Skip to main content
The Human Bit
Ask Bit

GuidesBy featureAnyone making a visual for a document, post, product or idea

Generating and editing images without losing the plot

For Anyone making a visual for a document, post, product or idea.

Image tools can create a picture from a description or edit an existing one on request, which is useful for drafts, ideas and simple visuals. They are not a replacement for a professional illustrator or photographer when accuracy, likeness or rights matter.

When to use this

You need an image quickly, a mockup, an illustration for a document, a variation on an existing photo, or a rough visual to explain an idea.

  • Turns a written description into a first draft image to react to
  • Edits an existing image on request, such as changing a background or removing an object
  • Produces quick variations so you can compare directions before committing

Workflow

  1. Describe the subject, style and purpose clearly, including what should not be in the image

  2. Ask for a few variations rather than treating the first result as final

  3. Look closely at detail, text and any people depicted before you use it anywhere

  4. For edits, be specific about what should change and what must stay exactly as it is

  5. Check any usage terms if the image will appear somewhere public or commercial

Prompts to try

Use it, adapt it, and make it your own.

Create an image of [subject], in [style], for [purpose]. Keep it simple and clean, avoid [things to exclude]. Show me a few directions before I pick one to refine further.
Ask Bit to adapt it →

Human lens

  • You decide whether an AI image is appropriate here, or a real photo or professional artist is needed
  • You check for anything odd, wrong or unintentionally offensive before you use it
  • You are responsible for who appears in an image and whether you have the right to use it that way

What to avoid

  • Generated images can misrender text, hands or fine detail, look closely before you use one
  • Do not generate a real, identifiable person without their consent, even when the tool allows it technically
  • Some settings restrict how AI generated images can be used, especially in commercial or news contexts

Related guides

View all →

Using deep research without trusting it blindly

Deep research modes read many sources and return a longer, cited answer. They are powerful for a first pass, and they still need you to check the sources and the reasoning.

Letting an assistant take multiple steps on its own

Agentic modes plan a task, take a sequence of actions such as browsing, running code or editing files, and check their own progress along the way. They can save real time on chores with several steps, and they can also wander off course, so you set the boundaries and check the outcome.

Using projects to keep AI in context, not starting over

Projects or workspaces let you gather files, instructions and past chats in one place, so the assistant carries the right context into every new conversation instead of you repeating it each time.

Talking to AI out loud instead of typing

Voice modes let you speak naturally and hear a spoken reply, which suits thinking out loud, practising a conversation or getting help while your hands are busy. It is a different medium from text, not a smarter version of it.

Tools that fit: ChatGPT, Gemini, Grok · Reviewed 2026-07-19