mirror of
https://github.com/JimLiu/baoyu-skills.git
synced 2026-07-12 22:09:48 +08:00
Compare commits
3 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 Jim Liu 宝玉
|
ea8ad82786 | ||
|
Jim Liu 宝玉
|
6fffe252c0 | ||
|
Jim Liu 宝玉
|
86a84739e8 |
@@ -6,7 +6,7 @@
|
||||
},
|
||||
"metadata": {
|
||||
"description": "Skills shared by Baoyu for improving daily work efficiency",
|
||||
"version": "1.30.0"
|
||||
"version": "1.30.1"
|
||||
},
|
||||
"plugins": [
|
||||
{
|
||||
|
||||
@@ -2,6 +2,15 @@
|
||||
|
||||
English | [中文](./CHANGELOG.zh.md)
|
||||
|
||||
## 1.30.1 - 2026-02-06
|
||||
|
||||
### Features
|
||||
- `baoyu-image-gen`: add OpenAI GPT Image edits support for reference images (`--ref`); auto-select Google or OpenAI when ref provided.
|
||||
|
||||
### Fixes
|
||||
- `baoyu-image-gen`: change ref-related warnings to explicit errors with fix hints; add reference image validation.
|
||||
- `baoyu-cover-image`: enhance reference image analysis with deep extraction template; require MUST INCORPORATE section for concrete visual elements.
|
||||
|
||||
## 1.30.0 - 2026-02-06
|
||||
|
||||
### Features
|
||||
|
||||
@@ -2,6 +2,15 @@
|
||||
|
||||
[English](./CHANGELOG.md) | 中文
|
||||
|
||||
## 1.30.1 - 2026-02-06
|
||||
|
||||
### 新功能
|
||||
- `baoyu-image-gen`：新增 OpenAI GPT Image edits 支持参考图片（`--ref`）；提供 ref 时自动选择 Google 或 OpenAI。
|
||||
|
||||
### 修复
|
||||
- `baoyu-image-gen`：将 ref 相关警告改为明确错误提示；新增参考图片验证。
|
||||
- `baoyu-cover-image`：增强参考图片分析，使用深度提取模板；要求 MUST INCORPORATE 章节以包含具体可复现的视觉元素。
|
||||
|
||||
## 1.30.0 - 2026-02-06
|
||||
|
||||
### 新功能
|
||||
|
||||
@@ -317,16 +317,23 @@ Reference Style Extracted (no file):
|
||||
- Identify visual metaphors
|
||||
- Detect content type
|
||||
|
||||
**1.3 Reference Image Analysis** (if provided in Step 1.0)
|
||||
**1.3 Reference Image Deep Analysis** ⚠️ CRITICAL (if provided in Step 1.0)
|
||||
|
||||
For each reference image:
|
||||
References are high-priority inputs. Perform deep visual analysis to extract **specific, concrete, reproducible** elements — not vague summaries.
|
||||
|
||||
| Analysis | Description |
|
||||
|----------|-------------|
|
||||
| Visual characteristics | Style, colors, composition |
|
||||
| Content/subject | What the reference depicts |
|
||||
| Style match | Which type/palette/rendering align |
|
||||
| Usage recommendation | `direct` / `style` / `palette` |
|
||||
For each reference image, extract ALL of the following:
|
||||
|
||||
| Analysis | Description | Example (good vs bad) |
|
||||
|----------|-------------|----------------------|
|
||||
| **Brand elements** | Logos, wordmarks, specific typography treatments | Good: "Logo uses vertical parallel lines for 'm'" / Bad: "Has a logo" |
|
||||
| **Signature patterns** | Unique decorative motifs, textures, geometric patterns | Good: "Woven intersecting curves forming diamond grid" / Bad: "Has patterns" |
|
||||
| **Color palette** | Exact hex values or close approximations for key colors | Good: "#2D4A3E dark teal, #F5F0E0 cream" / Bad: "Dark and light colors" |
|
||||
| **Layout structure** | Specific spatial arrangement, banner placement, zone splits | Good: "Bottom 30% dark banner with branding" / Bad: "Has a banner" |
|
||||
| **Typography** | Font style, weight, spacing, case, positioning | Good: "Uppercase, wide letter-spacing, handwritten ep number" / Bad: "Has text" |
|
||||
| **Content/subject** | What the reference depicts | Factual description |
|
||||
| **Usage recommendation** | `direct` / `style` / `palette` | Based on analysis |
|
||||
|
||||
**Output format**: List each element as a bullet point that can be directly copy-pasted into a prompt as a mandatory instruction.
