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

How to generate a new picture from boxes and reference images with Scumble

Draw boxes on an empty canvas, describe each one, and have FLUX 3 Image build the scene.

  • Content
  • Beginner
  • 30 minutes
  • From the README
  • Any agent

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

Credentials. The Black Forest Labs key is billed directly to your account, so store it only in Scumble's settings where the system credential store keeps it.

Who it is forA content creator planning a composed image who wants to say where each element goes instead of writing one long prompt.

The problemText prompts alone give little control over where people, objects and words end up in a generated scene.

The outcomeA generated picture where each boxed area follows its description, with reference layers named @img1 and @img2 in the prompt and returned as layers.

What you need first

  • Windows 10 or 11, 64-bit (the README lists Windows as the platform that runs today)
  • Either an API key for a supported provider such as Black Forest Labs, OpenAI, Google or fal.ai, or a ComfyUI server with the ComfyUI-InpaintCanvas node pack installed
  • A picture to edit, and a short written description of the change

Steps

  1. Install Scumble from the Microsoft Store with winget install scumble, or use the installer from the latest GitHub release.
  2. Open Settings with Ctrl+, , go to API providers, and paste your Black Forest Labs key for FLUX 3 Image, then press Save.
  3. On an empty canvas, draw a box for each element and describe it as something new, something kept, moved or removed, or words to render.
  4. Add a reference picture as a layer and name it in the prompt as @img1, then choose Generate new.
  5. Check the result layer, adjust the Match slider if needed, and export when the scene is correct.

Prompt for your agent

Using the Scumble repo at https://github.com/DenRakEiw/scumble, create a new image on an empty canvas with boxes described as <list of box descriptions> using FLUX 3 Image with my Black Forest Labs key. Expected output: a generated picture returned as a layer. Verify that each boxed area reflects its description.

Caveat. The README says boxes for FLUX 3 Image work on every provider Scumble runs it on, but the Black Forest Labs route is the one it confirms ran live with boxes.

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