seahi/baoyu-skills
1
0
Fork 0
mirror of https://github.com/JimLiu/baoyu-skills.git synced 2026-07-09 20:51:22 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(baoyu-image-gen): default to GA Gemini image endpoints and sync docs

Browse Source
This commit is contained in:
hypn4
2026-05-29 12:35:28 +09:00
parent d3d1a9f7cd
commit d79ebe4838
11 changed files with 35 additions and 32 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+5 -5
View File
@@ -750,7 +750,7 @@ AI SDK-based image generation using OpenAI GPT Image 2, Azure OpenAI, Google, Op
/baoyu-image-gen --prompt "A cat" --image cat.png --provider openrouter
# OpenRouter with reference images
/baoyu-image-gen --prompt "Make it blue" --image out.png --provider openrouter --model google/gemini-3.1-flash-image-preview --ref source.png
/baoyu-image-gen --prompt "Make it blue" --image out.png --provider openrouter --model google/gemini-3.1-flash-image --ref source.png
# DashScope (Aliyun Tongyi Wanxiang)
/baoyu-image-gen --prompt "一只可爱的猫" --image cat.png --provider dashscope
@@ -827,8 +827,8 @@ AI SDK-based image generation using OpenAI GPT Image 2, Azure OpenAI, Google, Op
| `OPENAI_IMAGE_MODEL` | OpenAI model | `gpt-image-2` |
| `AZURE_OPENAI_DEPLOYMENT` | Azure default deployment name | - |
| `AZURE_OPENAI_IMAGE_MODEL` | Backward-compatible Azure deployment/model alias | `gpt-image-2` |
| `OPENROUTER_IMAGE_MODEL` | OpenRouter model | `google/gemini-3.1-flash-image-preview` |
| `GOOGLE_IMAGE_MODEL` | Google model | `gemini-3-pro-image-preview` |
| `OPENROUTER_IMAGE_MODEL` | OpenRouter model | `google/gemini-3.1-flash-image` |
| `GOOGLE_IMAGE_MODEL` | Google model | `gemini-3-pro-image` |
| `DASHSCOPE_IMAGE_MODEL` | DashScope model | `qwen-image-2.0-pro` |
| `ZAI_IMAGE_MODEL` | Z.AI model | `glm-image` |
| `BIGMODEL_IMAGE_MODEL` | Backward-compatible alias for Z.AI model | `glm-image` |
@@ -1225,14 +1225,14 @@ AZURE_OPENAI_DEPLOYMENT=gpt-image-2
# OpenRouter
OPENROUTER_API_KEY=sk-or-xxx
OPENROUTER_IMAGE_MODEL=google/gemini-3.1-flash-image-preview
OPENROUTER_IMAGE_MODEL=google/gemini-3.1-flash-image
# OPENROUTER_BASE_URL=https://openrouter.ai/api/v1
# OPENROUTER_HTTP_REFERER=https://your-app.example.com
# OPENROUTER_TITLE=Your App Name
# Google
GOOGLE_API_KEY=xxx
GOOGLE_IMAGE_MODEL=gemini-3-pro-image-preview
GOOGLE_IMAGE_MODEL=gemini-3-pro-image
# GOOGLE_BASE_URL=https://generativelanguage.googleapis.com/v1beta
# DashScope (Aliyun Tongyi Wanxiang)
README.zh.md
+5 -5
View File
@@ -741,7 +741,7 @@ AI 驱动的生成后端。
/baoyu-image-gen --prompt "一只猫" --image cat.png --provider openrouter
# OpenRouter + 参考图
/baoyu-image-gen --prompt "把它变成蓝色" --image out.png --provider openrouter --model google/gemini-3.1-flash-image-preview --ref source.png
/baoyu-image-gen --prompt "把它变成蓝色" --image out.png --provider openrouter --model google/gemini-3.1-flash-image --ref source.png
