chore: release v1.102.0

Add --imageApiDialect flag, OPENAI_IMAGE_API_DIALECT env var, and
default_image_api_dialect config for gateways that expect aspect-ratio
size plus metadata.resolution instead of pixel size.

.claude-plugin/marketplace.json

@@ -6,7 +6,7 @@
   },
   "metadata": {
     "description": "Skills shared by Baoyu for improving daily work efficiency",
-    "version": "1.100.0"
+    "version": "1.102.0"
   },
   "plugins": [
     {

CHANGELOG.md

@@ -2,6 +2,16 @@
 
 English | [中文](./CHANGELOG.zh.md)
 
+## 1.102.0 - 2026-04-12
+
+### Features
+- `baoyu-imagine`: add OpenAI-compatible image API dialect — new `--imageApiDialect` flag, `OPENAI_IMAGE_API_DIALECT` env var, and `default_image_api_dialect` config for gateways that expect aspect-ratio `size` plus `metadata.resolution` instead of pixel `size`
+
+## 1.101.0 - 2026-04-12
+
+### Features
+- `baoyu-imagine`: improve Replicate provider compatibility — route models through family-specific input builders and validators (nano-banana, Seedream 4.5, Seedream 5 Lite, Wan 2.7 Image); update default model to `google/nano-banana-2`; fix Seedream 4.5 custom size encoding to use width/height schema; fix aspect-ratio default inheritance for unsupported Replicate models; block multi-output requests before they reach the API (by @justnode)
+
 ## 1.100.0 - 2026-04-12
 
 ### Features

CHANGELOG.zh.md

@@ -2,6 +2,16 @@
 
 [English](./CHANGELOG.md) | 中文
 
+## 1.102.0 - 2026-04-12
+
+### 新功能
+- `baoyu-imagine`：新增 OpenAI 兼容图像 API 方言支持 —— 新增 `--imageApiDialect` 参数、`OPENAI_IMAGE_API_DIALECT` 环境变量及 `default_image_api_dialect` 配置项，用于对接期望宽高比格式 `size` 加 `metadata.resolution` 的兼容网关
+
+## 1.101.0 - 2026-04-12
+
+### 新功能
+- `baoyu-imagine`：改进 Replicate 服务商兼容性 —— 针对不同模型系列（nano-banana、Seedream 4.5、Seedream 5 Lite、Wan 2.7 Image）实现专属输入构建器和验证器；将默认模型更新为 `google/nano-banana-2`；修复 Seedream 4.5 自定义尺寸编码（改用 width/height schema）；修复不支持的 Replicate 模型的宽高比默认值继承问题；在请求到达 API 前拦截多图请求 (by @justnode)
+
 ## 1.100.0 - 2026-04-12
 
 ### 新功能

README.md

@@ -754,9 +754,15 @@ AI SDK-based image generation using OpenAI, Azure OpenAI, Google, OpenRouter, Da
 # MiniMax with subject reference
 /baoyu-imagine --prompt "A girl stands by the library window, cinematic lighting" --image out.jpg --provider minimax --model image-01 --ref portrait.png --ar 16:9
 
-# Replicate
+# Replicate (default: google/nano-banana-2)
 /baoyu-imagine --prompt "A cat" --image cat.png --provider replicate
 
+# Replicate Seedream 4.5
+/baoyu-imagine --prompt "A studio portrait" --image portrait.png --provider replicate --model bytedance/seedream-4.5 --ar 3:2
+
+# Replicate Wan 2.7 Image Pro
+/baoyu-imagine --prompt "A concept frame" --image frame.png --provider replicate --model wan-video/wan-2.7-image-pro --size 2048x1152
+
 # Jimeng (即梦)
 /baoyu-imagine --prompt "一只可爱的猫" --image cat.png --provider jimeng
 
@@ -784,8 +790,9 @@ AI SDK-based image generation using OpenAI, Azure OpenAI, Google, OpenRouter, Da
 | `--size` | Size (e.g., `1024x1024`) |
 | `--quality` | `normal` or `2k` (default: `2k`) |
 | `--imageSize` | `1K`, `2K`, or `4K` for Google/OpenRouter |
-| `--ref` | Reference images (Google, OpenAI, Azure OpenAI, OpenRouter, Replicate, MiniMax, or Seedream 5.0/4.5/4.0) |
-| `--n` | Number of images per request |
+| `--imageApiDialect` | `openai-native` or `ratio-metadata` for OpenAI-compatible gateways |
+| `--ref` | Reference images (Google, OpenAI, Azure OpenAI, OpenRouter, Replicate supported families, MiniMax, or Seedream 5.0/4.5/4.0) |
+| `--n` | Number of images per request (`replicate` currently requires `--n 1`) |
 | `--json` | JSON output |
 
 **Environment Variables** (see [Environment Configuration](#environment-configuration) for setup):
@@ -813,10 +820,11 @@ AI SDK-based image generation using OpenAI, Azure OpenAI, Google, OpenRouter, Da
 | `ZAI_IMAGE_MODEL` | Z.AI model | `glm-image` |
 | `BIGMODEL_IMAGE_MODEL` | Backward-compatible alias for Z.AI model | `glm-image` |
 | `MINIMAX_IMAGE_MODEL` | MiniMax model | `image-01` |
-| `REPLICATE_IMAGE_MODEL` | Replicate model | `google/nano-banana-pro` |
+| `REPLICATE_IMAGE_MODEL` | Replicate model | `google/nano-banana-2` |
 | `JIMENG_IMAGE_MODEL` | Jimeng model | `jimeng_t2i_v40` |
 | `SEEDREAM_IMAGE_MODEL` | Seedream model | `doubao-seedream-5-0-260128` |
 | `OPENAI_BASE_URL` | Custom OpenAI endpoint | - |
+| `OPENAI_IMAGE_API_DIALECT` | OpenAI-compatible image API dialect (`openai-native` or `ratio-metadata`) | `openai-native` |
 | `OPENAI_IMAGE_USE_CHAT` | Use `/chat/completions` for OpenAI image generation | `false` |
 | `AZURE_OPENAI_BASE_URL` | Azure resource or deployment endpoint | - |
 | `AZURE_API_VERSION` | Azure image API version | `2025-04-01-preview` |
@@ -844,6 +852,9 @@ AI SDK-based image generation using OpenAI, Azure OpenAI, Google, OpenRouter, Da
 - MiniMax reference images are sent as `subject_reference`; the current API is specialized toward character / portrait consistency.
 - Jimeng does not support reference images.
 - Seedream reference images are supported by Seedream 5.0 / 4.5 / 4.0, not Seedream 3.0.
+- Replicate defaults to `google/nano-banana-2`. `baoyu-imagine` only enables Replicate advanced options for `google/nano-banana*`, `bytedance/seedream-4.5`, `bytedance/seedream-5-lite`, `wan-video/wan-2.7-image`, and `wan-video/wan-2.7-image-pro`.
+- Replicate currently saves exactly one output image per request. `--n > 1` is blocked locally instead of silently dropping extra results.
+- Replicate model behavior is family-specific: nano-banana uses `--quality` / `--ar`, Seedream uses validated `--size` / `--ar`, and Wan uses validated `--size` (with `--ar` converted locally to a concrete size).
 
 **Provider Auto-Selection**:
 1. If `--provider` is specified → use it
@@ -1161,7 +1172,7 @@ MINIMAX_IMAGE_MODEL=image-01
 
 # Replicate
 REPLICATE_API_TOKEN=r8_xxx
-REPLICATE_IMAGE_MODEL=google/nano-banana-pro
+REPLICATE_IMAGE_MODEL=google/nano-banana-2
 # REPLICATE_BASE_URL=https://api.replicate.com
 
 # Jimeng (即梦)

README.zh.md

@@ -754,9 +754,15 @@ AI 驱动的生成后端。
 # MiniMax + 角色参考图
 /baoyu-imagine --prompt "A girl stands by the library window, cinematic lighting" --image out.jpg --provider minimax --model image-01 --ref portrait.png --ar 16:9
 
-# Replicate
+# Replicate（默认：google/nano-banana-2）
 /baoyu-imagine --prompt "一只猫" --image cat.png --provider replicate
 
+# Replicate Seedream 4.5
+/baoyu-imagine --prompt "一张影棚人像" --image portrait.png --provider replicate --model bytedance/seedream-4.5 --ar 3:2
+
+# Replicate Wan 2.7 Image Pro
+/baoyu-imagine --prompt "一张概念分镜" --image frame.png --provider replicate --model wan-video/wan-2.7-image-pro --size 2048x1152
+
 # 即梦（Jimeng）
 /baoyu-imagine --prompt "一只可爱的猫" --image cat.png --provider jimeng
 
@@ -784,8 +790,9 @@ AI 驱动的生成后端。
 | `--size` | 尺寸（如 `1024x1024`） |
 | `--quality` | `normal` 或 `2k`（默认：`2k`） |
 | `--imageSize` | Google/OpenRouter 使用的 `1K`、`2K`、`4K` |
-| `--ref` | 参考图片（Google、OpenAI、Azure OpenAI、OpenRouter、Replicate、MiniMax 或 Seedream 5.0/4.5/4.0） |
-| `--n` | 单次请求生成图片数量 |
+| `--imageApiDialect` | OpenAI 兼容网关的图像 API 方言（`openai-native` 或 `ratio-metadata`） |
+| `--ref` | 参考图片（Google、OpenAI、Azure OpenAI、OpenRouter、Replicate 支持的模型家族、MiniMax 或 Seedream 5.0/4.5/4.0） |
+| `--n` | 单次请求生成图片数量（`replicate` 当前只支持 `--n 1`） |
 | `--json` | 输出 JSON 结果 |
 
