemma 4, a local open-source model from Google, with significant speed improvements through MLX optimization. The setup works on Apple Silicon Macs or via free APIs on Open Router, enabling autonomous agents to work offline and privately without subscription costs.
This NEW Chinese AI is INSANE! (FREE + Open Source!)
Long Cap 2.0 is a new open-source Chinese AI model from a food delivery app company that offers 1 million tokens of free context memory, beats GPT-4.5 on SWE bench pro benchmarks, and uses efficient parameter activation to reduce computational overhead while maintaining high performance.
Claude Code is now FREE: Here’s how…
Google's new Gemma 4 model running on Ollama is 90% faster on Apple Silicon, enabling free Claude Code usage locally without token costs. The setup requires three simple steps: downloading Ollama, Gemma 4, and installing into Claude Code, with alternatives available via OpenRouter API for non-Mac users.