# DashScope（阿里通义万相）
/baoyu-image-gen --prompt "一只可爱的猫" --image cat.png --provider dashscope
@@ -818,8 +818,8 @@ AI 驱动的生成后端。
| `OPENAI_IMAGE_MODEL` | OpenAI 模型 | `gpt-image-2` |
| `AZURE_OPENAI_DEPLOYMENT` | Azure 默认部署名 | - |
| `AZURE_OPENAI_IMAGE_MODEL` | 兼容旧配置的 Azure 部署/模型别名 | `gpt-image-2` |
| `OPENROUTER_IMAGE_MODEL` | OpenRouter 模型 | `google/gemini-3.1-flash-image-preview` |
| `GOOGLE_IMAGE_MODEL` | Google 模型 | `gemini-3-pro-image-preview` |
| `OPENROUTER_IMAGE_MODEL` | OpenRouter 模型 | `google/gemini-3.1-flash-image` |
| `GOOGLE_IMAGE_MODEL` | Google 模型 | `gemini-3-pro-image` |
| `DASHSCOPE_IMAGE_MODEL` | DashScope 模型 | `qwen-image-2.0-pro` |
| `ZAI_IMAGE_MODEL` | Z.AI 模型 | `glm-image` |
| `BIGMODEL_IMAGE_MODEL` | Z.AI 模型向后兼容别名 | `glm-image` |
@@ -1216,14 +1216,14 @@ AZURE_OPENAI_DEPLOYMENT=gpt-image-2
# OpenRouter
OPENROUTER_API_KEY=sk-or-xxx
OPENROUTER_IMAGE_MODEL=google/gemini-3.1-flash-image-preview
OPENROUTER_IMAGE_MODEL=google/gemini-3.1-flash-image
# OPENROUTER_BASE_URL=https://openrouter.ai/api/v1
# OPENROUTER_HTTP_REFERER=https://your-app.example.com
# OPENROUTER_TITLE=你的应用名
# Google
GOOGLE_API_KEY=xxx
GOOGLE_IMAGE_MODEL=gemini-3-pro-image-preview
GOOGLE_IMAGE_MODEL=gemini-3-pro-image
# GOOGLE_BASE_URL=https://generativelanguage.googleapis.com/v1beta
# DashScope（阿里通义万相）
skills/baoyu-image-gen/SKILL.md
+1 -1
View File
@@ -179,7 +179,7 @@ For OpenAI, the built-in default is `gpt-image-2`. `gpt-image-1.5`, `gpt-image-1
For Azure, `--model` / `default_model.azure` is the Azure deployment name. `AZURE_OPENAI_DEPLOYMENT` is the preferred env var; `AZURE_OPENAI_IMAGE_MODEL` is kept as a backward-compatible alias. If your Azure deployment is named after the underlying model, use `gpt-image-2`; otherwise use the exact custom deployment name.
EXTEND.md overrides env vars: if EXTEND.md sets `default_model.google: "gemini-3-pro-image-preview"` and the env var sets `GOOGLE_IMAGE_MODEL=gemini-3.1-flash-image-preview`, EXTEND.md wins.
EXTEND.md overrides env vars: if EXTEND.md sets `default_model.google: "gemini-3-pro-image"` and the env var sets `GOOGLE_IMAGE_MODEL=gemini-3.1-flash-image`, EXTEND.md wins.
**Display model info before each generation**:
skills/baoyu-image-gen/references/config/first-time-setup.md
+6 -6
View File
@@ -69,9 +69,9 @@ Only show if user selected Google or auto-detect (no explicit provider).
header: "Google Model"
question: "Default Google image generation model?"
options:
- label: "gemini-3-pro-image-preview (Recommended)"
- label: "gemini-3-pro-image (Recommended)"
description: "Highest quality, best for production use"
- label: "gemini-3.1-flash-image-preview"
- label: "gemini-3.1-flash-image"
description: "Fast generation, good quality, lower cost"
- label: "gemini-3-flash-preview"
description: "Fast generation, balanced quality and speed"
@@ -85,7 +85,7 @@ Only show if user selected OpenRouter.
