MiniMax-H3-Image-PE：MiniMax 为其图像模型推出了一款 27B 的提示词扩展器，却未告知任何人

There is no launch post for MiniMax-H3-Image-PE. There is no entry on M​iniMax's news feed, no blog, no changelog line, no social post — on 2026-11-11 the company's news index lists H3, M3.1 Flash, Speech 2.8 and Music 3.0, and nothing about images at all. What exists instead is a Hugging Face repository whose first commit is timestamped 2026-11-10 at 14:38 UTC, a model card that never states a release date, and a license file dated November 10, 2026. That is the whole announcement. MiniMax-H3-Image-PE is a prompt-expansion model — a caption writer — built to feed its sibling MiniMax-H3-Image, the open-weights 33.1B image generator M​iniMax published on 2026-11-03. The image model got eight days of quiet; its prompt expander has had one. Everything below that carries a number comes from those two repositories, the license text, or M​iniMax's own API documentation, and where something is not knowable from those sources it is marked as such rather than guessed. MiniMax-H3-Image and MiniMax-H3-Image-PE are not on OrcaRouter as of 2026-11-11, so this is a self-hosted evaluation. the catalogue The rest of the catalogue is one key away when you want to compare the expansion against a text model you already trust.

The short version, for anyone deciding whether to care: this model does not draw anything. You give it a sentence, it gives you back a long English description of the image you meant plus a recommended aspect ratio, wrapped in a two-key JSON object. A 27B model exists to write that paragraph because MiniMax-H3-Image is unusually fussy about its input — the parent card says it "expects a detailed English description of the whole image" and truncates anything past 4096 tokens. If you have ever typed six words into an image model and gotten six words' worth of thinking back, that gap is what this repository is trying to close, and on 2026-11-10 M​iniMax open-sourced its side of the fix.

仓库里实际有什么，以及时间戳说明了什么

The repository is MiniMaxAI/MiniMax-H3-Image-PE on Hugging Face. Its creation timestamp is 2026-11-08 15:35 UTC; its first commit — unhelpfully titled "Init MiniMaxAI/MiniMax-H3-Image-PE" — landed two days later, on 2026-11-10 at 14:38 UTC, authored by M​iniMax staff accounts ryanlee-dev and 500kg. A second commit followed 38 minutes later adding a Diffusers usage section, and that one is a pull request merged from Hugging Face's own multimodalart, which tells you the diffusers integration was contributed from outside M​iniMax rather than shipped by it. Three pull requests were opened against the repo on its first day, all closed or merged. None of them is an announcement.

What is inside is a checkpoint in four safetensors shards totalling roughly 17.9 GB, a tokenizer, a chat template, a quantisation config, and — the part that matters more than the weights — a prompt/ directory containing the actual system prompt, task prompt and request parameters M​iniMax uses. There is also a single client script, scripts/expand_prompt.py. The repository declares 27.4B parameters in total across two tensor types: about 25.6B stored as U8 and 1.76B left in BF16. That split is explained by the quantisation config, which records NVFP4 with a group size of 16 and lists the modules held out of quantisation — the embedding table and the convolution and gating projections inside each linear-attention block.

The base model is stated plainly on the card and in the metadata: Qwen3.8-27B, the Apache 2.0 vision-language model Q​wen published on 2026-08-05. So the architecture is Q​wen's, the weights are M​iniMax's fine-tune, and the packaging — NVFP4 rather than BF16 — is M​iniMax optimising for deployment rather than for redistribution fidelity. The card says the FP4 weights occupy about 19 GiB of GPU memory and that GPUs with native FP4 support run the NVFP4 weights directly while others fall back to bitsandbytes.

它具体做什么

仓库里有两套工作流，它们并不是一回事。这是在下载 18 GB 之前最需要弄明白的一件事。

• 文生图 PE——你会得到全部内容：微调后的权重、系统提示词、任务提示词、请求参数，以及一个可用的客户端。这条路径今天已经完整且可运行。

• 图像编辑 PE——你会得到一个提示词和一个消息组装示例。无权重。卡片上明确写道：“图像编辑 PE 仍在开发中；本次发布仅提供其提示词。”你需要自行选择一个视觉语言模型来运行该提示词。

文生图路径会接收你的指令，对其进行扩展，并返回受 schema 约束为恰好两个键的 JSON。针对测试提示词——“一只橘色虎斑猫在阳光照亮的窗台上睡觉”——的输出是一句关于温暖照片和柔和午后光线的话，再加上比例“3:2”。该 schema 很严格，additionalProperties 设为 false，并且 ratio 字段是包含十个值的枚举：1:1、5:4、4:3、3:2、16:9、21:9、4:5、3:4、2:3、9:16。没有自由文本比例，输出中没有“auto”标记，模型也无法用这十个字符串之外的任何内容作答。这是有意为之的设计选择，并且它直接对应父模型公布的尺寸表，该表恰好列出这些比例及其像素尺寸，从 1:1 的 4096×4096 一直到 21:9 的 6272×2688。

