Rohan Paul· @rohanpaul_ai · X·· 2026-05-06AI 评分73
AI 导读
Luma的Uni-1.1模型现已作为API开放。这是一个用于图像生成和自然语言编辑的统一智能模型，其核心特点是“意图优先”的图像生成。模型在生成前会进行思考，能补全场景缺失部分，理解空间上下文而非仅像素，并能基于参考图像保持一致性。该API内置提示词增强、研究和参考收集功能，专为生产环境打造。据称，其成本和延迟仅为同类模型的一半以下，且在图像生成与编辑的综合评测中位列前三。
正文 · 原文
Luman's Uni-1.1 model is now an API
Unified Intelligence model for image generation and natural-language editing.
So now for example, a studio could wire Uni-1 into an ad pipeline where it reads a product brief, reasons through the visual direction, creates scene variations, checks them against brand rules, and passes the strongest outputs into a review dashboard.
Luma Uni-1 specialize in “intent-first” image generation rather than traditional prompt-by-prompt rendering
- It thinks before generating anything
- Fills in the missing parts of a scene
- Understands spatial context, not only pixels
- Remains grounded in a reference image
#LumaPartner
The Uni-1.1 API is live today. Built-in prompt enhancement, research, and reference gathering at the API level. Trained in collaboration with Hollywood cinematographers, VFX artists, and world-class artists across cultural forms. Less than half the price and latency of comparable models. Designed for builders shipping in production — and ranked top 3 lab in the Image Arena across Text-to-Image and Image Edit. Start Building → https://lumalabs.ai/api在 X 查看被引用的帖子
来源：Rohan Paul · x.com