|
||||
|
||||
**1.4 Language Detection**
|
||||
- Detect source language
|
||||
@@ -380,10 +387,15 @@ references:
|
||||
|
||||
| Situation | Frontmatter | Body |
|
||||
|-----------|-------------|------|
|
||||
| Reference file saved to `refs/` | Add to `references` ✓ | Brief style note |
|
||||
| Reference file saved to `refs/` | Add to `references` ✓ | **Detailed mandatory style instructions** (see below) |
|
||||
| Style extracted verbally (no file) | Omit `references` | Full style description |
|
||||
| File in frontmatter but doesn't exist | ERROR - fix or remove | — |
|
||||
|
||||
⚠️ **"Brief style note" is NOT sufficient.** When references are provided, the prompt body MUST contain a dedicated `# Reference Style — MUST INCORPORATE` section with:
|
||||
1. Per-reference breakdown of **specific visual elements** extracted in Step 1.3
|
||||
2. Each element prefixed with "MUST" or "REQUIRED"
|
||||
3. An **integration approach** describing exactly how reference elements should be composed into the cover layout (e.g., "Use a split layout: illustration area 65% + dark branded banner 35%")
|
||||
|
||||
### Step 4: Generate Image
|
||||
|
||||
**4.1 Backup existing** `cover.png` → `cover-backup-YYYYMMDD-HHMMSS.png` (if regenerating)
|
||||
@@ -421,8 +433,8 @@ references:
|
||||
|
||||
| Skill Supports `--ref` | Action |
|
||||
|------------------------|--------|
|
||||
| Yes (e.g., baoyu-image-gen with Google) | Pass reference images via `--ref` |
|
||||
| No | Convert to text description, append to prompt |
|
||||
| Yes (e.g., baoyu-image-gen with Google/OpenAI) | Pass reference images via `--ref` |
|
||||
| No | If usage is `direct`, switch to a ref-capable backend (baoyu-image-gen + Google multimodal or OpenAI GPT Image edits). If unavailable, convert to text description and remove direct refs |
|
||||
|
||||
**Verification**: Before generating, confirm reference processing:
|
||||
```
|
||||
@@ -434,7 +446,7 @@ Reference Processing:
|
||||
**4.4 Generate**
|
||||
|
||||
1. Call selected skill with prompt file path, output path (`cover.png`), aspect ratio
|
||||
2. If references with `direct` usage AND skill supports `--ref`: include `--ref` parameter
|
||||
2. If references with `direct` usage: use ref-capable backend and include `--ref` (recommend `baoyu-image-gen --provider google --model gemini-3-pro-image-preview` or `--provider openai --model gpt-image-1.5`)
|
||||
3. On failure: auto-retry once before reporting error
|
||||
|
||||
### Step 5: Completion Report
|
||||
@@ -483,6 +495,15 @@ All modifications automatically backup existing `cover.png` before regenerating.
