DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to run image and video generation fully offline with Comfy UI

Install Comfy UI locally, start it with --offline, and keep generation off external services.

  • Content
  • Intermediate
  • 90 minutes
  • From the README
  • Any agent

Authorization notice. Comfy UI is dual-use. Only use it on software, sites and systems you own or have explicit permission to test.

Who it is forA studio or freelancer handling confidential client assets who must keep prompts, images, and models on their own machine.

The problemCloud generation services send prompts and outputs to third parties, which may break client confidentiality rules.

The outcomeA local Comfy UI session that generates media without calling the paid API nodes or downloading anything you did not request.

What you need first

  • A Windows or macOS computer for the desktop app, or a Windows, Linux, or macOS machine with a supported GPU for the manual install
  • A GPU with enough VRAM for the model you pick (the README says large models can run on as little as 4GB VRAM with 8GB RAM)
  • Disk space for the model files you choose to download
  • Optional: a Comfy Cloud account or partner node access for paid hosted models

Steps

  1. Follow the Manual Install section of the README (https://github.com/Comfy-Org/ComfyUI#manual-install-windows-linux) for your operating system and GPU type.
  2. Start Comfy UI from the install folder with python main.py --offline. (inferred, check the README)
  3. Place your model files in the model folders, or point to them by copying extra_model_paths.yaml.example to extra_model_paths.yaml and editing the paths.
  4. Build or load a workflow from the local template library and queue it with Ctrl + Enter.
  5. Confirm the paid API nodes are not used, then export results from your local output folder.

Prompt for your agent

Using the ComfyUI repo at https://github.com/Comfy-Org/ComfyUI, start ComfyUI in offline mode on <target machine> and run the workflow <workflow file> with the model stored at <model path>. Expected output: generated media files saved locally with no network calls to paid API nodes. Verify that the server log shows offline mode and that no outbound requests were made during the run.

Caveat. The README says core does not download anything unless requested, but you must still check each custom node you install, since custom nodes are separate code and the README does not say what they do with the network.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page