header: "OpenRouter Model"
question: "Default OpenRouter image generation model?"
options:
- label: "google/gemini-3.1-flash-image-preview (Recommended)"
- label: "google/gemini-3.1-flash-image (Recommended)"
description: "Best general-purpose OpenRouter image model with reference-image workflows"
- label: "google/gemini-2.5-flash-image-preview"
description: "Fast Gemini preview model on OpenRouter"
@@ -202,9 +202,9 @@ When EXTEND.md exists but `default_model.[current_provider]` is null, ask ONLY t
header: "Google Model"
question: "Choose a default Google image generation model?"
options:
- label: "gemini-3-pro-image-preview (Recommended)"
- label: "gemini-3-pro-image (Recommended)"
description: "Highest quality, best for production use"
- label: "gemini-3.1-flash-image-preview"
- label: "gemini-3.1-flash-image"
description: "Fast generation, good quality, lower cost"
- label: "gemini-3-flash-preview"
description: "Fast generation, balanced quality and speed"
@@ -249,7 +249,7 @@ Notes for Azure setup:
header: "OpenRouter Model"
question: "Choose a default OpenRouter image generation model?"
options:
- label: "google/gemini-3.1-flash-image-preview (Recommended)"
- label: "google/gemini-3.1-flash-image (Recommended)"
description: "Recommended for image output and reference-image edits"
- label: "google/gemini-2.5-flash-image-preview"
description: "Fast preview-oriented image generation"
skills/baoyu-image-gen/references/config/preferences-schema.md
+4 -4
View File
@@ -22,10 +22,10 @@ default_image_size: null # 1K|2K|4K|null (Google/OpenRouter, overrides qualit
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"
google: null # e.g., "gemini-3-pro-image", "gemini-3.1-flash-image"
openai: null # e.g., "gpt-image-2", "gpt-image-1.5", "gpt-image-1"
azure: null # Azure deployment name, e.g., "gpt-image-2" or "image-prod"
openrouter: null # e.g., "google/gemini-3.1-flash-image-preview"
openrouter: null # e.g., "google/gemini-3.1-flash-image"
dashscope: null # e.g., "qwen-image-2.0-pro"
zai: null # e.g., "glm-image"
minimax: null # e.g., "image-01"
@@ -110,10 +110,10 @@ default_aspect_ratio: "16:9"
default_image_size: 2K
default_image_api_dialect: null
default_model:
google: "gemini-3-pro-image-preview"
google: "gemini-3-pro-image"
openai: "gpt-image-2"
azure: "gpt-image-2"
openrouter: "google/gemini-3.1-flash-image-preview"
openrouter: "google/gemini-3.1-flash-image"
dashscope: "qwen-image-2.0-pro"
zai: "glm-image"
minimax: "image-01"
skills/baoyu-image-gen/references/providers/openrouter.md
+2 -2
View File
@@ -1,12 +1,12 @@
# OpenRouter
Read when the user picks `--provider openrouter`. Default model is `google/gemini-3.1-flash-image-preview`.
Read when the user picks `--provider openrouter`. Default model is `google/gemini-3.1-flash-image`.
