Imager

Imager is a tool for creating images that capture your vision:

• The process - You start with an idea or text you want an image to represent. You'll go through a guided process where to explore your creative vision, then systematically select the best visual elements (objects, compositions, colors, and styles), and finally generate a prompt and images based on your choices.

  
  

• The goal - Imager is designed to help you think about what you want just as much as creating an image. The goal is to assist you in bringing your genius out.

  
  

• Guardrails - Imager includes guardrails to support responsible image creation, including copyright protection, bias mitigation, and privacy.

Go ahead and take it for a spin, or read more about how it works below. You have 10 free back and forths.

---

How Imager works

Imager guides you through a structured creative process in three stages:

Vision Development

1. Share your content - Upload a text or write about the idea you want the image to represent.

2. Answer three focused questions - Think through your vision for the image

   
   

Creative Selections

Imager will make suggestion based on your input. You will choose between then and refine as needed. You will select the following one by one:

4. Objects - E.g., a tablet, a chair.

5. Composition - These are one-sentence descriptions starring the objects you selected. E.g., "a tablet on a table with an image of a telescope in it"

6. Colors - You will get suggestion for color pallets, each including several complementary colors

7. Artistic style - E.g., Expressionism, realistic photo.

8. Prompt- Imager will put your selections together into a few image prompts to choose from

   
   

Generation & Output

7. Generate your image - Imager creates an image for the prompt you selected. You can also copy your prompt into any image generator if you'd like to try different looks.

8. Refine if needed - If the image doesn't capture your vision, say why and get new prompt suggestions

---

Responsibility Guardrails

Imager is designed for responsible image creation. It incorporates several guardrails, including:

• Copyright - Imager avoids suggesting copyrighted artistic styles and uses descriptive visual features instead of proprietary content. In addition, if users request copyrighted works or branded styles, Imager declines and instead offers descriptive alternatives that capture key visual characteristics

• Bias - Imager is designed to avoid making assumptions about gender, race, age, location, or other characteristics, and instead prioritize representing human diversity thoughtfully

• Critical thinking - Imager encourages your critical thinking with tentative language and provides multiple options for each decision. It uses phrases like "might" and "could be" rather than definitive statements, always asking "does this sound right?"

• Privacy - You data remains yours. Imager runs on platforms that commit not to collect or train on user data.

---

About Imager's creator

My name is Ravit Dotan. My approach to AI combines different parts of my background. Primarily these ones:

• I'm a socially-oriented technologist. I build no-code AI tools to create the world I want to see, and I seek out people who want to do the same.

• I'm an AI ethicist. I've worked with tech companies, investors, and local governments on responsible AI development, adoption, investment, and procurement. Practical responsibility is baked into everything I build and teach.

• I'm a philosopher. I got my PhD from UC Berkeley, specializing in philosophy of machine learning, philosophy of science, and philosophy of knowledge. I've taught hundreds of people to think critically about worldviews and form their own.

  
  

All of this shapes how I think about and build AI. You can read more about me and follow my work on my blog and Linkedin page.

---