|
||||
- `--no-title` is alias for `--text none`
|
||||
- `--style` presets are backward-compatible; explicit `--palette`/`--rendering` override preset values
|
||||
|
||||
### Reference Image Priority ⚠️
|
||||
|
||||
When user provides reference images, they are **HIGH PRIORITY** and MUST strongly influence the generated cover:
|
||||
|
||||
- **References override defaults**: If reference images conflict with preferred palette/rendering, the reference visual identity takes precedence in the prompt
|
||||
- **Concrete > abstract**: Extract specific, reproducible visual elements (exact patterns, logo treatments, color hex values, layout structures) — not vague descriptions like "clean style"
|
||||
- **Mandatory language**: Use "MUST", "REQUIRED", "CRITICAL" in the prompt for reference elements — generic "follow the style" is insufficient for image generation models
|
||||
- **Visible in output**: After generation, verify that reference elements are actually present in the cover. If not, strengthen the prompt and regenerate
|
||||
|
||||
### Composition Principles
|
||||
|
||||
- **Generous whitespace**: 40-60% breathing room; avoid cluttered layouts
|
||||
|
||||
@@ -68,9 +68,15 @@ Palette notes: [key characteristics from palette definition]
|
||||
|
||||
[Watermark section if enabled]
|
||||
|
||||
[Reference images section if provided — see below]
|
||||
[Reference images section if provided — REQUIRED, see below]
|
||||
```
|
||||
|
||||
## Reference-Driven Design ⚠️ HIGH PRIORITY
|
||||
|
||||
When reference images are provided, they are the **primary visual input** and MUST strongly influence the output. The cover should look like it belongs to the same visual family as the references.
|
||||
|
||||
**Passing `--ref` alone is NOT enough.** Image generation models often ignore reference images unless the prompt text explicitly describes what to reproduce. Always combine `--ref` with detailed textual instructions.
|
||||
|
||||
## Content-Driven Design
|
||||
|
||||
- Article title and summary inform the visual metaphor choice
|
||||
@@ -175,63 +181,67 @@ For each reference image, extract:
|
||||
- **Color mood**: Palette characteristics (without specific colors)
|
||||
- **Elements**: Key visual elements and symbols used
|
||||
|
||||
### Step 2: Embed in Prompt
|
||||
### Step 2: Embed in Prompt ⚠️ CRITICAL
|
||||
|
||||
**If file saved AND skill supports `--ref`** (e.g., baoyu-image-gen with Google):
|
||||
- Pass ref images directly via `--ref` parameter
|
||||
- Add brief style note in prompt:
|
||||
**Passing `--ref` alone is NOT enough.** Image generation models frequently ignore reference images unless the prompt text explicitly and forcefully describes what to reproduce. You MUST always write detailed textual instructions regardless of whether `--ref` is used.
|
||||
|
||||
**If file saved (with or without `--ref` support)**:
|
||||
- Pass ref images via `--ref` parameter if skill supports it
|
||||
- **ALWAYS** add a detailed mandatory section in the prompt body:
|
||||
|
||||
```
|
||||
# Reference Style
|
||||
Follow the visual style of the attached reference image(s):
|
||||
- [1-2 sentence style summary from analysis]
|
||||
# Reference Style — MUST INCORPORATE
|
||||
|
||||
CRITICAL: The generated cover MUST visually reference the provided images. The cover must feel like it belongs to the same visual family.
|
||||
|
||||
## From Ref 1 ([filename]) — REQUIRED elements:
|
||||
- [Brand element]: [Specific description of logo/wordmark treatment, e.g., "The logo uses vertical parallel lines (|||) for the letter 'm'. Reproduce this exact treatment."]
|
||||
- [Signature pattern]: [Specific description, e.g., "Woven intersecting curves forming a diamond/lozenge grid pattern. This MUST appear prominently as a banner, border, or background section."]
|
||||
- [Colors]: [Exact hex values, e.g., "Dark teal #2D4A3E background, cream #F5F0E0 text"]
|
||||
- [Typography]: [Specific treatment, e.g., "Uppercase text with wide letter-spacing"]
|
||||
- [Layout element]: [Specific spatial element, e.g., "Bottom banner strip in dark color"]
|
||||
|
||||
## From Ref 2 ([filename]) — REQUIRED elements:
|
||||
[Same detailed breakdown]
|
||||
|
||||
## Integration approach:
|
||||
[Specific layout instruction describing how reference elements combine with the cover content, e.g., "Use a SPLIT LAYOUT: main illustration area (warm cream background) occupies ~65% of the image, while a dark teal BANNER STRIP (with the woven line pattern from Ref 2) runs along the bottom ~35%, containing branding elements from Ref 1."]