 **环境变量**（配置方法见[环境配置](#环境配置)）：
@@ -813,10 +820,11 @@ AI 驱动的生成后端。
 | `ZAI_IMAGE_MODEL` | Z.AI 模型 | `glm-image` |
 | `BIGMODEL_IMAGE_MODEL` | Z.AI 模型向后兼容别名 | `glm-image` |
 | `MINIMAX_IMAGE_MODEL` | MiniMax 模型 | `image-01` |
-| `REPLICATE_IMAGE_MODEL` | Replicate 模型 | `google/nano-banana-pro` |
+| `REPLICATE_IMAGE_MODEL` | Replicate 模型 | `google/nano-banana-2` |
 | `JIMENG_IMAGE_MODEL` | 即梦模型 | `jimeng_t2i_v40` |
 | `SEEDREAM_IMAGE_MODEL` | 豆包模型 | `doubao-seedream-5-0-260128` |
 | `OPENAI_BASE_URL` | 自定义 OpenAI 端点 | - |
+| `OPENAI_IMAGE_API_DIALECT` | OpenAI 兼容图像 API 方言（`openai-native` 或 `ratio-metadata`） | `openai-native` |
 | `OPENAI_IMAGE_USE_CHAT` | OpenAI 改走 `/chat/completions` | `false` |
 | `AZURE_OPENAI_BASE_URL` | Azure 资源或部署端点 | - |
 | `AZURE_API_VERSION` | Azure 图像 API 版本 | `2025-04-01-preview` |
@@ -844,6 +852,9 @@ AI 驱动的生成后端。
 - MiniMax 参考图会走 `subject_reference`，当前能力更偏角色 / 人像一致性。
 - 即梦不支持参考图。
 - 豆包参考图能力仅适用于 Seedream 5.0 / 4.5 / 4.0，不适用于 Seedream 3.0。
+- Replicate 默认模型改为 `google/nano-banana-2`。`baoyu-imagine` 目前只对 `google/nano-banana*`、`bytedance/seedream-4.5`、`bytedance/seedream-5-lite`、`wan-video/wan-2.7-image` 和 `wan-video/wan-2.7-image-pro` 开启本地能力识别与校验。
+- Replicate 当前只保存单张输出图，`--n > 1` 会在本地直接报错，避免多图结果被静默丢弃。
+- Replicate 的参数能力按模型家族区分：nano-banana 走 `--quality` / `--ar`，Seedream 走校验后的 `--size` / `--ar`，Wan 走校验后的 `--size`（`--ar` 会先在本地换算成具体尺寸）。
 
 **服务商自动选择**：
 1. 如果指定了 `--provider` → 使用指定的
@@ -1161,7 +1172,7 @@ MINIMAX_IMAGE_MODEL=image-01
 
 # Replicate
 REPLICATE_API_TOKEN=r8_xxx
-REPLICATE_IMAGE_MODEL=google/nano-banana-pro
+REPLICATE_IMAGE_MODEL=google/nano-banana-2
 # REPLICATE_BASE_URL=https://api.replicate.com
 
 # 即梦（Jimeng）

skills/baoyu-imagine/SKILL.md

@@ -57,7 +57,7 @@ if (Test-Path "$HOME/.baoyu-skills/baoyu-imagine/EXTEND.md") { "user" }
 
 Legacy compatibility: if `.baoyu-skills/baoyu-image-gen/EXTEND.md` exists and the new path does not, runtime renames it to `baoyu-imagine`. If both files exist, runtime leaves them unchanged and uses the new path.
 
-**EXTEND.md Supports**: Default provider | Default quality | Default aspect ratio | Default image size | Default models | Batch worker cap | Provider-specific batch limits
+**EXTEND.md Supports**: Default provider | Default quality | Default aspect ratio | Default image size | OpenAI image API dialect | Default models | Batch worker cap | Provider-specific batch limits
 
 Schema: `references/config/preferences-schema.md`
 
@@ -76,7 +76,7 @@ ${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --quality 2k
 # From prompt files
 ${BUN_X} {baseDir}/scripts/main.ts --promptfiles system.md content.md --image out.png
 
-# With reference images (Google, OpenAI, Azure OpenAI, OpenRouter, Replicate, MiniMax, or Seedream 4.0/4.5/5.0)
+# With reference images (Google, OpenAI, Azure OpenAI, OpenRouter, Replicate supported families, MiniMax, or Seedream 4.0/4.5/5.0)
 ${BUN_X} {baseDir}/scripts/main.ts --prompt "Make blue" --image out.png --ref source.png
 
 # With reference images (explicit provider/model)
@@ -118,11 +118,14 @@ ${BUN_X} {baseDir}/scripts/main.ts --prompt "A girl stands by the library window
 # MiniMax with custom size (documented for image-01)
 ${BUN_X} {baseDir}/scripts/main.ts --prompt "A cinematic poster" --image out.jpg --provider minimax --model image-01 --size 1536x1024
 
-# Replicate (google/nano-banana-pro)
+# Replicate (default: google/nano-banana-2)
 ${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider replicate
 
-# Replicate with specific model
-${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider replicate --model google/nano-banana
+# Replicate Seedream 4.5
+${BUN_X} {baseDir}/scripts/main.ts --prompt "A cinematic portrait" --image out.png --provider replicate --model bytedance/seedream-4.5 --ar 3:2
+
+# Replicate Wan 2.7 Image Pro
+${BUN_X} {baseDir}/scripts/main.ts --prompt "A concept frame" --image out.png --provider replicate --model wan-video/wan-2.7-image-pro --size 2048x1152
 
 # Batch mode with saved prompt files
 ${BUN_X} {baseDir}/scripts/main.ts --batchfile batch.json
@@ -142,7 +145,7 @@ ${BUN_X} {baseDir}/scripts/main.ts --batchfile batch.json --jobs 4 --json
       "promptFiles": ["prompts/hero.md"],
       "image": "out/hero.png",
       "provider": "replicate",
-      "model": "google/nano-banana-pro",
+      "model": "google/nano-banana-2",
       "ar": "16:9",
       "quality": "2k"
     },
@@ -173,8 +176,9 @@ Paths in `promptFiles`, `image`, and `ref` are resolved relative to the batch fi
 | `--size <WxH>` | Size (e.g., `1024x1024`) |
 | `--quality normal\|2k` | Quality preset (default: `2k`) |
 | `--imageSize 1K\|2K\|4K` | Image size for Google/OpenRouter (default: from quality) |
-| `--ref <files...>` | Reference images. Supported by Google multimodal, OpenAI GPT Image edits, Azure OpenAI edits (PNG/JPG only), OpenRouter multimodal models, Replicate, MiniMax subject-reference, and Seedream 5.0/4.5/4.0. Not supported by Jimeng, Seedream 3.0, or removed SeedEdit 3.0 |
-| `--n <count>` | Number of images |
+| `--imageApiDialect openai-native\|ratio-metadata` | OpenAI-compatible image API dialect. Use `ratio-metadata` when the endpoint is OpenAI-compatible but expects aspect-ratio `size` plus `metadata.resolution` instead of pixel `size` |
+| `--ref <files...>` | Reference images. Supported by Google multimodal, OpenAI GPT Image edits, Azure OpenAI edits (PNG/JPG only), OpenRouter multimodal models, Replicate supported families, MiniMax subject-reference, and Seedream 5.0/4.5/4.0. Not supported by Jimeng, Seedream 3.0, or removed SeedEdit 3.0 |
+| `--n <count>` | Number of images. Replicate currently supports only `--n 1` because this path saves exactly one output image |
 | `--json` | JSON output |
 
 ## Environment Variables
@@ -202,10 +206,11 @@ Paths in `promptFiles`, `image`, and `ref` are resolved relative to the batch fi
 | `ZAI_IMAGE_MODEL` | Z.AI model override (default: `glm-image`) |
 | `BIGMODEL_IMAGE_MODEL` | Backward-compatible alias for Z.AI model override |
 | `MINIMAX_IMAGE_MODEL` | MiniMax model override (default: `image-01`) |
-| `REPLICATE_IMAGE_MODEL` | Replicate model override (default: google/nano-banana-pro) |
+| `REPLICATE_IMAGE_MODEL` | Replicate model override (default: google/nano-banana-2) |
 | `JIMENG_IMAGE_MODEL` | Jimeng model override (default: jimeng_t2i_v40) |
 | `SEEDREAM_IMAGE_MODEL` | Seedream model override (default: doubao-seedream-5-0-260128) |
 | `OPENAI_BASE_URL` | Custom OpenAI endpoint |
+| `OPENAI_IMAGE_API_DIALECT` | OpenAI-compatible image API dialect override (`openai-native` or `ratio-metadata`) |
 | `AZURE_OPENAI_BASE_URL` | Azure resource endpoint or deployment endpoint |
 | `AZURE_API_VERSION` | Azure image API version (default: `2025-04-01-preview`) |
 | `OPENROUTER_BASE_URL` | Custom OpenRouter endpoint (default: `https://openrouter.ai/api/v1`) |
@@ -239,6 +244,22 @@ For Azure, `--model` / `default_model.azure` should be the Azure deployment name
 
 **EXTEND.md overrides env vars**. If both EXTEND.md `default_model.google: "gemini-3-pro-image-preview"` and env var `GOOGLE_IMAGE_MODEL=gemini-3.1-flash-image-preview` exist, EXTEND.md wins.
 