比例决策不是凭感觉。发布的任务提示词用数百字阐述了一套严格的优先级顺序：明确指定的最终画布最先胜出，其次是所要求的交付物（海报是竖向的，幻灯片页眉是横向的，头像是正方形的），然后是主体的主要构图，最后是可选上下文——并明确警告：“一个普通的房间、公园、森林、天空或电影感背景，绝不能把聚焦的主体变成横向。”该提示词还禁止虚构平台：你不能擅自假定是 Instagram。它还区分了所描绘的场景与传播性人造制品——仪表板、海报、包装、技术图表或多面板合成图会被构建为信息架构，而不是包含所请求对象的场景。对于任何看过图像模型把“季度业绩幻灯片”变成会议室照片的人来说，这一区分正是此次发布中有趣的部分。

为什么要在一句说明文字上花费 27B 参数

答案就在父模型的文档里，而且比提示词扩展器本身更有意思。MiniMax-H3-Image 是一个 33.1B 的稠密单流扩散 Transformer，50 层，隐藏维度 5376，56 个注意力头，它从完整 Qwen3-VL 文本编码器第 50 层读取隐藏状态，而这个文本编码器是从 MiniMax-H3 原封不动继承下来的。该文本编码器有 66.7 GB，并不在图像仓库中——你需要从视频模型仓库单独下载它。其检查点被蒸馏为六步采样，不使用无分类器引导，而 API 强制执行这一点：任何不是 6 的 num_inference_steps，以及任何不是 1 的 guidance_scale，都会返回 HTTP 400，而 negative_prompt则会被直接拒绝。没有任何旋钮可调。

When there is no dial, the prompt is the control surface. That is the design logic connecting the two repositories: a six-step distilled sampler with no negative prompt has very little room to interpret a short instruction, so M​iniMax moved the interpretation into a separate model that can think before it writes. The hosted equivalent is an API endpoint called H3-Image-Context-IR, which does the same job server-side — accepts up to 32,000 characters of prompt and one to sixteen reference images, returns a revised prompt and a chosen ratio, and bills by converting the expansion model's input, output and thinking tokens into text tokens. MiniMax-H3-Image-PE is that endpoint's local escape hatch, and the parent card recommends exactly that usage: run the PE, save its expanded_caption into the generation call, and skip paying for enhancement twice.

The request parameters released with the PE are worth reading as a statement of intent rather than as tuning advice. Temperature 1.0, top_p 0.95, top_k 20, a 4096-token budget that includes thinking, and reasoning_effort set to "xhigh", with thinking enabled and preserved. M​iniMax is running its caption writer in maximum-deliberation mode and constraining only the final serialisation, not the reasoning. Serving that means SGLang 0.5.23 or newer with XGrammar 0.2.7 or newer, the q​wen3 reasoning parser, and constrained JSON decoding — or the Diffusers modular-blocks route the card documents. One caveat on that second route: the blocks repository the card points at, diffusers/minimax-h3-image-pe-blocks, returned HTTP 401 when checked on 2026-11-11, so it was not publicly readable at the time of writing. The card's Diffusers section may well be ahead of the artifact it depends on.

许可证才是真正能拦住人们的部分

MiniMax-H3-Image-PE 未单独授权。模型卡指出，它“是 MiniMax-H3-Image 的一部分，并因此受”《MiniMax-H3-Image 社区许可协议》约束，而许可证文件中有一行日期写着：“发布日期/许可证日期：2026年11月10日。”请仔细阅读这一点，因为这意味著提示词扩展器的许可证日期与父图像模型的发布日期相隔八天，而许可证本身是一份同时约束两者的文件。

有三项条款比其余条款更重要，而它们没有一项是通常的“开放权重”叙事：

• 地域 — 该授权仅适用于“适用地域”内，而“适用地域”定义为全球范围 不包括 欧盟、英国、大韩民国和美利坚合众国。这属于地域排除，而非使用限制，并且它写在定义中，而不是埋在附录里。

• 商业规模 — 若你的年化收入或你关联方的年化收入超过 100 万美元，则第 IV 条要求另行取得事先书面授权，或若你向第三方提供托管服务，则无论规模大小均同样适用。第二项条件不设收入门槛。

