Image·11 min
Food Photography Prompts That Look Edible
Food photography prompts that avoid the plastic look: which angle suits which dish, hard vs diffuse light, steam and gloss cues, and copy-paste templates by shot type.
Read moreBlog
Better prompts. Better AI results.
Tutorials, comparisons, and frameworks to write better prompts for ChatGPT, Claude, Gemini, Midjourney, Veo3 and Kling.
Page 3 of 29
Video·15 min
Generating B-Roll with AI (Prompt Library)
A 40-prompt AI B-roll library by editing job: establishing, cutaway, texture, transition and background-for-text, plus the aspect ratio, audio and duration settings that decide which clips cut in.
Read moreVideo·13 min
Prompting Multi-Shot Sequences (Scene by Scene)
Multi shot ai video, sorted by what's real: Kling's settings.multi_shot field, Runway's multi_shot_video recipe, LTX and Veo's single-prompt techniques, and what needs separate generations.
Read moreVideo·11 min
Travel and Landscape Video Prompts
Landscape video prompts for aerial vistas, golden-hour light and time-of-day change, with verified aspect ratio, duration and audio fields from Veo 3.1, Kling 3.0 Omni and Runway Gen-4.5.
Read moreImage·16 min
Editing and Inpainting Prompts for GPT Image 2
GPT Image 2 editing and inpainting: exact mask requirements, input fidelity, multi-image edits, and what changes with no mask at all. Verified against OpenAI's own docs, Sept 2026.
Read moreChatGPT·13 min
Perplexity Spaces for Recurring Research
Perplexity Spaces don't exist under that name anymore. What Perplexity documents today as Projects, Deep Research, Model Council and Skills for recurring research, verified September 3, 2026.
Read moreImage·13 min
Text Rendering in FLUX.2 (What Works, What Doesn't)
What Black Forest Labs actually documents about FLUX.2 text rendering, which variant to use, the exact prompting method, and the limits BFL doesn't publish that Ideogram does.
Read moreVideo·13 min
Pacing and Timing in Video Prompts
What actually controls pacing in an AI video prompt: duration and shot counts are real, documented parameters. Slow motion and speed ramps are prompt language on every vendor checked, not a field.
Read moreChatGPT·13 min
Claude System Prompts: What Belongs There
Claude system prompt means three things: the API's system parameter, a claude.ai Project's custom instructions, and Claude Code's CLAUDE.md. What belongs in each, verified against Anthropic's docs.
Read moreImage·14 min
The Anatomy of a Great Image Prompt (Six Parts)
A six-part image prompt structure (subject, setting, composition, light, style, constraints), built one piece at a time and checked against what Google, OpenAI and Ideogram document.
Read moreImage·15 min
FLUX.2 Photorealism Recipes: 10 Prompt Formulas
Ten FLUX.2 photorealism prompt formulas, each built from Black Forest Labs' own documented parameters and prompting guidance, with a copy-paste template and a filled example.
Read moreImage·11 min
Keeping One Visual Style Across a Whole Series
No vendor guarantees a consistent AI art style across a series. OpenAI and Google both name it as a limitation. The honest fix: a style contract, references, one sitting, and curation.
Read moreEngineering·11 min
Comic and Manga Panel Prompting
Comic and manga panel prompting without naming a living artist's style: character sheets, panel-to-panel consistency, shot variety, and why lettering gets added after generation.
Read moreVideo·11 min
Lens and Depth of Field in Video Prompts
No AI video vendor exposes a lens, aperture, or depth-of-field field. What Google, Kling, OpenAI, and LTX actually document instead, and the prompt language that measurably shapes focus.
Read moreEngineering·10 min
Stop Sequences: How and When to Use Them
Stop sequences across OpenAI, Anthropic and Google, verified from each vendor's own API reference — exact field names, why OpenAI blocks stop on o3 and o4-mini, and when a schema beats it.
Read moreVideo·10 min
Camera Control Parameters in AI Video Tools
Camera control in AI video tools, sorted into real API fields versus prompt language only — verified from Kling, Runway, Seedance, Vidu and Veo's own documentation.
Read moreEngineering·11 min
The TAG Prompt Framework
TAG is Task, Action, Goal — the shortest prompt framework in this cluster. What each field does, a worked example proving Goal matters, and the two things it's missing.
Read moreEngineering·11 min
The CREATE Prompt Framework
CREATE is Character, Request, Examples, Adjustments, Type of Output, Extras — six fields for a longer creative brief. Traced to its 2023 source, including where it contradicts itself.
Read moreEngineering·10 min
Naming Prompts So You Can Find Them Later
A working system for naming, describing, and tagging saved prompts, so future-you can find the right one in seconds — not a folder system, a naming one.
Read moreEngineering·10 min
Template It or Write It Fresh? (A Decision Rule)
A simple rule for deciding, before you start typing, whether a task deserves a saved template or is genuinely faster to just write fresh: the three-times rule, with the math behind it.
Read moreEngineering·11 min
Spring-Cleaning Your Prompt Library
A periodic keep, merge, or retire pass for a prompt library you already have — for clutter and quality, not for prompts that broke because a model changed underneath them.
Read moreChatGPT·13 min
How to Make ChatGPT Write Like You
Paste three samples of your own writing, ask ChatGPT to extract the pattern, then save it as a reusable voice profile so new output actually sounds like you.
Read moreChatGPT·12 min
How to Make ChatGPT Cite Real Sources
A model without search access generates plausible-looking citations from its training, not a lookup. Here is the mechanism, a real court sanction, and what each vendor documents for grounding.
Read moreChatGPT·12 min
How to Prompt AI for Maths (And When Not To)
AI does arithmetic unreliably by design. Here's when a prompt is enough, how to force a real calculation instead of a guess, and which numbers you should never trust to a chat window alone.
Read morePage 3 of 29