+### OpenAI-Compatible Gateway Dialects
+
+`provider=openai` means the auth and routing entrypoint is OpenAI-compatible. It does **not** guarantee that the upstream image API uses OpenAI native image-request semantics.
+
+Use `default_image_api_dialect` in `EXTEND.md`, `OPENAI_IMAGE_API_DIALECT`, or `--imageApiDialect` when the endpoint expects a different wire format:
+
+- `openai-native`: Sends pixel `size` such as `1536x1024` and native OpenAI quality fields when supported
+- `ratio-metadata`: Sends aspect-ratio `size` such as `16:9` and maps quality/size intent into `metadata.resolution` (`1K|2K|4K`) plus `metadata.orientation`
+
+Recommended use:
+
+- OpenAI native Images API or strict clones: keep `openai-native`
+- OpenAI-compatible gateways in front of Gemini or similar models: try `ratio-metadata`
+
+Current limitation: `ratio-metadata` only applies to text-to-image generation. Reference-image edit flows still require `openai-native` or another provider with first-class edit support.
+
 **Agent MUST display model info** before each generation:
 - Show: `Using [provider] / [model]`
 - Show switch hint: `Switch model: --model <id> | EXTEND.md default_model.[provider] | env <PROVIDER>_IMAGE_MODEL`
@@ -360,10 +381,33 @@ Notes:
 
 ### Replicate Models
 
-Supported model formats:
+Replicate support in `baoyu-imagine` is intentionally scoped to the model families that the tool can validate locally and save without dropping outputs:
 
-- `owner/name` (recommended for official models), e.g. `google/nano-banana-pro`
-- `owner/name:version` (community models by version), e.g. `stability-ai/sdxl:<version>`
+- `google/nano-banana*` (default: `google/nano-banana-2`)
+  - Supports prompt-only and reference-image generation
+  - Uses Replicate `aspect_ratio`, `resolution`, and `output_format`
+  - `--size <WxH>` is accepted only as a shorthand for a documented aspect ratio plus `1K` / `2K`
+- `bytedance/seedream-4.5`
+  - Supports prompt-only and reference-image generation
+  - Uses Replicate `size`, `aspect_ratio`, and `image_input`
+  - Local validation blocks unsupported `1K` requests before the API call
+- `bytedance/seedream-5-lite`
+  - Supports prompt-only and reference-image generation
+  - Uses Replicate `size`, `aspect_ratio`, and `image_input`
+  - Local validation currently accepts `2K` / `3K` only
+- `wan-video/wan-2.7-image`
+  - Supports prompt-only and reference-image generation
+  - Uses Replicate `size` and `images`
+  - Max output size is 2K
+- `wan-video/wan-2.7-image-pro`
+  - Supports prompt-only and reference-image generation
+  - Uses Replicate `size` and `images`
+  - 4K is allowed only for text-to-image; local validation blocks `4K + --ref`
+
+Guardrails:
+
+- Replicate currently supports only single-output save semantics in this tool. Keep `--n 1`.
+- If a Replicate model is outside the compatibility list above, `baoyu-imagine` only treats it as prompt-only and rejects advanced local options instead of guessing a nano-banana-style schema.
 
 Examples:
 
@@ -398,7 +442,7 @@ Supported: `1:1`, `16:9`, `9:16`, `4:3`, `3:4`, `2.35:1`
 - Google multimodal: uses `imageConfig.aspectRatio`
 - OpenAI: maps to closest supported size
 - OpenRouter: sends `imageGenerationOptions.aspect_ratio`; if only `--size <WxH>` is given, aspect ratio is inferred automatically
-- Replicate: passes `aspect_ratio` to model; when `--ref` is provided without `--ar`, defaults to `match_input_image`
+- Replicate: behavior is model-family-specific. `google/nano-banana*` uses `aspect_ratio`; `bytedance/seedream-*` uses documented Replicate aspect ratios; Wan 2.7 maps `--ar` to a concrete `size`
 - MiniMax: sends official `aspect_ratio` values directly; if `--size <WxH>` is given without `--ar`, `width` / `height` are sent for `image-01`
 
 ## Generation Mode

skills/baoyu-imagine/references/config/first-time-setup.md

@@ -58,7 +58,7 @@ options:
   - label: "MiniMax"
     description: "MiniMax image generation with subject-reference character workflows"
   - label: "Replicate"
-    description: "Community models - nano-banana-pro, flexible model selection"
+    description: "Curated Replicate image families - nano-banana-2, Seedream, and Wan image models"
 ```
 
 ### Question 2: Default Google Model
@@ -175,6 +175,7 @@ default_provider: [selected provider or null]
 default_quality: [selected quality]
 default_aspect_ratio: null
 default_image_size: null
+default_image_api_dialect: null
 default_model:
   google: [selected google model or null]
   openai: null
@@ -187,6 +188,8 @@ default_model:
 ---
 ```
 
+If the user selects `OpenAI` but says their endpoint is only OpenAI-compatible and fronts another image model family, save `default_image_api_dialect: ratio-metadata` when they explicitly confirm the gateway expects aspect-ratio `size` plus metadata-based resolution. Otherwise leave it `null` / `openai-native`.
+
 ## Flow 2: EXTEND.md Exists, Model Null
 
 When EXTEND.md exists but `default_model.[current_provider]` is null, ask ONLY the model question for the current provider.
@@ -298,10 +301,14 @@ Notes for Z.AI setup:
 header: "Replicate Model"
 question: "Choose a default Replicate image generation model?"
 options:
-  - label: "google/nano-banana-pro (Recommended)"
-    description: "Google's fast image model on Replicate"
-  - label: "google/nano-banana"
-    description: "Google's base image model on Replicate"
+  - label: "google/nano-banana-2 (Recommended)"
+    description: "Current default for general Replicate image generation in baoyu-imagine"
+  - label: "bytedance/seedream-4.5"
+    description: "Replicate Seedream 4.5 with validated local size/ref guardrails"
+  - label: "bytedance/seedream-5-lite"
+    description: "Replicate Seedream 5 Lite with validated local size/ref guardrails"
+  - label: "wan-video/wan-2.7-image-pro"
+    description: "Replicate Wan 2.7 Image Pro with 4K text-to-image support"
 ```
 
 ### MiniMax Model Selection

skills/baoyu-imagine/references/config/preferences-schema.md

@@ -19,6 +19,8 @@ default_aspect_ratio: null  # "16:9"|"1:1"|"4:3"|"3:4"|"2.35:1"|null
 
 default_image_size: null    # 1K|2K|4K|null (Google/OpenRouter, overrides quality)
 
+default_image_api_dialect: null  # openai-native|ratio-metadata|null (OpenAI-compatible gateways; null = use env/default)
+
 default_model:
   google: null              # e.g., "gemini-3-pro-image-preview", "gemini-3.1-flash-image-preview"
   openai: null              # e.g., "gpt-image-1.5", "gpt-image-1"
@@ -27,7 +29,7 @@ default_model:
   dashscope: null           # e.g., "qwen-image-2.0-pro"
   zai: null                 # e.g., "glm-image"
   minimax: null             # e.g., "image-01"
-  replicate: null           # e.g., "google/nano-banana-pro"
+  replicate: null           # e.g., "google/nano-banana-2"
 
 batch:
   max_workers: 10
@@ -68,6 +70,7 @@ batch:
 | `default_quality` | string\|null | null | Default quality (null = 2k) |
 | `default_aspect_ratio` | string\|null | null | Default aspect ratio |
 | `default_image_size` | string\|null | null | Google/OpenRouter image size (overrides quality) |
+| `default_image_api_dialect` | string\|null | null | OpenAI-compatible image dialect (`openai-native` or `ratio-metadata`) |
 | `default_model.google` | string\|null | null | Google default model |
 | `default_model.openai` | string\|null | null | OpenAI default model |
 | `default_model.azure` | string\|null | null | Azure default deployment name |
@@ -88,6 +91,7 @@ batch:
 version: 1
 default_provider: google
 default_quality: 2k
+default_image_api_dialect: null
 ---
 ```
 
@@ -99,6 +103,7 @@ default_provider: google
 default_quality: 2k
 default_aspect_ratio: "16:9"
 default_image_size: 2K
+default_image_api_dialect: null
 default_model:
   google: "gemini-3-pro-image-preview"
   openai: "gpt-image-1.5"
@@ -107,7 +112,7 @@ default_model:
   dashscope: "qwen-image-2.0-pro"
   zai: "glm-image"
   minimax: "image-01"
-  replicate: "google/nano-banana-pro"
+  replicate: "google/nano-banana-2"
 batch:
   max_workers: 10
   provider_limits:

skills/baoyu-imagine/scripts/main.test.ts

@@ -17,6 +17,7 @@ import {
   mergeConfig,
   normalizeOutputImagePath,
   parseArgs,
+  parseOpenAIImageApiDialect,
   parseSimpleYaml,
 } from "./main.ts";
 
@@ -28,9 +29,12 @@ function makeArgs(overrides: Partial<CliArgs> = {}): CliArgs {
     provider: null,
     model: null,
     aspectRatio: null,
+    aspectRatioSource: null,
     size: null,
     quality: null,
     imageSize: null,
+    imageSizeSource: null,
+    imageApiDialect: null,
     referenceImages: [],
     n: 1,
     batchFile: null,
@@ -83,6 +87,8 @@ test("parseArgs parses the main baoyu-imagine CLI flags", () => {
     "2k",
     "--imageSize",
     "4k",
+    "--imageApiDialect",
+    "ratio-metadata",
     "--ref",
     "ref/one.png",
     "ref/two.jpg",
@@ -97,7 +103,10 @@ test("parseArgs parses the main baoyu-imagine CLI flags", () => {
   assert.equal(args.imagePath, "out/hero");
   assert.equal(args.provider, "zai");
   assert.equal(args.quality, "2k");
+  assert.equal(args.aspectRatioSource, null);
   assert.equal(args.imageSize, "4K");
+  assert.equal(args.imageSizeSource, "cli");
+  assert.equal(args.imageApiDialect, "ratio-metadata");
   assert.deepEqual(args.referenceImages, ["ref/one.png", "ref/two.jpg"]);
   assert.equal(args.n, 3);
   assert.equal(args.jobs, 5);
@@ -121,6 +130,7 @@ default_provider: openrouter
 default_quality: normal
 default_aspect_ratio: '16:9'
 default_image_size: 2K
+default_image_api_dialect: ratio-metadata
 default_model:
   google: gemini-3-pro-image-preview
   openai: gpt-image-1.5
@@ -153,6 +163,7 @@ batch:
   assert.equal(config.default_quality, "normal");
   assert.equal(config.default_aspect_ratio, "16:9");
   assert.equal(config.default_image_size, "2K");
+  assert.equal(config.default_image_api_dialect, "ratio-metadata");
   assert.equal(config.default_model?.google, "gemini-3-pro-image-preview");
   assert.equal(config.default_model?.openai, "gpt-image-1.5");
   assert.equal(config.default_model?.zai, "glm-image");
@@ -248,13 +259,48 @@ test("mergeConfig only fills values missing from CLI args", () => {
       default_quality: "2k",
       default_aspect_ratio: "3:2",
       default_image_size: "2K",
+      default_image_api_dialect: "ratio-metadata",
     } satisfies Partial<ExtendConfig>,
   );
 
