Image Gen Prompt Framework: Complete Guide with Examples (2026)

Last updated June 28, 2026 · 1 example · Works with ChatGPT, Claude, Gemini

Quick Answer

Image Gen is a seven-field framework for AI image generation: Subject describes what to depict, Style specifies the visual aesthetic, Lighting controls illumination, Composition directs framing, Mood sets atmosphere, Negative lists exclusions, and Parameters adds model-specific flags. Works with Midjourney, DALL·E 3, Stable Diffusion, Flux, and Ideogram.

What Is the Image Gen Prompt Framework?

Image generation prompts require a completely different structure from language prompts. The most common mistake is writing a single descriptive sentence. The Image Gen framework breaks the prompt into seven orthogonal dimensions, each controlling a separate aspect of the output. The Negative field is particularly important: telling the model what to exclude is often as impactful as telling it what to include.

What Does Image Gen Stand For?

Structured template for Midjourney, DALL·E, Stable Diffusion, and Flux.

Subject

The primary subject and scene. Who or what is depicted, what are they doing, and where? Be specific.

Style

The visual aesthetic — photorealistic, oil painting, anime, vector illustration, cinematic. Can reference a specific artist or art movement.

Lighting

Illumination type — golden hour, studio, neon, volumetric fog, backlit, dramatic shadows, soft diffused.

Composition

Framing and perspective — close-up portrait, wide shot, bird's eye view, rule of thirds, symmetrical.

Mood

Emotional atmosphere — serene, tense, nostalgic, futuristic, melancholic. Controls color palette and energy.

Negative

What to exclude — blurry, watermark, text, extra limbs, low quality, deformed. Critical for Stable Diffusion and Flux.

Parameters

Model-specific flags — --ar 16:9, --v 6.1 (Midjourney); cfg_scale, steps (Stable Diffusion); quality (DALL·E 3).

When to Use Image Gen

Use the Image Gen framework for any AI image generation task. For video generation, use the Video Gen framework which adds Motion and Camera fields.

Image Gen Examples

Product hero image

Subject: A minimalist dark-themed web application interface showing glowing bubble nodes connected by thin lines, floating in space.

Style: Cinematic 3D render, dark UI aesthetic, similar to Linear or Vercel product marketing visuals.

Lighting: Deep space background, neon teal and purple accent glow from interface elements, subtle lens flare.

Composition: Centered, slight angle (15 degrees), interface filling 70% of frame, floating above a dark gradient.

Mood: Futuristic, premium, calm. The feeling of powerful software that is also beautiful.

Negative: Text, watermark, blurry, low resolution, cluttered, busy background, people.

Parameters: --ar 16:9 --v 6.1 --style raw

Image Gen vs Other Frameworks

Image Gen vs Video Gen: Video Gen adds Motion and Camera fields for video generation. Image Gen is for static images only.

Use this Image Gen template in Promptary — free

Save your first Image Gen prompt in the structured editor and get a permanent REST API endpoint. Personal plan is free forever, no credit card required.

Start free

Frequently Asked Questions

What AI image generators work with this framework?

The Image Gen framework works with all major models: Midjourney (v6+), DALL·E 3, Stable Diffusion, Flux, Ideogram, and Adobe Firefly. The Parameters field handles model-specific flags.

How important is the Negative field?

Very — especially for Stable Diffusion and Flux. Without it, models frequently produce blurry backgrounds, extra limbs, and watermarks. Always fill it in, even with just: blurry, low quality, watermark, deformed.

Can I save image generation prompts and version them in Promptary?

Yes. Promptary's Image Gen framework saves each field separately. Team plan users get version history for every edit, and any saved prompt is accessible via the REST API.