• 界面署名——同一节要求你在任何使用这些作品的商业产品或服务的用户界面上显著展示“MiniMax-H3-Image”。

还有一项再分发条件，要求附带一份包含特定版权行声明的 NOTICE 文件；以及第 V 节规定的一项义务：维护保障措施，防止产生违规输出，并配备报告机制和根据善意报告采取行动的职责。对于 2026 年的社区许可证而言，这些都不算不寻常。真正会让许多团队决定这 18 GB 的下载是否还值得开始的，是地域排除条款；而且它也是最容易被漏掉的条款，因为 Hugging Face 模型页面只把它作为“other”并附上一个链接来呈现。

什么是尚不可知的

明确边界比填充边界更有用。

• 没有基准测试数字。两张模型卡都没有公布任何一项得分。母公司只给出了定性说法——“开源模型中指令遵循能力最强”、“达到最先进水平”——截至 2026-11-11，未发现对 MiniMax-H3-Image 或其提示词扩展器的独立评估。没有 Elo，没有偏好胜率，也没有与托管版 Context-IR 端点进行的扩展质量对比。

• 没有证据表明编辑路径有效。该编辑提示词考虑周全且具体得不同寻常——它要求调用方提供每张参考图约简后的宽高比，明确告知模型绝不能根据预览图估算源图比例，并指示模型构建预期目标，而非假装已看到隐藏结果。但该路径并未随附任何权重，因此无人测量过通用 VLM 是否能像微调模型（想必）那样遵循它。

• No announcement, therefore no stated intent. Whether this is a permanent commitment or a byproduct of the image launch is not stated anywhere. The repository has no roadmap, no model index entry, and no discussion from M​iniMax explaining why the expander was split out rather than folded into the image checkpoint.

• 下载量数字太小，说明不了什么。MiniMax-H3-Image 在 2026-11-11 显示有 667 次下载和 136 个点赞，此时距其发布已过去八天。PE 模型显示有 0 次下载和 7 个点赞。对于一个仅发布一天的仓库来说，这只是一个下限，还不是定论——但这确实意味着还没有人发布过实地报告。

如果你真的在动手构建某个东西，这适合放在哪里

实际问题不是“这是一个好模型吗”——目前没人能回答——而是“采用它会让我承诺什么”。具体有三件事。你要承诺运行两个模型而不是一个：一个 18 GB 的扩展器，加上一个 68.65 GB 的图像检查点，再加上一个 66.7 GB 的文本编码器；如果你运行 MiniMax-H3，后者你很可能已经有了。你要承诺固定的 4096 个 token 解码预算（包括推理），而 API 文档将请求超时设为 600 秒，在这样的超时下，若不谨慎，这种延迟是无法藏在交互式 UI 背后的。你还要承诺接受一个地域范围排除四个主要市场的许可证。

The mitigation for the first two is the same one that applies to any model you have not measured yourself: put it behind a routing layer rather than into a hardcoded call path. This is the case routing is built for — the expander is a text-generation model behind an OpenAI-compatible /v1/chat/completions endpoint, so it can sit alongside everything else on one key, and a routing rule can send long or structured prompts to it while a shorter path handles the rest. If the expansion turns out to degrade a particular workload, failover moves that traffic without a redeploy. That is also the honest way to evaluate an unproven model: run it on a slice, keep the old path warm, and let the comparison decide. One clarification worth stating plainly, since it is easy to assume otherwise — MiniMax-H3-Image and MiniMax-H3-Image-PE are not on OrcaRouter's catalogue as of 2026-11-11, so this is a self-hosted evaluation, not a call we can make for you. What the catalogue does carry is M​iniMax's H3 video model and the M3.x text line at provider list price with zero markup passed through, which is the same arithmetic that applies the day an image endpoint arrives.

For the third — the territory clause — no amount of engineering helps. If you are in the EU, the UK, Korea or the US, the license does not grant you the rights it grants everyone else, and M​iniMax's own remedy is to contact them for a separate grant "based on robust controls and guardrails." That is a business conversation, and it should happen before the download, not after.

看什么

Two signals would turn this from a repository into a release. The first is an announcement: a blog post, a model-index entry, a mention on M​iniMax's news feed. Its absence is currently the most informative thing about the launch, and its arrival would clarify whether the PE is meant to be the default local path or a stopgap. The second is the Diffusers blocks repository becoming publicly reachable — right now it returns 401, and until it resolves, the "run it locally through Diffusers" route documented on the card is a claim rather than a path.

In between, the thing to actually read is the task prompt. It is a few hundred lines of plain English describing how to decide what an image is for, and it is the most concrete artefact M​iniMax has published about how it thinks image prompts should work. You can learn more from it in ten minutes than from any benchmark table, and unlike the weights, it costs nothing to read.