   assert.equal(merged.provider, "openai");
   assert.equal(merged.quality, "2k");
   assert.equal(merged.aspectRatio, "3:2");
+  assert.equal(merged.aspectRatioSource, "config");
   assert.equal(merged.imageSize, "4K");
+  assert.equal(merged.imageSizeSource, "cli");
+  assert.equal(merged.imageApiDialect, "ratio-metadata");
+});
+
+test("mergeConfig tags inherited imageSize defaults so providers can ignore incompatible config", () => {
+  const merged = mergeConfig(
+    makeArgs(),
+    {
+      default_image_size: "2K",
+    } satisfies Partial<ExtendConfig>,
+  );
+
+  assert.equal(merged.imageSize, "2K");
+  assert.equal(merged.imageSizeSource, "config");
+});
+
+test("mergeConfig falls back to OPENAI_IMAGE_API_DIALECT when CLI and EXTEND are unset", (t) => {
+  useEnv(t, {
+    OPENAI_IMAGE_API_DIALECT: "ratio-metadata",
+  });
+
+  const merged = mergeConfig(makeArgs(), {});
+  assert.equal(merged.imageApiDialect, "ratio-metadata");
+});
+
+test("parseOpenAIImageApiDialect validates supported values", () => {
+  assert.equal(parseOpenAIImageApiDialect("openai-native"), "openai-native");
+  assert.equal(parseOpenAIImageApiDialect("ratio-metadata"), "ratio-metadata");
+  assert.equal(parseOpenAIImageApiDialect(null), null);
+  assert.throws(
+    () => parseOpenAIImageApiDialect("gateway-magic"),
+    /Invalid OpenAI image API dialect/,
+  );
 });
 
 test("detectProvider rejects non-ref-capable providers and prefers Google first when multiple keys exist", (t) => {
@@ -474,6 +520,7 @@ test("loadBatchTasks and createTaskArgs resolve batch-relative paths", async (t)
     makeArgs({
       provider: "replicate",
       quality: "2k",
+      imageApiDialect: "ratio-metadata",
       json: true,
     }),
     loaded.tasks[0]!,
@@ -490,6 +537,7 @@ test("loadBatchTasks and createTaskArgs resolve batch-relative paths", async (t)
   assert.equal(taskArgs.provider, "replicate");
   assert.equal(taskArgs.aspectRatio, "16:9");
   assert.equal(taskArgs.quality, "2k");
+  assert.equal(taskArgs.imageApiDialect, "ratio-metadata");
   assert.equal(taskArgs.json, true);
 });
 
@@ -503,5 +551,11 @@ test("path normalization, worker count, and retry classification follow expected
   assert.equal(getWorkerCount(5, 0, 4), 1);
 
   assert.equal(isRetryableGenerationError(new Error("API error (401): denied")), false);
+  assert.equal(
+    isRetryableGenerationError(
+      new Error("Replicate returned 2 outputs, but baoyu-imagine currently supports saving exactly one image per request."),
+    ),
+    false,
+  );
   assert.equal(isRetryableGenerationError(new Error("socket hang up")), true);
 });

skills/baoyu-imagine/scripts/main.ts

@@ -8,6 +8,7 @@ import type {
   BatchTaskInput,
   CliArgs,
   ExtendConfig,
+  OpenAIImageApiDialect,
   Provider,
 } from "./types";
 
@@ -83,8 +84,9 @@ Options:
   --size <WxH>              Size (e.g., 1024x1024)
   --quality normal|2k       Quality preset (default: 2k)
   --imageSize 1K|2K|4K      Image size for Google/OpenRouter (default: from quality)
-  --ref <files...>          Reference images (Google, OpenAI, Azure, OpenRouter, Replicate, MiniMax, or Seedream 4.0/4.5/5.0)
-  --n <count>               Number of images for the current task (default: 1)
+  --imageApiDialect <id>    OpenAI-compatible image dialect: openai-native|ratio-metadata
+  --ref <files...>          Reference images (Google, OpenAI, Azure, OpenRouter, Replicate supported families, MiniMax, or Seedream 4.0/4.5/5.0)
+  --n <count>               Number of images for the current task (default: 1; Replicate currently requires 1)
   --json                    JSON output
   -h, --help                Show help
 
@@ -97,7 +99,7 @@ Batch file format:
         "promptFiles": ["prompts/hero.md"],
         "image": "out/hero.png",
         "provider": "replicate",
-        "model": "google/nano-banana-pro",
+        "model": "google/nano-banana-2",
         "ar": "16:9"
       }
     ]
@@ -107,6 +109,7 @@ Behavior:
   - Batch mode automatically runs in parallel when pending tasks >= 2
   - Each image retries automatically up to 3 attempts
   - Batch summary reports success count, failure count, and per-image errors
+  - Replicate currently supports single-image save semantics only; --n must stay at 1
 
 Environment variables:
   OPENAI_API_KEY            OpenAI API key
@@ -128,10 +131,11 @@ Environment variables:
   ZAI_IMAGE_MODEL           Default Z.AI model (glm-image)
   BIGMODEL_IMAGE_MODEL      Backward-compatible alias for Z.AI model (glm-image)
   MINIMAX_IMAGE_MODEL       Default MiniMax model (image-01)
-  REPLICATE_IMAGE_MODEL     Default Replicate model (google/nano-banana-pro)
+  REPLICATE_IMAGE_MODEL     Default Replicate model (google/nano-banana-2)
   JIMENG_IMAGE_MODEL        Default Jimeng model (jimeng_t2i_v40)
   SEEDREAM_IMAGE_MODEL      Default Seedream model (doubao-seedream-5-0-260128)
   OPENAI_BASE_URL           Custom OpenAI endpoint
+  OPENAI_IMAGE_API_DIALECT  OpenAI-compatible image dialect (openai-native|ratio-metadata)
   OPENAI_IMAGE_USE_CHAT     Use /chat/completions instead of /images/generations (true|false)
   OPENROUTER_BASE_URL       Custom OpenRouter endpoint
   OPENROUTER_HTTP_REFERER   Optional app URL for OpenRouter attribution
@@ -164,9 +168,12 @@ export function parseArgs(argv: string[]): CliArgs {
     provider: null,
     model: null,
     aspectRatio: null,
+    aspectRatioSource: null,
     size: null,
     quality: null,
     imageSize: null,
+    imageSizeSource: null,
+    imageApiDialect: null,
     referenceImages: [],
     n: 1,
     batchFile: null,
@@ -270,6 +277,7 @@ export function parseArgs(argv: string[]): CliArgs {
       const v = argv[++i];
       if (!v) throw new Error("Missing value for --ar");
       out.aspectRatio = v;
+      out.aspectRatioSource = "cli";
       continue;
     }
 
@@ -291,6 +299,16 @@ export function parseArgs(argv: string[]): CliArgs {
       const v = argv[++i]?.toUpperCase();
       if (v !== "1K" && v !== "2K" && v !== "4K") throw new Error(`Invalid imageSize: ${v}`);
       out.imageSize = v;
+      out.imageSizeSource = "cli";
+      continue;
+    }
+
+    if (a === "--imageApiDialect") {
+      const v = argv[++i];
+      if (v !== "openai-native" && v !== "ratio-metadata") {
+        throw new Error(`Invalid imageApiDialect: ${v}`);
+      }
+      out.imageApiDialect = v;
       continue;
     }
 
@@ -397,6 +415,9 @@ export function parseSimpleYaml(yaml: string): Partial<ExtendConfig> {
         config.default_aspect_ratio = cleaned === "null" ? null : cleaned;
       } else if (key === "default_image_size") {
         config.default_image_size = value === "null" ? null : value as "1K" | "2K" | "4K";
+      } else if (key === "default_image_api_dialect") {
+        config.default_image_api_dialect =
+          value === "null" ? null : parseOpenAIImageApiDialect(value);
       } else if (key === "default_model") {
         config.default_model = {
           google: null,
@@ -482,6 +503,15 @@ export function parseSimpleYaml(yaml: string): Partial<ExtendConfig> {
   return config;
 }
 
+export function parseOpenAIImageApiDialect(
+  value: string | undefined | null
+): OpenAIImageApiDialect | null {
+  if (!value) return null;
+  const normalized = value.replace(/['"]/g, "").trim();
+  if (normalized === "openai-native" || normalized === "ratio-metadata") return normalized;
+  throw new Error(`Invalid OpenAI image API dialect: ${value}`);
+}
+
 type ExtendConfigPathPair = {
   current: string;
   legacy: string;
@@ -541,12 +571,25 @@ export async function loadExtendConfig(
 }
 
 export function mergeConfig(args: CliArgs, extend: Partial<ExtendConfig>): CliArgs {
+  const aspectRatio = args.aspectRatio ?? extend.default_aspect_ratio ?? null;
+  const imageSize = args.imageSize ?? extend.default_image_size ?? null;
+  const imageApiDialect =
+    args.imageApiDialect ??
+    extend.default_image_api_dialect ??
+    parseOpenAIImageApiDialect(process.env.OPENAI_IMAGE_API_DIALECT);
   return {
     ...args,
     provider: args.provider ?? extend.default_provider ?? null,
     quality: args.quality ?? extend.default_quality ?? null,
-    aspectRatio: args.aspectRatio ?? extend.default_aspect_ratio ?? null,
-    imageSize: args.imageSize ?? extend.default_image_size ?? null,
+    aspectRatio,
+    aspectRatioSource:
+      args.aspectRatioSource ??
+      (args.aspectRatio !== null ? "cli" : (aspectRatio !== null ? "config" : null)),
+    imageSize,
+    imageSizeSource:
+      args.imageSizeSource ??
+      (args.imageSize !== null ? "cli" : (imageSize !== null ? "config" : null)),
+    imageApiDialect,
   };
 }
 
