{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreic4izx6sgamqnlrscr3wn7wwphsq5bymteoymo27mpii2etba7r7a",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mmgbrk3jj4y2"
  },
  "path": "/t/may-2026-chatgpt-api-image-gallery-prompt-tips-and-help-generative-art-theme-science/1378298?page=58#post_1176",
  "publishedAt": "2026-05-22T04:29:02.000Z",
  "site": "https://community.openai.com",
  "textContent": "If you’ve got a bunch of logged API calls to original GPT-Image-1 model, you also have a lot of symptoms recorded. Fixin’ Time!\n\nIf you were to have requested API loading previews, you got a partial image that looked pretty good and promising. But then, the final image was twisted and distorted from what could have been - and from expectations.\n\nFor example, see this prior use of image-1 (that was an example use-case). It is a multi-image edit, replacing clothes by prompt. See the preview. Then see the over-sharp and over-imagined convoluted output - our subject from the input image even changes ethnicity!\n\nNo joke - this is the same API request, preview to final that is being switched in the animated GIF.\n\nNo matter. Let’s take that partial image, the bottom half of which was unfinished (the API just gives a fake blur there). Then have today’s gpt-image-2 model finish the job, that job being a prompted repair on the edits endpoint with the full-length preview.\n\nResult? She is back to her original identity, and a less over-sharpened, twisted mess is teased out of the low-res preview.\n\n### Animated again between input preview and output:\n\n### Final - quality:medium\n\n### Final - quality:high\n\nThe remainder all inferred.\n\nNow let’s go for another outfit change, prompted, since I don’t have a drive full of fashion. A sun dress? [sexual; denied] (and gpt-image-1 didn’t like her as input before either..). Same prompt, different “quality”?\n\n\n",
  "title": "May 2026 — ChatGPT / API Image Gallery, Prompt Tips, and Help: Generative Art Theme: Science"
}