## Common Models
Use full OpenRouter model IDs:
- `google/gemini-3.1-flash-image-preview` (recommended — supports image output and reference-image workflows)
- `google/gemini-3.1-flash-image` (recommended — supports image output and reference-image workflows)
- `google/gemini-2.5-flash-image-preview`
- `black-forest-labs/flux.2-pro`
- Any other OpenRouter image-capable model ID
skills/baoyu-image-gen/references/usage-examples.md
+2 -2
View File
@@ -34,13 +34,13 @@ ${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider a
${BUN_X} {baseDir}/scripts/main.ts --prompt "A cinematic landscape" --image out.png --provider openai --model gpt-image-2 --size 3840x2160
# Google with explicit model
${BUN_X} {baseDir}/scripts/main.ts --prompt "Make blue" --image out.png --provider google --model gemini-3-pro-image-preview --ref source.png
${BUN_X} {baseDir}/scripts/main.ts --prompt "Make blue" --image out.png --provider google --model gemini-3-pro-image --ref source.png
# OpenRouter (recommended default)
${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider openrouter
# OpenRouter with reference
${BUN_X} {baseDir}/scripts/main.ts --prompt "Make blue" --image out.png --provider openrouter --model google/gemini-3.1-flash-image-preview --ref source.png
${BUN_X} {baseDir}/scripts/main.ts --prompt "Make blue" --image out.png --provider openrouter --model google/gemini-3.1-flash-image --ref source.png
# DashScope (default model)
${BUN_X} {baseDir}/scripts/main.ts --prompt "一只可爱的猫" --image out.png --provider dashscope
skills/baoyu-image-gen/scripts/main.test.ts
+2 -2
View File
@@ -142,7 +142,7 @@ default_aspect_ratio: '16:9'
default_image_size: 2K
default_image_api_dialect: ratio-metadata
default_model:
google: gemini-3-pro-image-preview
google: gemini-3-pro-image
openai: gpt-image-2
zai: glm-image
azure: image-prod
@@ -174,7 +174,7 @@ batch:
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?.google, "gemini-3-pro-image");
assert.equal(config.default_model?.openai, "gpt-image-2");
assert.equal(config.default_model?.zai, "glm-image");
assert.equal(config.default_model?.azure, "image-prod");
skills/baoyu-image-gen/scripts/main.ts
+2 -2
View File
@@ -126,8 +126,8 @@ Environment variables:
JIMENG_SECRET_ACCESS_KEY Jimeng Secret Access Key
ARK_API_KEY Seedream/Ark API key
OPENAI_IMAGE_MODEL Default OpenAI model (gpt-image-2)
OPENROUTER_IMAGE_MODEL Default OpenRouter model (google/gemini-3.1-flash-image-preview)
GOOGLE_IMAGE_MODEL Default Google model (gemini-3-pro-image-preview)
OPENROUTER_IMAGE_MODEL Default OpenRouter model (google/gemini-3.1-flash-image)
GOOGLE_IMAGE_MODEL Default Google model (gemini-3-pro-image)
DASHSCOPE_IMAGE_MODEL Default DashScope model (qwen-image-2.0-pro)
ZAI_IMAGE_MODEL Default Z.AI model (glm-image)
BIGMODEL_IMAGE_MODEL Backward-compatible alias for Z.AI model (glm-image)
skills/baoyu-image-gen/scripts/providers/google.ts
+1 -1
View File
@@ -16,7 +16,7 @@ const GOOGLE_IMAGEN_MODELS = [
];
export function getDefaultModel(): string {
return process.env.GOOGLE_IMAGE_MODEL || "gemini-3-pro-image-preview";
return process.env.GOOGLE_IMAGE_MODEL || "gemini-3-pro-image";
}
export function normalizeGoogleModelId(model: string): string {
skills/baoyu-image-gen/scripts/providers/openrouter.ts
+5 -2
View File
@@ -2,7 +2,7 @@ import path from "node:path";
import { readFile } from "node:fs/promises";
import type { CliArgs } from "../types";
const DEFAULT_MODEL = "google/gemini-3.1-flash-image-preview";
const DEFAULT_MODEL = "google/gemini-3.1-flash-image";
const COMMON_ASPECT_RATIOS = [
"1:1",
"2:3",
@@ -67,7 +67,10 @@ function isTextAndImageModel(model: string): boolean {
function getSupportedAspectRatios(model: string): Set<string> {
const normalized = normalizeModelId(model);
if (normalized !== "google/gemini-3.1-flash-image-preview") {
if (
normalized !== "google/gemini-3.1-flash-image" &&
normalized !== "google/gemini-3.1-flash-image-preview"
) {
return new Set(COMMON_ASPECT_RATIOS);
}