@@ -759,6 +802,7 @@ export function isRetryableGenerationError(error: unknown): boolean {
     "API error (403)",
     "API error (404)",
     "temporarily disabled",
+    "supports saving exactly one image",
   ];
   return !nonRetryableMarkers.some((marker) => msg.includes(marker));
 }
@@ -872,9 +916,12 @@ export function createTaskArgs(baseArgs: CliArgs, task: BatchTaskInput, batchDir
     provider: task.provider ?? baseArgs.provider ?? null,
     model: task.model ?? baseArgs.model ?? null,
     aspectRatio: task.ar ?? baseArgs.aspectRatio ?? null,
+    aspectRatioSource: task.ar != null ? "task" : (baseArgs.aspectRatioSource ?? null),
     size: task.size ?? baseArgs.size ?? null,
     quality: task.quality ?? baseArgs.quality ?? null,
     imageSize: task.imageSize ?? baseArgs.imageSize ?? null,
+    imageSizeSource: task.imageSize != null ? "task" : (baseArgs.imageSizeSource ?? null),
+    imageApiDialect: task.imageApiDialect ?? baseArgs.imageApiDialect ?? null,
     referenceImages: task.ref ? task.ref.map((filePath) => resolveBatchPath(batchDir, filePath)) : [],
     n: task.n ?? baseArgs.n,
     batchFile: null,

skills/baoyu-imagine/scripts/providers/azure.test.ts

@@ -48,6 +48,7 @@ function makeArgs(overrides: Partial<CliArgs> = {}): CliArgs {
     size: null,
     quality: null,
     imageSize: null,
+    imageApiDialect: null,
     referenceImages: [],
     n: 1,
     batchFile: null,

skills/baoyu-imagine/scripts/providers/google.test.ts

@@ -50,6 +50,7 @@ function makeArgs(overrides: Partial<CliArgs> = {}): CliArgs {
     size: null,
     quality: null,
     imageSize: null,
+    imageApiDialect: null,
     referenceImages: [],
     n: 1,
     batchFile: null,

skills/baoyu-imagine/scripts/providers/jimeng.test.ts

@@ -15,6 +15,7 @@ function makeArgs(overrides: Partial<CliArgs> = {}): CliArgs {
     size: null,
     quality: null,
     imageSize: null,
+    imageApiDialect: null,
     referenceImages: [],
     n: 1,
     batchFile: null,

skills/baoyu-imagine/scripts/providers/minimax.test.ts

@@ -50,6 +50,7 @@ function makeArgs(overrides: Partial<CliArgs> = {}): CliArgs {
     size: null,
     quality: null,
     imageSize: null,
+    imageApiDialect: null,
     referenceImages: [],
     n: 1,
     batchFile: null,

skills/baoyu-imagine/scripts/providers/openai.test.ts

@@ -2,9 +2,16 @@ import assert from "node:assert/strict";
 import test from "node:test";
 
 import {
+  buildOpenAIGenerationsBody,
   extractImageFromResponse,
+  getOpenAIAspectRatio,
+  getOpenAIImageApiDialect,
+  getOpenAIResolution,
   getMimeType,
   getOpenAISize,
+  getOrientationFromAspectRatio,
+  inferAspectRatioFromSize,
+  inferResolutionFromSize,
   parseAspectRatio,
 } from "./openai.ts";
 
@@ -18,6 +25,69 @@ test("OpenAI aspect-ratio parsing and size selection match model families", () =
   assert.equal(getOpenAISize("dall-e-2", "16:9", "2k"), "1024x1024");
   assert.equal(getOpenAISize("gpt-image-1.5", "16:9", "2k"), "1536x1024");
   assert.equal(getOpenAISize("gpt-image-1.5", "4:3", "2k"), "1024x1024");
+  assert.equal(inferAspectRatioFromSize("1536x1024"), "3:2");
+  assert.equal(inferResolutionFromSize("1536x1024"), "2K");
+  assert.equal(getOpenAIAspectRatio({ aspectRatio: null, size: "2048x1152" }), "16:9");
+  assert.equal(getOpenAIResolution({ imageSize: null, size: "2048x1152", quality: "normal" }), "2K");
+  assert.equal(getOrientationFromAspectRatio("16:9"), "landscape");
+  assert.equal(getOrientationFromAspectRatio("9:16"), "portrait");
+  assert.equal(getOrientationFromAspectRatio("1:1"), null);
+  assert.equal(getOpenAIImageApiDialect({ imageApiDialect: null }), "openai-native");
+});
+
+test("OpenAI generations body switches between native and ratio-metadata dialects", () => {
+  assert.deepEqual(
+    buildOpenAIGenerationsBody("Draw a skyline", "gpt-image-1.5", {
+      aspectRatio: "16:9",
+      size: null,
+      quality: "2k",
+      imageSize: null,
+      imageApiDialect: null,
+    }),
+    {
+      model: "gpt-image-1.5",
+      prompt: "Draw a skyline",
+      size: "1536x1024",
+    },
+  );
+
+  assert.deepEqual(
+    buildOpenAIGenerationsBody("Draw a skyline", "gemini-3-pro-image-preview", {
+      aspectRatio: "16:9",
+      size: null,
+      quality: "2k",
+      imageSize: null,
+      imageApiDialect: "ratio-metadata",
+    }),
+    {
+      model: "gemini-3-pro-image-preview",
+      prompt: "Draw a skyline",
+      size: "16:9",
+      metadata: {
+        resolution: "2K",
+        orientation: "landscape",
+      },
+    },
+  );
+
+  assert.deepEqual(
+    buildOpenAIGenerationsBody("Draw a portrait", "gemini-3-pro-image-preview", {
+      aspectRatio: null,
+      size: "1152x2048",
+      quality: "normal",
+      imageSize: null,
+      imageApiDialect: "ratio-metadata",
+    }),
+    {
+      model: "gemini-3-pro-image-preview",
+      prompt: "Draw a portrait",
+      size: "9:16",
+      metadata: {
+        resolution: "2K",
+        orientation: "portrait",
+      },
+    },
+  );
 });
 
 test("OpenAI mime-type detection covers supported reference image extensions", () => {

skills/baoyu-imagine/scripts/providers/openai.ts

@@ -1,6 +1,6 @@
 import path from "node:path";
 import { readFile } from "node:fs/promises";
-import type { CliArgs } from "../types";
+import type { CliArgs, OpenAIImageApiDialect } from "../types";
 
 export function getDefaultModel(): string {
   return process.env.OPENAI_IMAGE_MODEL || "gpt-image-1.5";
@@ -23,6 +23,8 @@ type SizeMapping = {
   portrait: string;
 };
 
+type OpenAIGenerationsBody = Record<string, unknown>;
+
 export function getOpenAISize(
   model: string,
   ar: string | null,
@@ -60,6 +62,114 @@ export function getOpenAISize(
   return sizes.square;
 }
 
+function parsePixelSize(value: string): { width: number; height: number } | null {
+  const match = value.match(/^(\d+)\s*[xX]\s*(\d+)$/);
+  if (!match) return null;
+
+  const width = parseInt(match[1]!, 10);
+  const height = parseInt(match[2]!, 10);
+  if (!Number.isFinite(width) || !Number.isFinite(height) || width <= 0 || height <= 0) {
+    return null;
+  }
+
+  return { width, height };
+}
+
+function gcd(a: number, b: number): number {
+  let x = Math.abs(a);
+  let y = Math.abs(b);
+  while (y !== 0) {
+    const next = x % y;
+    x = y;
+    y = next;
+  }
+  return x || 1;
+}
+
+export function getOpenAIImageApiDialect(args: Pick<CliArgs, "imageApiDialect">): OpenAIImageApiDialect {
+  return args.imageApiDialect ?? "openai-native";
+}
+
+export function inferAspectRatioFromSize(size: string | null): string | null {
+  if (!size) return null;
+  const parsed = parsePixelSize(size);
+  if (!parsed) return null;
+
+  const divisor = gcd(parsed.width, parsed.height);
+  return `${parsed.width / divisor}:${parsed.height / divisor}`;
+}
+
+export function inferResolutionFromSize(size: string | null): "1K" | "2K" | "4K" | null {
+  if (!size) return null;
+  const parsed = parsePixelSize(size);
+  if (!parsed) return null;
+
+  const longestEdge = Math.max(parsed.width, parsed.height);
+  if (longestEdge <= 1024) return "1K";
+  if (longestEdge <= 2048) return "2K";
+  return "4K";
+}
+
+export function getOpenAIAspectRatio(args: Pick<CliArgs, "aspectRatio" | "size">): string {
+  return args.aspectRatio ?? inferAspectRatioFromSize(args.size) ?? "1:1";
+}
+
+export function getOpenAIResolution(
+  args: Pick<CliArgs, "imageSize" | "size" | "quality">
+): "1K" | "2K" | "4K" {
+  if (args.imageSize === "1K" || args.imageSize === "2K" || args.imageSize === "4K") {
+    return args.imageSize;
+  }
+
+  const inferred = inferResolutionFromSize(args.size);
+  if (inferred) return inferred;
+
+  return args.quality === "normal" ? "1K" : "2K";
+}
+
+export function getOrientationFromAspectRatio(ar: string): "landscape" | "portrait" | null {
+  const parsed = parseAspectRatio(ar);
+  if (!parsed) return null;
+
+  const ratio = parsed.width / parsed.height;
+  if (Math.abs(ratio - 1) < 0.1) return null;
+  return ratio > 1 ? "landscape" : "portrait";
+}
+
+export function buildOpenAIGenerationsBody(
+  prompt: string,
+  model: string,
+  args: Pick<CliArgs, "aspectRatio" | "size" | "quality" | "imageSize" | "imageApiDialect">
+): OpenAIGenerationsBody {
+  if (getOpenAIImageApiDialect(args) === "ratio-metadata") {
+    const aspectRatio = getOpenAIAspectRatio(args);
+    const metadata: Record<string, string> = {
+      resolution: getOpenAIResolution(args),
+    };
+    const orientation = getOrientationFromAspectRatio(aspectRatio);
+    if (orientation) metadata.orientation = orientation;
+
+    return {
+      model,
+      prompt,
+      size: aspectRatio,
+      metadata,
+    };
+  }
+
+  const body: OpenAIGenerationsBody = {
+    model,
+    prompt,
+    size: args.size || getOpenAISize(model, args.aspectRatio, args.quality),
+  };
+
+  if (model.includes("dall-e-3")) {
+    body.quality = args.quality === "2k" ? "hd" : "standard";
+  }
+
+  return body;
+}
+
 export async function generateImage(
   prompt: string,
   model: string,
@@ -78,18 +188,28 @@ export async function generateImage(
     return generateWithChatCompletions(baseURL, apiKey, prompt, model);
   }
 
