{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreibe6eta44dea4fzcvij4bwm4opov7ssdkr3sfwzw7fvbegosdonne",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mohsmvdzvdk2"
  },
  "path": "/t/june-2026-theme-through-time-chatgpt-api-image-generative-art-gallery-prompt-tips-and-help/1378298?page=106#post_2148",
  "publishedAt": "2026-06-17T06:59:41.000Z",
  "site": "https://community.openai.com",
  "tags": [
    "(click for more details)"
  ],
  "textContent": "I am wondering, when I create prompts with any LLM, I usually get such texts too, and then I ask to revise them, consolidate redundancies, and remove statements that have no visual descriptors. The non-relevant statements are in a second block. That way I can choose if they can stay or go.\n\nDo you have a similar workflow?\n\nIn particular recent models like GPT 5.5 have a high degree of verbosity that ads a lot of semantic noise.\n\nI took the chance to test my workflow with someone else’s prompt. I bet it can be optimized even further.\n\nRevised Prompt (click for more details)\n\nEdit: Workflow I meant with revised prompt and output.",
  "title": "June 2026 (Theme: Through Time) — ChatGPT / API Image Generative Art Gallery, Prompt Tips, and Help"
}