用户报告称，OpenAI 的 GPT-Image-2 模型在通过 Codex 访问时，未能有效利用参考图像。该模型似乎忽略了提供的参考图像的风格元素、调色板和内容，而是默认输出其自身的标准结果。这种行为与之前的版本不同，导致用户质疑问题出在模型本身还是其在 Codex 中的集成。 AI
影响 AI 艺术工具的图像生成质量和用户控制能力可能下降。
排序理由 用户报告特定产品功能未能按预期工作。
AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →
OpenAI 的 GPT-Image-2 通过 Codex 无法使用参考图像
本文如何被排名
- Signal score
- 18 / 100
- Composite score across the factors below. Higher = stronger signal that this story matters right now.
- Newsworthiness bucket
- Tool
- 用户报告特定产品功能未能按预期工作。
- Source corroboration
- Single-source cluster
- Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
- Topics
- product
- Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
- AI-industry relevance
- High
- Clearly on-topic for AI-industry coverage.
- Story freshness
- Breaking (< 6h)
- Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.
完整方法见我们的编辑标准。
报道来源 [1]
-
GPT Image 2 是否会使用参考图像进行处理？（来自 Codex）
<!-- SC_OFF --><div class="md"><p>I'm calling it through Codex, uploading a reference and asking for a new subject in that look. Nothing carries. Not the style, not the palette, not the line quality, not the content. I get the model's house look with zero trace of what I gave it.…