Dark slides covering eight essentials of image generation

OpenAI just published a full guide on prompting GPT Image 2.6, and it's one of the clearest prompting references I've read.

I turned it into a 40-second video. Here's what's inside:

THE 8 PRINCIPLES
1. Define the result: subject, use, composition, aspect ratio
2. Pick a readable format: prose, labeled sections, or structured text
3. Describe what's visible: materials, lighting, color, framing
4. Specify people and actions: scale, gaze, interaction
5. Quote exact text, state its placement, check the spelling
6. For edits, separate what changes from what must stay
7. Give every reference image a role
8. Iterate one change at a time

TWO MODELS
• Flare (gpt-image-2.6-flare): built for speed
• Sunburst (gpt-image-2.6-sunburst): more detail, more precise edits

PARAMETERS WORTH KNOWING
• quality: auto / low / medium / high / xhigh / max
• size: 1024x1024, 1536x1024, 1024x1536, or custom (multiples of 16, ratio up to 3:1)
• background: transparent output is supported
• output_format: png, jpeg, webp, plus svg and gif

The guide also walks through markup-guided edits, translating text inside images, style transfer, identity-preserving outfit changes, transparent cutouts, sketch-to-render, and object removal.

My takeaway: prompt like a creative director, not a search box. Be specific about what you see, what must stay, and what changes.

Full guide: https://t.co/bCCjDHI6li