|
||||
```
|
||||
|
||||
**If file saved BUT skill does NOT support `--ref`**:
|
||||
- Embed detailed text description in prompt:
|
||||
|
||||
```
|
||||
# Reference Style (Text Description)
|
||||
Emulate the following visual style from reference image(s):
|
||||
|
||||
Reference 1: [filename]
|
||||
- Style: [detailed rendering technique description]
|
||||
- Composition: [layout and hierarchy description]
|
||||
- Elements: [key visual elements used]
|
||||
- Mood: [emotional tone and visual weight]
|
||||
|
||||
[Repeat for additional references]
|
||||
|
||||
Apply these style characteristics to the cover design while maintaining the specified Type, Palette, and Rendering dimensions.
|
||||
```
|
||||
**Key rules**:
|
||||
- Each visual element gets its own bullet with "MUST" or "REQUIRED"
|
||||
- Descriptions must be **specific enough to reproduce** — not vague ("clean style")
|
||||
- The integration approach must describe **exact spatial arrangement**
|
||||
- After generation, verify reference elements are visible; if not, strengthen and regenerate
|
||||
|
||||
**If style/palette extracted verbally (NO file saved)**:
|
||||
- DO NOT add references metadata to prompt
|
||||
- Append extracted info directly to prompt body:
|
||||
- Append extracted info directly to prompt body using the same MUST INCORPORATE format above:
|
||||
|
||||
```
|
||||
# Extracted Style (from reference)
|
||||
# Reference Style — MUST INCORPORATE (extracted from visual analysis)
|
||||
|
||||
COLORS (from reference):
|
||||
- Primary: #E8756D coral
|
||||
- Secondary: #7ECFC0 mint
|
||||
...
|
||||
CRITICAL: Apply these specific visual elements extracted from the reference images.
|
||||
|
||||
STYLE (from reference):
|
||||
- Clean lines, minimal shadows
|
||||
- Gradient backgrounds
|
||||
- Flat vector icons
|
||||
...
|
||||
## REQUIRED elements:
|
||||
- [Same detailed bullet format as above]
|
||||
|
||||
## Integration approach:
|
||||
[Same spatial layout instruction]
|
||||
```
|
||||
|
||||
### Reference Analysis Template
|
||||
|
||||
Use this format when analyzing reference images:
|
||||
Use this format when analyzing reference images. Extract **specific, concrete, reproducible** details — not vague summaries.
|
||||
|
||||
| Aspect | Analysis Points |
|
||||
|--------|-----------------|
|
||||
| **Rendering** | Line quality (clean/sketchy/painted), texture presence, depth treatment |
|
||||
| **Composition** | Element placement, whitespace ratio, visual flow |
|
||||
| **Typography** | Font style, text placement, hierarchy (if present) |
|
||||
| **Elements** | Icon vocabulary, decorative motifs, character style |
|
||||
| **Mood** | Contrast level, saturation, visual weight |
|
||||
| Aspect | Analysis Points | Good Example | Bad Example |
|
||||
|--------|-----------------|--------------|-------------|
|
||||
| **Brand elements** | Logos, wordmarks, distinctive typography | "Logo 'm' formed by 3 vertical lines" | "Has a logo" |
|
||||
| **Signature patterns** | Unique motifs, textures, geometric patterns | "Woven curves forming diamond grid" | "Has patterns" |
|
||||
| **Colors** | Exact hex values or close approximations | "#2D4A3E dark teal, #F5F0E0 cream" | "Dark and light" |
|
||||
| **Layout** | Spatial zones, banner placement, proportions | "Bottom 30% is dark banner with branding" | "Has a banner" |
|
||||
| **Typography** | Font style, weight, case, spacing, position | "Uppercase, wide letter-spacing, right-aligned" | "Has text" |
|
||||
| **Rendering** | Line quality, texture, depth treatment | "Topographic contour lines as background texture" | "Clean style" |
|
||||
| **Elements** | Icon vocabulary, decorative motifs | "Geometric intersecting line ornaments at corners" | "Has decorations" |
|
||||
|
||||
**Output**: Each extracted element should be written as a **copy-pasteable prompt instruction** prefixed with "MUST" or "REQUIRED".