-  const size = args.size || getOpenAISize(model, args.aspectRatio, args.quality);
+  const imageApiDialect = getOpenAIImageApiDialect(args);
 
   if (args.referenceImages.length > 0) {
+    if (imageApiDialect !== "openai-native") {
+      throw new Error(
+        "Reference images are not supported with the ratio-metadata OpenAI dialect yet. Use openai-native, Google, Azure, OpenRouter, MiniMax, Seedream, or Replicate for image-edit workflows."
+      );
+    }
     if (model.includes("dall-e-2") || model.includes("dall-e-3")) {
       throw new Error(
         "Reference images with OpenAI in this skill require GPT Image models. Use --model gpt-image-1.5 (or another gpt-image model)."
       );
     }
+    const size = args.size || getOpenAISize(model, args.aspectRatio, args.quality);
     return generateWithOpenAIEdits(baseURL, apiKey, prompt, model, size, args.referenceImages, args.quality);
   }
 
-  return generateWithOpenAIGenerations(baseURL, apiKey, prompt, model, size, args.quality);
+  return generateWithOpenAIGenerations(
+    baseURL,
+    apiKey,
+    buildOpenAIGenerationsBody(prompt, model, args)
+  );
 }
 
 async function generateWithChatCompletions(
@@ -129,17 +249,8 @@ async function generateWithChatCompletions(
 async function generateWithOpenAIGenerations(
   baseURL: string,
   apiKey: string,
-  prompt: string,
-  model: string,
-  size: string,
-  quality: CliArgs["quality"]
+  body: OpenAIGenerationsBody
 ): Promise<Uint8Array> {
-  const body: Record<string, any> = { model, prompt, size };
-
-  if (model.includes("dall-e-3")) {
-    body.quality = quality === "2k" ? "hd" : "standard";
-  }
-
   const res = await fetch(`${baseURL}/images/generations`, {
     method: "POST",
     headers: {

skills/baoyu-imagine/scripts/providers/openrouter.test.ts

@@ -28,6 +28,7 @@ function makeArgs(overrides: Partial<CliArgs> = {}): CliArgs {
     size: null,
     quality: null,
     imageSize: null,
+    imageApiDialect: null,
     referenceImages: [],
     n: 1,
     batchFile: null,

skills/baoyu-imagine/scripts/providers/replicate.test.ts

@@ -5,7 +5,10 @@ import type { CliArgs } from "../types.ts";
 import {
   buildInput,
   extractOutputUrl,
+  getDefaultModel,
+  getModelFamily,
   parseModelId,
+  validateArgs,
 } from "./replicate.ts";
 
 function makeArgs(overrides: Partial<CliArgs> = {}): CliArgs {
@@ -16,9 +19,12 @@ function makeArgs(overrides: Partial<CliArgs> = {}): CliArgs {
     provider: null,
     model: null,
     aspectRatio: null,
+    aspectRatioSource: null,
     size: null,
     quality: null,
     imageSize: null,
+    imageSizeSource: null,
+    imageApiDialect: null,
     referenceImages: [],
     n: 1,
     batchFile: null,
@@ -29,10 +35,24 @@ function makeArgs(overrides: Partial<CliArgs> = {}): CliArgs {
   };
 }
 
-test("Replicate model parsing accepts official formats and rejects malformed ones", () => {
-  assert.deepEqual(parseModelId("google/nano-banana-pro"), {
+test("Replicate default model now points at nano-banana-2", () => {
+  const previous = process.env.REPLICATE_IMAGE_MODEL;
+  delete process.env.REPLICATE_IMAGE_MODEL;
+  try {
+    assert.equal(getDefaultModel(), "google/nano-banana-2");
+  } finally {
+    if (previous == null) {
+      delete process.env.REPLICATE_IMAGE_MODEL;
+    } else {
+      process.env.REPLICATE_IMAGE_MODEL = previous;
+    }
+  }
+});
+
+test("Replicate model parsing and family detection accept supported official ids", () => {
+  assert.deepEqual(parseModelId("google/nano-banana-2"), {
     owner: "google",
-    name: "nano-banana-pro",
+    name: "nano-banana-2",
     version: null,
   });
   assert.deepEqual(parseModelId("owner/model:abc123"), {
@@ -41,46 +61,224 @@ test("Replicate model parsing accepts official formats and rejects malformed one
     version: "abc123",
   });
 
+  assert.equal(getModelFamily("google/nano-banana-pro"), "nano-banana");
+  assert.equal(getModelFamily("bytedance/seedream-4.5"), "seedream45");
+  assert.equal(getModelFamily("bytedance/seedream-5-lite"), "seedream5lite");
+  assert.equal(getModelFamily("wan-video/wan-2.7-image"), "wan27image");
+  assert.equal(getModelFamily("wan-video/wan-2.7-image-pro"), "wan27imagepro");
+  assert.equal(getModelFamily("stability-ai/sdxl"), "unknown");
+
   assert.throws(
     () => parseModelId("just-a-model-name"),
     /Invalid Replicate model format/,
   );
 });
 
-test("Replicate input builder maps aspect ratio, image count, quality, and refs", () => {
+test("Replicate nano-banana input builder maps refs, aspect ratio, and quality presets", () => {
   assert.deepEqual(
     buildInput(
+      "google/nano-banana-2",
       "A robot painter",
       makeArgs({
         aspectRatio: "16:9",
         quality: "2k",
-        n: 3,
       }),
       ["data:image/png;base64,AAAA"],
     ),
     {
       prompt: "A robot painter",
-      aspect_ratio: "16:9",
-      number_of_images: 3,
       resolution: "2K",
       output_format: "png",
+      aspect_ratio: "16:9",
       image_input: ["data:image/png;base64,AAAA"],
     },
   );
 
   assert.deepEqual(
-    buildInput("A robot painter", makeArgs({ quality: "normal" }), ["ref"]),
+    buildInput(
+      "google/nano-banana-2",
+      "A robot painter",
+      makeArgs({ size: "1024x1024", quality: "normal" }),
+      [],
+    ),
     {
       prompt: "A robot painter",
-      aspect_ratio: "match_input_image",
       resolution: "1K",
       output_format: "png",
-      image_input: ["ref"],
+      aspect_ratio: "1:1",
     },
   );
 });
 
-test("Replicate output extraction supports string, array, and object URLs", () => {
+test("Replicate Seedream and Wan inputs use family-specific request fields", () => {
+  assert.deepEqual(
+    buildInput(
+      "bytedance/seedream-4.5",
+      "A cinematic portrait",
+      makeArgs({ quality: "2k", referenceImages: ["local.png"] }),
+      ["data:image/png;base64,AAAA"],
+    ),
+    {
+      prompt: "A cinematic portrait",
+      size: "4K",
+      image_input: ["data:image/png;base64,AAAA"],
+      aspect_ratio: "match_input_image",
+    },
+  );
+
+  assert.deepEqual(
+    buildInput(
+      "bytedance/seedream-4.5",
+      "A cinematic portrait",
+      makeArgs({ size: "1536x1024" }),
+      [],
+    ),
+    {
+      prompt: "A cinematic portrait",
+      size: "custom",
+      width: 1536,
+      height: 1024,
+    },
+  );
+
+  assert.deepEqual(
+    buildInput(
+      "bytedance/seedream-5-lite",
+      "A poster",
+      makeArgs({ aspectRatio: "21:9", quality: "2k" }),
+      [],
+    ),
+    {
+      prompt: "A poster",
+      size: "3K",
+      aspect_ratio: "21:9",
+    },
+  );
+
+  assert.deepEqual(
+    buildInput(
+      "wan-video/wan-2.7-image",
+      "A storyboard frame",
+      makeArgs({ aspectRatio: "16:9", quality: "2k" }),
+      [],
+    ),
+    {
+      prompt: "A storyboard frame",
+      size: "2048*1152",
+    },
+  );
+
+  assert.deepEqual(
+    buildInput(
+      "wan-video/wan-2.7-image-pro",
+      "Blend these references",
+      makeArgs({ size: "2K", referenceImages: ["a.png", "b.png"] }),
+      ["ref-a", "ref-b"],
+    ),
+    {
+      prompt: "Blend these references",
+      size: "2K",
+      images: ["ref-a", "ref-b"],
+    },
+  );
+});
+
+test("Replicate validateArgs blocks misleading multi-output and unsupported family options locally", () => {
+  assert.throws(
+    () =>
+      validateArgs(
+        "google/nano-banana-2",
+        makeArgs({ n: 2 }),
+      ),
+    /exactly one output image/,
+  );
+
+  assert.throws(
+    () =>
+      validateArgs(
+        "bytedance/seedream-4.5",
+        makeArgs({ size: "1K" }),
+      ),
+    /2K, 4K, or an explicit WxH size/,
+  );
+
+  assert.throws(
+    () =>
+      validateArgs(
+        "bytedance/seedream-5-lite",
+        makeArgs({ size: "4K" }),
+      ),
+    /supports 2K or 3K output/,
+  );
+
+  assert.throws(
+    () =>
+      validateArgs(
+        "wan-video/wan-2.7-image",
+        makeArgs({ referenceImages: new Array(10).fill("ref.png") }),
+      ),
+    /at most 9 reference images/,
+  );
+
+  assert.throws(
+    () =>
+      validateArgs(
+        "wan-video/wan-2.7-image-pro",
+        makeArgs({ referenceImages: ["ref.png"], size: "4K" }),
+      ),
+    /only supports 4K text-to-image/,
+  );
+
+  assert.throws(
+    () =>
+      validateArgs(
+        "stability-ai/sdxl",
+        makeArgs({ aspectRatio: "16:9" }),
+      ),
+    /compatibility list/,
+  );
+
+  assert.doesNotThrow(() =>
+    validateArgs(
+      "google/nano-banana-2",
+      makeArgs({ imageSize: "2K", imageSizeSource: "config" }),
+    ),
+  );
+
+  assert.throws(
+    () =>
+      validateArgs(
+        "google/nano-banana-2",
+        makeArgs({ imageSize: "2K", imageSizeSource: "cli" }),
+      ),
+    /do not use --imageSize/,
+  );
+
+  assert.doesNotThrow(() =>
+    validateArgs(
+      "stability-ai/sdxl",
+      makeArgs({ aspectRatio: "16:9", aspectRatioSource: "config" }),
+    ),
+  );
+
+  assert.throws(
+    () =>
+      validateArgs(
+        "stability-ai/sdxl",
+        makeArgs({ aspectRatio: "16:9", aspectRatioSource: "cli" }),
+      ),
+    /compatibility list/,
+  );
+
+  assert.doesNotThrow(() =>
+    validateArgs(
+      "stability-ai/sdxl",
+      makeArgs(),
+    ),
+  );
+});
+
+test("Replicate output extraction supports single outputs and rejects silent multi-image drops", () => {
   assert.equal(
     extractOutputUrl({ output: "https://example.com/a.png" } as never),
     "https://example.com/a.png",
@@ -94,6 +292,17 @@ test("Replicate output extraction supports string, array, and object URLs", () =
     "https://example.com/c.png",
   );
 
