prompts.

and magazines showing crisp covers. Multiple illuminated billboards and neon signs feature perfectly legible text:

A photorealistic image of a red fox sitting in a snowy forest at dusk.

Transform this product image into a premium e-commerce poster style.

** ``` Transform this product image into a premium e-commerce poster style.

Generate a vintage diner chalkboard reading "TODAY SPECIAL — Lobster Roll $24"

Edit https://example.com/photo.png — same scene but everyone is on their phones now

/codex-image a red apple on white background

A photorealistic candid photograph taken with flash at a crowded house party in 2008. The camera angle is slightly tilted, capturing a kitchen scene. In the foreground, a red plastic cup sits on a counter with a Sharpie-written name tag reading 'JASON' in messy capital letters. Behind it, a girl with side-swept bangs and a striped American Apparel tank top is laughing with her eyes closed, holding a flip phone up as if taking a photo of the photographer. On the fridge behind her, a printed paper reads 'NO BEER IN THE FREEZER!!! - Mom' in Arial font, taped with Scotch tape. A digital oven clock in the background shows '11:47' in green LED. The photo has harsh direct flash lighting, red-eye on one person in the background, slightly blown-out highlights, and the warm-yellow cast of a 2008 digital point-and-shoot. The bottom of the image has a subtle Facebook watermark from when it was re-uploaded in 2012. Every text element must be era-accurate and physically correct.

"reframe this image to show the behind the scenes. A photo taken from a third party behind the directory as the scene plays out"

A stunning 18-year-old Chinese girl with a youthful, pure face and realistic skin texture, sitting on a cozy, slightly messy bed in her bedroom. She is taking a mirror selfie with a smartphone, capturing a natural and intimate moment.

Make a 15×15 grid starting with 1000 BC to 2026. In each section, show a unique invention diorama that changed the world at its time, no repeats. Use colors, background, & era relevant components

> **Language:** English · **Quality:** A · **Source:** promptgather <details><summary>Prompt · English</summary> ```text A photorealistic candid photograph taken with flash at a crowded house party in 2008. The camera angle is slightly tilted, capturing a kitchen scene. In the foreground, a red plastic cup sits on a counter with a Sharpie-written name tag reading 'JASON' in messy capital letters. Behind it, a girl with side-swept bangs and a striped American Apparel tank top is laughing with her eyes closed, holding a flip phone up as if taking a photo of the photographer. On the fridge behind her, a printed paper reads 'NO BEER IN THE FREEZER!!! - Mom' in Arial font, taped with Scotch tape. A digital oven clock in the background shows '11:47' in green LED. The photo has harsh direct flash lighting, red-eye on one person in the background, slightly blown-out highlights, and the warm-yellow cast of a 2008 digital point-and-shoot. The bottom of the image has a subtle Facebook watermark from when it was re-uploaded in 2012. Every text element must be era-accurate and physically correct. ``` Author: @GlitterPixely<br>Channel: promptgather<br>Date: 2026-04-23<br>Source: [https://promptgather.io/prompts/gpt-image-2](https://promptgather.io/prompts/gpt-image-2) </details> ### 23. Behind the Director: The Vader Reveal Scene Unseen Angle <img src=

beautiful stunning ultra-detailed 4K 8K masterpiece trending on artstation cinematic lighting professional photography premium quality

Create a pitch-deck slide titled "Q3 Revenue Performance" that looks like a real Series A board-meeting slide. Layout (16:9): title top-left, 36pt Inter dark gray. Two-column body: left 60% chart, right 40% three KPI cards. Chart: vertical bars, Q1–Q3 2026, y-axis $0–$8M, three bars at $3.2M, $4.8M, $6.5M, muted blue palette. KPI cards: "+34% YoY", "189 new accounts", "$42K ACV". White background, Inter typography, tight 8px grid, no clip art, no gradients, no stock photography.

注意里面**没有**:没有夸赞词、没有"ultra detailed"、没有"8K"。每一个词都在做具体的指令性工作。 Skill 教 Claude(或任何 agent)规范结构:

Skill 就是文本 + 一个脚本。无构建、无重启、无注册。 ### 给你的团队定制 Fork 一份。设计上可以替换的部分: - **`references/use-cases.md`** — 加你们自家风格、品牌色卡、常用素材模板(自家的 pitch-deck 模板、自家的品牌 hex、自家的信息图格式) - **`scripts/gpt_image.py`** — 加 `--watermark` flag、自定义输出命名、S3 上传、Slack 推送、随便加 - **`DEFAULT_BASE`** — 指向你们的私有网关而不是默认值 - **agent 拿到的 system prompt** — 如果你们的 agent 不会自动发现就把 `SKILL.md` 接进 bootstrap 通用的改动欢迎 PR。团队特定的留在你的 fork 里。 ### License MIT。看 `LICENSE`。随便用。 ### 致谢 为 [Claude Code](https://claude.com/claude-code) 而做,但这个模式(markdown skill + 零依赖 CLI + 视觉自验证)适用于任何能读文件 + 调脚本的 agent。 灵感:OpenAI 官方 GPT Image 2 Cookbook,Anthropic superpowers/writing-skills 关于 agent 可发现 skill 的模式。 --- ## English > Drop this into Claude Code or Codex. Your agent will go from "here's a curl command, good luck" to producing pitch-deck slides, Chinese posters, pixel-art tilesets, photoreal product shots, and surgical photo edits — first try, every try. GPT Image 2 dropped in April 2026. It's a generational leap: long instructional prompts no longer lose detail, text rendering is finally correct (Chinese / Japanese / Korean too), custom resolutions go up to 3840px, and the edit endpoint does precise local edits via a `change ONLY X / preserve Y exactly` pattern. But here's the catch: agents trained before April 2026 don't know any of this. They write prompts the old way — *"4K, ultra detailed, masterpiece, trending on artstation"* — which on GPT Image 2 is at best ignored and often actively harmful. They paste curl commands instead of saving files. They generate, then ask the user "does this look right?" instead of looking themselves. This skill fixes all of that. ### What you get

4K, ultra detailed, masterpiece, trending on artstation

Every panorama is one step in a walking route. - The camera stays at human eye height.

小红书爆款封面、Keynote 级 PPT 配图、热力图 / 流程图 / SWOT、公众号文章逻辑图——一个 Skill 全搞定。 12 种内置视觉风格，从 Apple Keynote 极简到中式宋体留白，从赛博霓虹到杂志撞色，每种都按真实设计师的方法论拆细到 hex / 字体 / Do & Don't。

12 种内置视觉风格，从 Apple Keynote 极简到中式宋体留白，从赛博霓虹到杂志撞色，每种都按真实设计师的方法论拆细到 hex / 字体 / Do & Don't。

「画张小红书封面：标题"我用AI每天读100篇文章"，xhs-vibrant 风格」 「做张PPT配图：核心观点 Context, not Prompts，minimal 风格」 「画个产品路线图，dark-atmospheric 风格」 「为我这篇文章批量配 6 张图，sketch-notes 风格」 「整套幻灯片：把这份 markdown 转成 12 页 deck」

Use imagegen to create an image with this request: { \

frosted glass serum bottle with matte white cap\

soft diffused studio lighting\