|
||||
|
||||
@@ -60,9 +60,12 @@ npx -y bun ${SKILL_DIR}/scripts/main.ts --prompt "A cat" --image out.png --quali
|
||||
# From prompt files
|
||||
npx -y bun ${SKILL_DIR}/scripts/main.ts --promptfiles system.md content.md --image out.png
|
||||
|
||||
# With reference images (Google multimodal only)
|
||||
# With reference images (Google multimodal or OpenAI edits)
|
||||
npx -y bun ${SKILL_DIR}/scripts/main.ts --prompt "Make blue" --image out.png --ref source.png
|
||||
|
||||
# With reference images (explicit provider/model)
|
||||
npx -y bun ${SKILL_DIR}/scripts/main.ts --prompt "Make blue" --image out.png --provider google --model gemini-3-pro-image-preview --ref source.png
|
||||
|
||||
# Specific provider
|
||||
npx -y bun ${SKILL_DIR}/scripts/main.ts --prompt "A cat" --image out.png --provider openai
|
||||
|
||||
@@ -78,12 +81,12 @@ npx -y bun ${SKILL_DIR}/scripts/main.ts --prompt "一只可爱的猫" --image ou
|
||||
| `--promptfiles <files...>` | Read prompt from files (concatenated) |
|
||||
| `--image <path>` | Output image path (required) |
|
||||
| `--provider google\|openai\|dashscope` | Force provider (default: google) |
|
||||
| `--model <id>`, `-m` | Model ID |
|
||||
| `--model <id>`, `-m` | Model ID (`--ref` with OpenAI requires GPT Image model, e.g. `gpt-image-1.5`) |
|
||||
| `--ar <ratio>` | Aspect ratio (e.g., `16:9`, `1:1`, `4:3`) |
|
||||
| `--size <WxH>` | Size (e.g., `1024x1024`) |
|
||||
| `--quality normal\|2k` | Quality preset (default: 2k) |
|
||||
| `--imageSize 1K\|2K\|4K` | Image size for Google (default: from quality) |
|
||||
| `--ref <files...>` | Reference images (Google multimodal only) |
|
||||
| `--ref <files...>` | Reference images. Supported by Google multimodal and OpenAI edits (GPT Image models). If provider omitted: Google first, then OpenAI |
|
||||
| `--n <count>` | Number of images |
|
||||
| `--json` | JSON output |
|
||||
|
||||
@@ -105,9 +108,10 @@ npx -y bun ${SKILL_DIR}/scripts/main.ts --prompt "一只可爱的猫" --image ou
|
||||
|
||||
## Provider Selection
|
||||
|
||||
1. `--provider` specified → use it
|
||||
2. Only one API key available → use that provider
|
||||
3. Multiple available → default to Google
|
||||
1. `--ref` provided + no `--provider` → auto-select Google first, then OpenAI
|
||||
2. `--provider` specified → use it (if `--ref`, must be `google` or `openai`)
|
||||
3. Only one API key available → use that provider
|
||||
4. Multiple available → default to Google
|
||||
|
||||
## Quality Presets
|
||||
|
||||
@@ -157,7 +161,7 @@ Supported: `1:1`, `16:9`, `9:16`, `4:3`, `3:4`, `2.35:1`
|
||||
- Missing API key → error with setup instructions
|
||||
- Generation failure → auto-retry once
|
||||
- Invalid aspect ratio → warning, proceed with default
|
||||
- Reference images with non-multimodal model → warning, ignore refs
|
||||
- Reference images with unsupported provider/model → error with fix hint (switch to Google multimodal or OpenAI GPT Image edits)
|
||||
|
||||
## Extension Support
|
||||
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
import path from "node:path";
|
||||
import process from "node:process";
|
||||
import { homedir } from "node:os";
|
||||
import { mkdir, readFile, writeFile } from "node:fs/promises";
|
||||