+  assert.throws(
+    () =>
+      extractOutputUrl({
+        output: [
+          "https://example.com/one.png",
+          "https://example.com/two.png",
+        ],
+      } as never),
+    /supports saving exactly one image/,
+  );
+
   assert.throws(
     () => extractOutputUrl({ output: { invalid: true } } as never),
     /Unexpected Replicate output format/,

skills/baoyu-imagine/scripts/providers/replicate.ts

@@ -2,10 +2,37 @@ import path from "node:path";
 import { readFile } from "node:fs/promises";
 import type { CliArgs } from "../types";
 
-const DEFAULT_MODEL = "google/nano-banana-pro";
+const DEFAULT_MODEL = "google/nano-banana-2";
 const SYNC_WAIT_SECONDS = 60;
 const POLL_INTERVAL_MS = 2000;
 const MAX_POLL_MS = 300_000;
+const DOCUMENTED_REPLICATE_ASPECT_RATIOS = new Set([
+  "1:1",
+  "2:3",
+  "3:2",
+  "3:4",
+  "4:3",
+  "5:4",
+  "4:5",
+  "9:16",
+  "16:9",
+  "21:9",
+]);
+
+export type ReplicateModelFamily =
+  | "nano-banana"
+  | "seedream45"
+  | "seedream5lite"
+  | "wan27image"
+  | "wan27imagepro"
+  | "unknown";
+
+type PixelSize = {
+  width: number;
+  height: number;
+};
+
+type Seedream45Size = "2K" | "4K" | { width: number; height: number };
 
 export function getDefaultModel(): string {
   return process.env.REPLICATE_IMAGE_MODEL || DEFAULT_MODEL;
@@ -20,6 +47,40 @@ function getBaseUrl(): string {
   return base.replace(/\/+$/g, "");
 }
 
+function normalizeModelId(model: string): string {
+  return model.trim().toLowerCase().split(":")[0]!;
+}
+
+export function getModelFamily(model: string): ReplicateModelFamily {
+  const normalized = normalizeModelId(model);
+
+  if (
+    normalized === "google/nano-banana" ||
+    normalized === "google/nano-banana-pro" ||
+    normalized === "google/nano-banana-2"
+  ) {
+    return "nano-banana";
+  }
+
+  if (normalized === "bytedance/seedream-4.5") {
+    return "seedream45";
+  }
+
+  if (normalized === "bytedance/seedream-5-lite") {
+    return "seedream5lite";
+  }
+
+  if (normalized === "wan-video/wan-2.7-image") {
+    return "wan27image";
+  }
+
+  if (normalized === "wan-video/wan-2.7-image-pro") {
+    return "wan27imagepro";
+  }
+
+  return "unknown";
+}
+
 export function parseModelId(model: string): { owner: string; name: string; version: string | null } {
   const [ownerName, version] = model.split(":");
   const parts = ownerName!.split("/");
@@ -31,27 +92,219 @@ export function parseModelId(model: string): { owner: string; name: string; vers
   return { owner: parts[0], name: parts[1], version: version || null };
 }
 
-export function buildInput(prompt: string, args: CliArgs, referenceImages: string[]): Record<string, unknown> {
-  const input: Record<string, unknown> = { prompt };
+function parsePixelSize(value: string): PixelSize | null {
+  const match = value.trim().match(/^(\d+)\s*[xX*]\s*(\d+)$/);
+  if (!match) return null;
+
+  const width = parseInt(match[1]!, 10);
+  const height = parseInt(match[2]!, 10);
+  if (!Number.isFinite(width) || !Number.isFinite(height) || width <= 0 || height <= 0) {
+    return null;
+  }
+
+  return { width, height };
+}
+
+function parseAspectRatio(value: string): PixelSize | null {
+  const match = value.trim().match(/^(\d+)\s*:\s*(\d+)$/);
+  if (!match) return null;
+
+  const width = parseInt(match[1]!, 10);
+  const height = parseInt(match[2]!, 10);
+  if (!Number.isFinite(width) || !Number.isFinite(height) || width <= 0 || height <= 0) {
+    return null;
+  }
+
+  return { width, height };
+}
+
+function gcd(a: number, b: number): number {
+  let x = Math.abs(a);
+  let y = Math.abs(b);
+
+  while (y !== 0) {
+    const next = x % y;
+    x = y;
+    y = next;
+  }
+
+  return x || 1;
+}
+
+function inferAspectRatioFromSize(size: string): string | null {
+  const parsed = parsePixelSize(size);
+  if (!parsed) return null;
+
+  const divisor = gcd(parsed.width, parsed.height);
+  const normalized = `${parsed.width / divisor}:${parsed.height / divisor}`;
+  if (!DOCUMENTED_REPLICATE_ASPECT_RATIOS.has(normalized)) {
+    return null;
+  }
+
+  return normalized;
+}
+
+function getQualityPreset(args: CliArgs): "normal" | "2k" {
+  return args.quality === "normal" ? "normal" : "2k";
+}
+
+function validateDocumentedAspectRatio(model: string, aspectRatio: string): void {
+  if (aspectRatio === "match_input_image") {
+    return;
+  }
+
+  if (DOCUMENTED_REPLICATE_ASPECT_RATIOS.has(aspectRatio)) {
+    return;
+  }
+
+  throw new Error(
+    `Replicate model ${model} does not support aspect ratio ${aspectRatio}. Supported values: ${Array.from(DOCUMENTED_REPLICATE_ASPECT_RATIOS).join(", ")}`
+  );
+}
+
+function getRequestedAspectRatio(model: string, args: CliArgs): string | null {
+  if (args.aspectRatio) {
+    validateDocumentedAspectRatio(model, args.aspectRatio);
+    return args.aspectRatio;
+  }
+
+  if (!args.size) return null;
+
+  const inferred = inferAspectRatioFromSize(args.size);
+  if (!inferred) {
+    throw new Error(
+      `Replicate model ${model} cannot derive a supported aspect ratio from --size ${args.size}. Use one of: ${Array.from(DOCUMENTED_REPLICATE_ASPECT_RATIOS).join(", ")}`
+    );
+  }
+
+  return inferred;
+}
+
+function getNanoBananaResolution(args: CliArgs): "1K" | "2K" {
+  if (args.size) {
+    const parsed = parsePixelSize(args.size);
+    if (!parsed) {
+      throw new Error("Replicate nano-banana --size must be in WxH format, for example 1536x1024.");
+    }
+
+    const longestEdge = Math.max(parsed.width, parsed.height);
+    if (longestEdge <= 1024) return "1K";
+    if (longestEdge <= 2048) return "2K";
+    throw new Error("Replicate nano-banana only supports sizes that map to 1K or 2K output.");
+  }
+
+  return getQualityPreset(args) === "normal" ? "1K" : "2K";
+}
+
+function resolveSeedream45Size(args: CliArgs): Seedream45Size {
+  if (args.size) {
+    const upper = args.size.trim().toUpperCase();
+    if (upper === "2K" || upper === "4K") {
+      return upper;
+    }
+
+    const parsed = parsePixelSize(args.size);
+    if (!parsed) {
+      throw new Error("Replicate Seedream 4.5 --size must be 2K, 4K, or an explicit WxH size.");
+    }
+    if (parsed.width < 1024 || parsed.width > 4096 || parsed.height < 1024 || parsed.height > 4096) {
+      throw new Error("Replicate Seedream 4.5 custom --size must keep width and height between 1024 and 4096.");
+    }
+    return parsed;
+  }
+
+  return getQualityPreset(args) === "normal" ? "2K" : "4K";
+}
+
+function resolveSeedream5LiteSize(args: CliArgs): "2K" | "3K" {
+  if (args.size) {
+    const upper = args.size.trim().toUpperCase();
+    if (upper === "2K" || upper === "3K") {
+      return upper;
+    }
+
+    throw new Error("Replicate Seedream 5 Lite currently supports 2K or 3K output in this tool.");
+  }
+
+  return getQualityPreset(args) === "normal" ? "2K" : "3K";
+}
+
+function formatCustomWanSize(size: PixelSize): string {
+  return `${size.width}*${size.height}`;
+}
+
+function resolveWanSizeFromAspectRatio(
+  aspectRatio: string,
+  maxDimension: number,
+): string {
+  const parsedRatio = parseAspectRatio(aspectRatio);
+  if (!parsedRatio) {
+    throw new Error(`Replicate Wan aspect ratio must be in W:H format, got ${aspectRatio}.`);
+  }
+
+  const scale = Math.min(maxDimension / parsedRatio.width, maxDimension / parsedRatio.height);
+  const width = Math.max(1, Math.floor(parsedRatio.width * scale));
+  const height = Math.max(1, Math.floor(parsedRatio.height * scale));
+  return formatCustomWanSize({ width, height });
+}
+
+function resolveWanSize(family: "wan27image" | "wan27imagepro", args: CliArgs): "1K" | "2K" | "4K" | string {
+  const referenceMode = args.referenceImages.length > 0;
+  const maxDimension = family === "wan27imagepro" && !referenceMode ? 4096 : 2048;
+
+  if (args.size) {
+    const upper = args.size.trim().toUpperCase();
+    if (upper === "1K" || upper === "2K" || upper === "4K") {
+      if (upper === "4K" && family !== "wan27imagepro") {
+        throw new Error("Replicate Wan 2.7 Image only supports 1K, 2K, or custom sizes up to 2048px.");
+      }
+      if (upper === "4K" && referenceMode) {
+        throw new Error("Replicate Wan 2.7 Image Pro only supports 4K text-to-image. Remove --ref or lower the size.");
+      }
+      return upper;
+    }
+
+    const parsed = parsePixelSize(args.size);
+    if (!parsed) {
+      throw new Error("Replicate Wan --size must be 1K, 2K, 4K, or an explicit WxH size.");
+    }
+    if (parsed.width > maxDimension || parsed.height > maxDimension) {
+      throw new Error(
+        `Replicate ${family === "wan27imagepro" ? "Wan 2.7 Image Pro" : "Wan 2.7 Image"} custom --size must keep width and height at or below ${maxDimension}px in the current mode.`
+      );
+    }
+    return formatCustomWanSize(parsed);
+  }
 
   if (args.aspectRatio) {
-    input.aspect_ratio = args.aspectRatio;
+    return resolveWanSizeFromAspectRatio(
+      args.aspectRatio,
+      getQualityPreset(args) === "normal" ? 1024 : 2048,
+    );
+  }
+
+  return getQualityPreset(args) === "normal" ? "1K" : "2K";
+}
+
+function buildNanoBananaInput(
+  prompt: string,
+  model: string,
+  args: CliArgs,
+  referenceImages: string[],
+): Record<string, unknown> {
+  const input: Record<string, unknown> = {
+    prompt,
+    resolution: getNanoBananaResolution(args),
+    output_format: "png",
+  };
+
+  const aspectRatio = getRequestedAspectRatio(model, args);
+  if (aspectRatio) {
+    input.aspect_ratio = aspectRatio;
   } else if (referenceImages.length > 0) {
     input.aspect_ratio = "match_input_image";
   }
 
