{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreif7klqojf2thyuqrzrym6mg3t3q3c66x2vhhch3bkeluavhqahudm",
"uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3ml25o6kndit2"
},
"path": "/t/collection-of-gpt-image-generator-2-0-issues-bugs-and-work-around-tips-check-first-post/1379535?page=7#post_136",
"publishedAt": "2026-05-04T16:07:10.000Z",
"site": "https://community.openai.com",
"tags": [
"(click for more details)"
],
"textContent": "It looks like the model is **stumbling** when it tries to calculate complex light interactions (caustics) with fine, volumetric, repeating textures. I suspect the neural network is either trying to **cut corners** to save resources by applying a procedural Voronoi (?) pattern, or it’s getting **bogged down** in these complex calculations and just outputting whatever is left over. These are just my assumptions.\nI tried this prompt, and here’s the result.\n\nPrompt v 1 (click for more details)\n\nThen I asked Qwen to analyze the image and look for solutions on the web. It **cheated a bit** by describing slightly larger obsidian shards and removing the dust, but the **direct ban on repeating patterns** seems to have worked. Either way, the quality of the second image is much higher.\n\nPrompt v2 (click for more details)\n\nPosting the second picture in the reply since I’m a new user and can only attach one media per post.",
"title": "Collection of GPT-image-generator 2.0 issues, bugs, and work-around tips (check first post)"
}