MiniMax H3-Image 登顶 Multi-Image Edit Arena 开源模型第一
MiniMax H3-Image is the #1 open model in Multi-Image Edit Arena, scoring 1365 (#11 overall) and tied...
MiniMax 这次的 H3-Image 是开源的，多图编辑能打平谷歌的 Nano Banana，2K 编辑只要十几秒。做图像工具或者想本地部署的朋友可以直接去 Hugging Face 下权重试试，首周 API 还有半价。
MiniMax 发布开源图像生成与编辑模型 H3-Image，在 Multi-Image Edit Arena 以 1365 分排名第 11，成为该榜第一的开源模型，并与 Nano Banana 2、Nano Banana Pro 打平，也是榜单前 20 中唯一的开源模型。该模型支持最高 1600 万像素（4K）分辨率生成，可最多使用 16 张参考图，官方称 2K 图像编辑生成时间约 10-15 秒，比 Nano Banana 2.1 快 3 倍。
在其他榜单上，H3-Image 以 1359 分位列 Single-Image Edit 开源模型第二（与 Qwen-Image-2.1 打平），以 1197 分位列 Text-to-Image 开源第三（与 Ideogram 4.0 打平）。模型权重已在 Hugging Face 开放，用户可通过 MiniMax API、MiniMax Code 和 Hailuo AI 使用，上线首周 16MP 以上的生成享 5 折优惠。
在闭源模型长期占据图像编辑榜前列的背景下，H3-Image 的成绩显示开源模型在多图编辑、高分辨率生成等能力上正在缩小与闭源前沿的差距。对需要在本地部署或自建图像编辑流程的开发者来说，这是一个可直接使用的高分辨率选项。
MiniMax H3-Image is the #1 open model in Multi-Image Edit Arena, scoring 1365 (#11 overall) and tied...
MiniMax H3-Image is the #1 open model in Multi-Image Edit Arena, scoring 1365 ( #11 overall) and tied with Nano Banana 2 and Nano Banana Pro. It is the only open model in the top 20. It also lands: - #2 open model in Single-Image Edit (1359, tied with Qwen-Image-2.1) - #3 open in Text-to-Image (1197, tied with Ideogram 4.0) The lab reports this as the fastest 2K image editing model: 3x faster than Nano Banana 2.1 at 10-15s of generation time for 2K editing. Open weights are starting to close the gap towards the frontier. Congrats to the @minimax_AI team! MiniMax (official) @MiniMax_AI 4K image generation in 10 seconds! ⚡ Meet MiniMax H3-Image. 16 million pixel resolution. Stunning realism. Precise prompt following & editing. Up to 16 reference images. All in 10 seconds. And it's open-weight. 🚀 Available now via our API, MiniMax Code, and Hailuo AI — with 50% off 16MP+ generations during launch week! Can't wait to see what you create. 🔥 Hugging Face huggingface.co/MiniMaxAI/Mini… g0 API platform.minimax.io/docs/guides/im… cM MiniMax Code: code.minimax.io/about CL
This report is categorized under AITOP's "Models" desk, focusing on China's AI industry and domestic foundation model ecosystem. Within our cross-regional analytical framework, it directly maps to US-China foundation model benchmarks and commercialization comparison and AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include MiniMax, H3-Image, Nano Banana, Qwen-Image.
Source attribution: curated from lmarena.ai (@lmarena_ai).