import { access, mkdir, readFile, writeFile } from "node:fs/promises";
|
||||
import type { CliArgs, Provider, ExtendConfig } from "./types";
|
||||
|
||||
function printUsage(): void {
|
||||
@@ -20,7 +20,7 @@ Options:
|
||||
--size <WxH> Size (e.g., 1024x1024)
|
||||
--quality normal|2k Quality preset (default: 2k)
|
||||
--imageSize 1K|2K|4K Image size for Google (default: from quality)
|
||||
--ref <files...> Reference images (Google multimodal only)
|
||||
--ref <files...> Reference images (Google multimodal or OpenAI edits)
|
||||
--n <count> Number of images (default: 1)
|
||||
--json JSON output
|
||||
-h, --help Show help
|
||||
@@ -323,12 +323,26 @@ function normalizeOutputImagePath(p: string): string {
|
||||
}
|
||||
|
||||
function detectProvider(args: CliArgs): Provider {
|
||||
if (args.referenceImages.length > 0 && args.provider && args.provider !== "google" && args.provider !== "openai") {
|
||||
throw new Error(
|
||||
"Reference images require a ref-capable provider. Use --provider google (Gemini multimodal) or --provider openai (GPT Image edits)."
|
||||
);
|
||||
}
|
||||
|
||||
if (args.provider) return args.provider;
|
||||
|
||||
const hasGoogle = !!(process.env.GOOGLE_API_KEY || process.env.GEMINI_API_KEY);
|
||||
const hasOpenai = !!process.env.OPENAI_API_KEY;
|
||||
const hasDashscope = !!process.env.DASHSCOPE_API_KEY;
|
||||
|
||||
if (args.referenceImages.length > 0) {
|
||||
if (hasGoogle) return "google";
|
||||
if (hasOpenai) return "openai";
|
||||
throw new Error(
|
||||
"Reference images require Google or OpenAI. Set GOOGLE_API_KEY/GEMINI_API_KEY or OPENAI_API_KEY, or remove --ref."
|
||||
);
|
||||
}
|
||||
|
||||
const available = [hasGoogle && "google", hasOpenai && "openai", hasDashscope && "dashscope"].filter(Boolean) as Provider[];
|
||||
|
||||
if (available.length === 1) return available[0]!;
|
||||
@@ -340,11 +354,34 @@ function detectProvider(args: CliArgs): Provider {
|
||||
);
|
||||
}
|
||||
|
||||
async function validateReferenceImages(referenceImages: string[]): Promise<void> {
|
||||
for (const refPath of referenceImages) {
|
||||
const fullPath = path.resolve(refPath);
|
||||
try {
|
||||
await access(fullPath);
|
||||
} catch {
|
||||
throw new Error(`Reference image not found: ${fullPath}`);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
type ProviderModule = {
|
||||
getDefaultModel: () => string;
|
||||
generateImage: (prompt: string, model: string, args: CliArgs) => Promise<Uint8Array>;
|
||||
};
|
||||
|
||||
function isRetryableGenerationError(error: unknown): boolean {
|
||||
const msg = error instanceof Error ? error.message : String(error);
|
||||
const nonRetryableMarkers = [
|
||||
"Reference image",
|
||||
"not supported",
|
||||
"only supported",
|
||||
"No API key found",
|
||||
"is required",
|
||||
];
|
||||
return !nonRetryableMarkers.some((marker) => msg.includes(marker));
|
||||
}
|
||||
|
||||
async function loadProviderModule(provider: Provider): Promise<ProviderModule> {
|
||||
if (provider === "google") {
|
||||
return (await import("./providers/google")) as ProviderModule;
|
||||
@@ -387,6 +424,10 @@ async function main(): Promise<void> {
|
||||
return;
|
||||
}
|
||||
|
||||
if (mergedArgs.referenceImages.length > 0) {
|
||||
