Skip to content

SegFault42 /HeliosGen

AI image and video pipelines on a local node canvas
ComfyUI workflowNo licenseEnglish README
Stars
2.3k
30 days
New
Last push
14 days ago

About HeliosGen

HeliosGen is a free desktop app for chaining AI image and video models. Drag prompts, models and reference images onto a node canvas, then run them in order or side by side. It runs on your machine, but you need your own paid kie.ai API key. Only macOS (Apple Silicon) builds are out so far.

Best for: Indie animators who want a local, node-based canvas to chain image and video models without a subscription.

What it does

  • Drags and connects nodes to build reusable image and video pipelines
  • Runs several models in one pipeline, in parallel or in sequence
  • Keeps generation history in a local SQLite database
  • Shows a JSON prompt preview and an AI prompt improvement helper
  • Can send GPT Image 2 through your ChatGPT Codex subscription instead

Quickstart

Rewritten from the README. Check the repo for the latest steps.

  1. 1
    Download the macOS build from the GitHub releases page.
  2. 2
    On macOS, right-click the app and choose Open once, or run the command below.
    xattr -cr /Applications/HeliosGen.app
  3. 3
    Launch HeliosGen, open Settings → API Keys and paste your kie.ai API key.
  4. 4
    Start generating; on macOS your data sits in the command below.
    ~/Library/Application Support/cash.sdd.helios.desktop/
  5. 5
    To build from source: the command below, cd HeliosGen, npm install, npm run desktop:build (needs Node 22+, Rust and Tauri system deps).
    git clone https://github.com/SegFault42/HeliosGen

Models and languages

Models it works with

  • Veo 3.1
  • Kling 3.0
  • Seedance 2.0
  • Nano Banana Pro
  • GPT Image 2
  • Seedream 5.0
  • Z-Image
  • Grok Imagine
  • HappyHorse
  • Gemini Omni Video

Interface and docs

  • English

Alternatives

Other comfyui workflow projects people compare with HeliosGen.

Writes MiniMax H3 video prompts from your images, video and audio

ComfyUI workflow
  • MiniMax H3
  • Claude
  • GPT-4o
  • +6
241 GitHub stars18 days agoGPL-3.0

A few ComfyUI nodes for MiniMax H3 video, with less hand-wiring

ComfyUI workflow
  • MiniMax H3
  • Ollama
798 GitHub stars2 days agoMIT

Plans, generates and fixes AI video scenes in ComfyUI

ComfyUI workflow
  • LTX 2.3
  • MiniMax H3
  • Z-Image
  • +2
740 GitHub starstodayCustom license

Puts WanVideo and related video models inside ComfyUI

ComfyUI workflow
  • Wan 2.1
  • Wan 2.2
  • SkyReels V2
  • +7
6.7k GitHub stars4 months agoApache-2.0

Featured on OpenMicroDrama

Do you maintain HeliosGen? Add this badge to your README so English speakers can find our write-up.

Featured on OpenMicroDrama
markdown
[![Featured on OpenMicroDrama](https://openmicrodrama.com/badges/featured.svg)](https://openmicrodrama.com/projects/segfault42-heliosgen)

The badge links to this page. Want your description changed? Email support@openmicrodrama.com.

Reviewed Oct 1, 2026. Repo metadata lists no license file, though the README says MIT; Windows and Linux builds aren't published yet. We write these descriptions ourselves. The repo's own docs are the final word.