Flux Colab Notebooks — ControlNet, Redux, Inpaint, Outpaint
A set of four free Google Colab / Jupyter notebooks (by LucipherDev) for running Flux.1 in the cloud — ControlNet, Redux image variation, and Fill-based inpainting / outpainting — no local GPU required. Each notebook is open-source on GitHub with a one-click "Open in Colab" badge; a companion mask-drawing UI makes inpainting inside Colab painless.
✓ 100% free — runs in Google Colab, no local GPU or install needed.Requirements
- Google account (free Colab tier works)
- A modern web browser — no local GPU needed
- A Hugging Face account (some Flux weights are gated)
- Free Colab T4 GPU (Colab Pro helps for heavier runs)
Setup steps
- Pick the notebook you need from the list below and open its GitHub page.
- Click the "Open in Colab" badge in the repo README to launch it in Google Colab.
- Run the setup cells top to bottom to install dependencies and download the Flux weights.
- For inpainting / outpainting, use the Colab mask-drawing UI to paint your mask, then run the generate cell.
- Download your results, or mount Google Drive first so outputs persist across sessions.
Notes & tips
- These are the free base notebooks. The Patreon add-on versions add in-notebook Hugging Face LoRA downloads, Gemini/Florence-2 auto-captioning, and Google Drive auto-save.
- Flux weights are large — expect the first setup run to take several minutes.
More resources
- Flux.1 ControlNet notebook (GitHub) https://github.com/LucipherDev/Flux.1-dev-ControlNet-jupyter
- Flux.1 Redux (image variation) notebook (GitHub) https://github.com/LucipherDev/Flux.1-redux-jupyter
- Flux.1 Fill — inpaint / outpaint notebook (GitHub) https://github.com/LucipherDev/Flux.1-fill-jupyter
- Colab mask-drawing UI for inpainting (GitHub) https://github.com/LucipherDev/Colab-Inpaint-Interface-jupyter
Want the 1-click version?
Skip the manual model downloads and node installs — get a ready-to-run installer, or unlock all 75+ with Local Lab Pro.