await validateReferenceImages(mergedArgs.referenceImages);
|
||||
}
|
||||
|
||||
const provider = detectProvider(mergedArgs);
|
||||
const providerModule = await loadProviderModule(provider);
|
||||
|
||||
@@ -408,7 +449,7 @@ async function main(): Promise<void> {
|
||||
imageData = await providerModule.generateImage(prompt, model, mergedArgs);
|
||||
break;
|
||||
} catch (e) {
|
||||
if (!retried) {
|
||||
if (!retried && isRetryableGenerationError(e)) {
|
||||
retried = true;
|
||||
console.error("Generation failed, retrying...");
|
||||
continue;
|
||||
|
||||
@@ -58,7 +58,9 @@ export async function generateImage(
|
||||
if (!apiKey) throw new Error("DASHSCOPE_API_KEY is required");
|
||||
|
||||
if (args.referenceImages.length > 0) {
|
||||
console.error("Warning: Reference images not yet supported with DashScope, ignoring.");
|
||||
throw new Error(
|
||||
"Reference images are not supported with DashScope provider in baoyu-image-gen. Use --provider google with a Gemini multimodal model."
|
||||
);
|
||||
}
|
||||
|
||||
const size = args.size ? normalizeSize(args.size) : getSizeFromAspectRatio(args.aspectRatio, args.quality);
|
||||
|
||||
@@ -216,13 +216,17 @@ export async function generateImage(
|
||||
): Promise<Uint8Array> {
|
||||
if (isGoogleImagen(model)) {
|
||||
if (args.referenceImages.length > 0) {
|
||||
console.error("Warning: Reference images not supported with Imagen models, ignoring.");
|
||||
throw new Error(
|
||||
"Reference images are not supported with Imagen models. Use gemini-3-pro-image-preview or gemini-3-flash-preview."
|
||||
);
|
||||
}
|
||||
return generateWithImagen(prompt, model, args);
|
||||
}
|
||||
|
||||
if (!isGoogleMultimodal(model) && args.referenceImages.length > 0) {
|
||||
console.error("Warning: Reference images are only supported with Gemini multimodal models.");
|
||||
throw new Error(
|
||||
"Reference images are only supported with Gemini multimodal models. Use gemini-3-pro-image-preview or gemini-3-flash-preview."
|
||||
);
|
||||
}
|
||||
|
||||
return generateWithGemini(prompt, model, args);
|
||||
|
||||
@@ -1,9 +1,13 @@
|
||||
import path from "node:path";
|
||||
import { readFile } from "node:fs/promises";
|
||||
import type { CliArgs } from "../types";
|
||||
|
||||
export function getDefaultModel(): string {
|
||||
return process.env.OPENAI_IMAGE_MODEL || "gpt-image-1.5";
|
||||
}
|
||||
|
||||
type OpenAIImageResponse = { data: Array<{ url?: string; b64_json?: string }> };
|
||||
|
||||
function parseAspectRatio(ar: string): { width: number; height: number } | null {
|
||||
const match = ar.match(/^(\d+(?:\.\d+)?):(\d+(?:\.\d+)?)$/);
|
||||
if (!match) return null;
|
||||
@@ -66,20 +70,32 @@ export async function generateImage(
|
||||
|
||||
if (!apiKey) throw new Error("OPENAI_API_KEY is required");
|
||||
|
||||
if (args.referenceImages.length > 0) {
|
||||
console.error("Warning: Reference images not supported with OpenAI, ignoring.");
|
||||
}
|
||||
|
||||
const size = args.size || getOpenAISize(model, args.aspectRatio, args.quality);
|
||||
|
||||
const body: Record<string, any> = {
|
||||
model,
|
||||
prompt,
|
||||
size,
|
||||
};
|
||||
if (args.referenceImages.length > 0) {
|
||||
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)."