-  if (args.n > 1) {
-    input.number_of_images = args.n;
-  }
-
-  if (args.quality === "normal") {
-    input.resolution = "1K";
-  } else if (args.quality === "2k") {
-    input.resolution = "2K";
-  }
-
-  input.output_format = "png";
-
   if (referenceImages.length > 0) {
     input.image_input = referenceImages;
   }
@@ -59,6 +312,158 @@ export function buildInput(prompt: string, args: CliArgs, referenceImages: strin
   return input;
 }
 
+function buildSeedreamInput(
+  family: "seedream45" | "seedream5lite",
+  prompt: string,
+  model: string,
+  args: CliArgs,
+  referenceImages: string[],
+): Record<string, unknown> {
+  const size = family === "seedream45" ? resolveSeedream45Size(args) : resolveSeedream5LiteSize(args);
+  const input: Record<string, unknown> = {
+    prompt,
+  };
+
+  if (family === "seedream45" && typeof size === "object") {
+    input.size = "custom";
+    input.width = size.width;
+    input.height = size.height;
+  } else {
+    input.size = size;
+  }
+
+  if (referenceImages.length > 0) {
+    input.image_input = referenceImages;
+  }
+
+  if (args.aspectRatio) {
+    validateDocumentedAspectRatio(model, args.aspectRatio);
+    input.aspect_ratio = args.aspectRatio;
+  } else if (referenceImages.length > 0 && family === "seedream45") {
+    input.aspect_ratio = "match_input_image";
+  }
+
+  return input;
+}
+
+function buildWanInput(
+  family: "wan27image" | "wan27imagepro",
+  prompt: string,
+  args: CliArgs,
+  referenceImages: string[],
+): Record<string, unknown> {
+  const input: Record<string, unknown> = {
+    prompt,
+    size: resolveWanSize(family, args),
+  };
+
+  if (referenceImages.length > 0) {
+    input.images = referenceImages;
+  }
+
+  return input;
+}
+
+export function validateArgs(model: string, args: CliArgs): void {
+  parseModelId(model);
+
+  if (args.n !== 1) {
+    throw new Error("Replicate integration currently supports exactly one output image per request. Remove --n or use --n 1.");
+  }
+
+  if (args.imageSize && args.imageSizeSource !== "config") {
+    throw new Error("Replicate models in baoyu-imagine do not use --imageSize. Use --quality, --ar, or --size instead.");
+  }
+
+  const family = getModelFamily(model);
+
+  if (family === "nano-banana") {
+    if (args.referenceImages.length > 14) {
+      throw new Error("Replicate nano-banana supports at most 14 reference images.");
+    }
+    if (args.aspectRatio) {
+      validateDocumentedAspectRatio(model, args.aspectRatio);
+    }
+    if (args.size) {
+      getRequestedAspectRatio(model, args);
+      getNanoBananaResolution(args);
+    }
+    return;
+  }
+
+  if (family === "seedream45") {
+    if (args.referenceImages.length > 14) {
+      throw new Error("Replicate Seedream 4.5 supports at most 14 reference images.");
+    }
+    if (args.aspectRatio) {
+      validateDocumentedAspectRatio(model, args.aspectRatio);
+    }
+    resolveSeedream45Size(args);
+    return;
+  }
+
+  if (family === "seedream5lite") {
+    if (args.referenceImages.length > 14) {
+      throw new Error("Replicate Seedream 5 Lite supports at most 14 reference images.");
+    }
+    if (args.aspectRatio) {
+      validateDocumentedAspectRatio(model, args.aspectRatio);
+    }
+    resolveSeedream5LiteSize(args);
+    return;
+  }
+
+  if (family === "wan27image" || family === "wan27imagepro") {
+    if (args.referenceImages.length > 9) {
+      throw new Error("Replicate Wan 2.7 image models support at most 9 reference images.");
+    }
+    if (args.aspectRatio) {
+      const parsed = parseAspectRatio(args.aspectRatio);
+      if (!parsed) {
+        throw new Error(`Replicate Wan aspect ratio must be in W:H format, got ${args.aspectRatio}.`);
+      }
+    }
+    resolveWanSize(family, args);
+    return;
+  }
+
+  const hasExplicitAspectRatio = !!args.aspectRatio && args.aspectRatioSource !== "config";
+
+  if (args.referenceImages.length > 0 || hasExplicitAspectRatio || args.size) {
+    throw new Error(
+      `Replicate model ${model} is not in the baoyu-imagine compatibility list. Supported families: google/nano-banana*, bytedance/seedream-4.5, bytedance/seedream-5-lite, wan-video/wan-2.7-image, wan-video/wan-2.7-image-pro.`
+    );
+  }
+}
+
+export function getDefaultOutputExtension(model: string): ".png" {
+  const _family = getModelFamily(model);
+  return ".png";
+}
+
+export function buildInput(
+  model: string,
+  prompt: string,
+  args: CliArgs,
+  referenceImages: string[],
+): Record<string, unknown> {
+  const family = getModelFamily(model);
+
+  if (family === "nano-banana") {
+    return buildNanoBananaInput(prompt, model, args, referenceImages);
+  }
+
+  if (family === "seedream45" || family === "seedream5lite") {
+    return buildSeedreamInput(family, prompt, model, args, referenceImages);
+  }
+
+  if (family === "wan27image" || family === "wan27imagepro") {
+    return buildWanInput(family, prompt, args, referenceImages);
+  }
+
+  return { prompt };
+}
+
 async function readImageAsDataUrl(p: string): Promise<string> {
   const buf = await readFile(p);
   const ext = path.extname(p).toLowerCase();
@@ -150,6 +555,11 @@ export function extractOutputUrl(prediction: PredictionResponse): string {
   if (typeof output === "string") return output;
 
   if (Array.isArray(output)) {
+    if (output.length !== 1) {
+      throw new Error(
+        `Replicate returned ${output.length} outputs, but baoyu-imagine currently supports saving exactly one image per request.`
+      );
+    }
     const first = output[0];
     if (typeof first === "string") return first;
   }
@@ -178,13 +588,14 @@ export async function generateImage(
   if (!apiToken) throw new Error("REPLICATE_API_TOKEN is required. Get one at https://replicate.com/account/api-tokens");
 
   const parsedModel = parseModelId(model);
+  validateArgs(model, args);
 
   const refDataUrls: string[] = [];
   for (const refPath of args.referenceImages) {
     refDataUrls.push(await readImageAsDataUrl(refPath));
   }
 
-  const input = buildInput(prompt, args, refDataUrls);
+  const input = buildInput(model, prompt, args, refDataUrls);
 
   console.log(`Generating image with Replicate (${model})...`);
 

skills/baoyu-imagine/scripts/providers/seedream.test.ts

@@ -25,6 +25,7 @@ function makeArgs(overrides: Partial<CliArgs> = {}): CliArgs {
     size: null,
     quality: null,
     imageSize: null,
+    imageApiDialect: null,
     referenceImages: [],
     n: 1,
     batchFile: null,

skills/baoyu-imagine/scripts/providers/zai.test.ts

@@ -25,6 +25,7 @@ function makeArgs(overrides: Partial<CliArgs> = {}): CliArgs {
     size: null,
     quality: null,
     imageSize: null,
+    imageApiDialect: null,
     referenceImages: [],
     n: 1,
     batchFile: null,

skills/baoyu-imagine/scripts/types.ts

@@ -10,6 +10,7 @@ export type Provider =
   | "seedream"
   | "azure";
 export type Quality = "normal" | "2k";
+export type OpenAIImageApiDialect = "openai-native" | "ratio-metadata";
 
 export type CliArgs = {
   prompt: string | null;
@@ -18,9 +19,12 @@ export type CliArgs = {
   provider: Provider | null;
   model: string | null;
   aspectRatio: string | null;
+  aspectRatioSource?: "cli" | "task" | "config" | null;
   size: string | null;
   quality: Quality | null;
   imageSize: string | null;
+  imageSizeSource?: "cli" | "task" | "config" | null;
+  imageApiDialect: OpenAIImageApiDialect | null;
   referenceImages: string[];
   n: number;
   batchFile: string | null;
@@ -40,6 +44,7 @@ export type BatchTaskInput = {
   size?: string | null;
   quality?: Quality | null;
   imageSize?: "1K" | "2K" | "4K" | null;
+  imageApiDialect?: OpenAIImageApiDialect | null;
   ref?: string[];
   n?: number;
 };
@@ -57,6 +62,7 @@ export type ExtendConfig = {
   default_quality: Quality | null;
   default_aspect_ratio: string | null;
   default_image_size: "1K" | "2K" | "4K" | null;
+  default_image_api_dialect: OpenAIImageApiDialect | null;
   default_model: {
     google: string | null;
     openai: string | null;