|
||||
);
|
||||
}
|
||||
return generateWithOpenAIEdits(baseURL, apiKey, prompt, model, size, args.referenceImages, args.quality);
|
||||
}
|
||||
|
||||
return generateWithOpenAIGenerations(baseURL, apiKey, prompt, model, size, args.quality);
|
||||
}
|
||||
|
||||
async function generateWithOpenAIGenerations(
|
||||
baseURL: string,
|
||||
apiKey: string,
|
||||
prompt: string,
|
||||
model: string,
|
||||
size: string,
|
||||
quality: CliArgs["quality"]
|
||||
): Promise<Uint8Array> {
|
||||
const body: Record<string, any> = { model, prompt, size };
|
||||
|
||||
if (model.includes("dall-e-3")) {
|
||||
body.quality = args.quality === "2k" ? "hd" : "standard";
|
||||
body.quality = quality === "2k" ? "hd" : "standard";
|
||||
}
|
||||
|
||||
const res = await fetch(`${baseURL}/images/generations`, {
|
||||
@@ -96,7 +112,62 @@ export async function generateImage(
|
||||
throw new Error(`OpenAI API error: ${err}`);
|
||||
}
|
||||
|
||||
const result = (await res.json()) as { data: Array<{ url?: string; b64_json?: string }> };
|
||||
const result = (await res.json()) as OpenAIImageResponse;
|
||||
return extractImageFromResponse(result);
|
||||
}
|
||||
|
||||
async function generateWithOpenAIEdits(
|
||||
baseURL: string,
|
||||
apiKey: string,
|
||||
prompt: string,
|
||||
model: string,
|
||||
size: string,
|
||||
referenceImages: string[],
|
||||
quality: CliArgs["quality"]
|
||||
): Promise<Uint8Array> {
|
||||
const form = new FormData();
|
||||
form.append("model", model);
|
||||
form.append("prompt", prompt);
|
||||
form.append("size", size);
|
||||
|
||||
if (model.includes("gpt-image")) {
|
||||
form.append("quality", quality === "2k" ? "high" : "medium");
|
||||
}
|
||||
|
||||
for (const refPath of referenceImages) {
|
||||
const bytes = await readFile(refPath);
|
||||
const filename = path.basename(refPath);
|
||||
const mimeType = getMimeType(filename);
|
||||
const blob = new Blob([bytes], { type: mimeType });
|
||||
form.append("image[]", blob, filename);
|
||||
}
|
||||
|
||||
const res = await fetch(`${baseURL}/images/edits`, {
|
||||
method: "POST",
|
||||
headers: {
|
||||
Authorization: `Bearer ${apiKey}`,
|
||||
},
|
||||
body: form,
|
||||
});
|
||||
|
||||
if (!res.ok) {
|
||||
const err = await res.text();
|
||||
throw new Error(`OpenAI edits API error: ${err}`);
|
||||
}
|
||||
|
||||
const result = (await res.json()) as OpenAIImageResponse;
|
||||
return extractImageFromResponse(result);
|
||||
}
|
||||
|
||||
function getMimeType(filename: string): string {
|
||||
const ext = path.extname(filename).toLowerCase();
|
||||
if (ext === ".jpg" || ext === ".jpeg") return "image/jpeg";
|
||||
if (ext === ".webp") return "image/webp";
|
||||
if (ext === ".gif") return "image/gif";
|
||||
return "image/png";
|
||||
}
|
||||
|
||||
async function extractImageFromResponse(result: OpenAIImageResponse): Promise<Uint8Array> {
|
||||
const img = result.data[0];
|
||||
|
||||
if (img?.b64_json) {
|
||||
|
||||
Reference in New Issue
Block a user