JimLiu/baoyu-skills / skills/baoyu-image-gen
baoyu-image-gen
VerifiedAI image generation with OpenAI GPT Image 2.5, Azure OpenAI, Google, OpenRouter, DashScope, Z.AI GLM-Image, MiniMax, Jimeng, Seedream, Replicate and Agnes APIs. Supports text-to-image, reference images, aspect ratios, and batch generation from saved prompt files. Sequential by default; use batch parallel generation when the user already has multiple prompts or wants stable multi-image throughput. Use when user asks to generate, create, or draw images.
scripts/providers/azure.ts
View on GitHubimport path from "node:path";
import { readFile } from "node:fs/promises";
import type { CliArgs } from "../types";
import { getOpenAISize, extractImageFromResponse } from "./openai.ts";
type OpenAIImageResponse = { data: Array<{ url?: string; b64_json?: string }> };
type AzureEndpoint = {
resourceBaseURL: string;
deployment: string | null;
};
const DEFAULT_AZURE_API_VERSION = "2025-04-01-preview";
const AZURE_EDIT_IMAGE_EXTENSIONS = new Set([".png", ".jpg", ".jpeg"]);
export function parseAzureBaseURL(url: string): AzureEndpoint {
const parsed = new URL(url);
const trimmedPath = parsed.pathname.replace(/\/+$/, "");
const deploymentMatch = trimmedPath.match(/^(.*?)(?:\/openai)?\/deployments\/([^/]+)$/);
if (deploymentMatch) {
parsed.pathname = `${deploymentMatch[1] || ""}/openai`;
return {
resourceBaseURL: parsed.toString().replace(/\/+$/, ""),
deployment: decodeURIComponent(deploymentMatch[2]!),
};
}
parsed.pathname = trimmedPath.endsWith("/openai") ? trimmedPath : `${trimmedPath}/openai`;
return {
resourceBaseURL: parsed.toString().replace(/\/+$/, ""),
deployment: null,
};
}
export function getDefaultModel(): string {
const explicitDeployment = process.env.AZURE_OPENAI_DEPLOYMENT?.trim();
if (explicitDeployment) return explicitDeployment;
const baseURL = process.env.AZURE_OPENAI_BASE_URL;
if (baseURL) {
try {
const { deployment } = parseAzureBaseURL(baseURL);
if (deployment) return deployment;
} catch {
// Ignore invalid URLs here so the required-env check can raise the user-facing error later.
}
}
return process.env.AZURE_OPENAI_IMAGE_MODEL || "gpt-image-2.5-flare";
}
function getEndpoint(): AzureEndpoint {
const url = process.env.AZURE_OPENAI_BASE_URL;
if (!url) {
throw new Error(
"AZURE_OPENAI_BASE_URL is required. Set it to your Azure resource or deployment endpoint, e.g.: https://your-resource.openai.azure.com or https://your-resource.openai.azure.com/openai/deployments/your-deployment"
);
}
return parseAzureBaseURL(url);
}
function getApiKey(): string {
const key = process.env.AZURE_OPENAI_API_KEY;
if (!key) {
throw new Error(
"AZURE_OPENAI_API_KEY is required. Get it from Azure Portal → your OpenAI resource → Keys and Endpoint."
);
}
return key;
}
function getApiVersion(): string {
return process.env.AZURE_API_VERSION || DEFAULT_AZURE_API_VERSION;
}
function getDeployment(model: string): string {
const deployment = model.trim();
if (!deployment) {
throw new Error(
"Azure deployment name is required. Use --model <deployment>, AZURE_OPENAI_DEPLOYMENT, AZURE_OPENAI_IMAGE_MODEL, or embed the deployment in AZURE_OPENAI_BASE_URL."
);
}
return deployment;
}
function buildURL(deployment: string, pathSuffix: string): string {
const { resourceBaseURL } = getEndpoint();
return `${resourceBaseURL}/deployments/${encodeURIComponent(deployment)}${pathSuffix}?api-version=${getApiVersion()}`;
}
function authHeaders(): Record<string, string> {
return { "api-key": getApiKey() };
}
function getAzureQuality(quality: CliArgs["quality"]): "medium" | "high" {
return quality === "2k" ? "high" : "medium";
}
export function validateArgs(_model: string, args: CliArgs): void {
for (const refPath of args.referenceImages) {
const ext = path.extname(refPath).toLowerCase();
if (!AZURE_EDIT_IMAGE_EXTENSIONS.has(ext)) {
throw new Error(
`Azure OpenAI reference images must be PNG or JPG/JPEG. Unsupported file: ${refPath}`
);
}
}
}
export async function generateImage(
prompt: string,
model: string,
args: CliArgs
): Promise<Uint8Array> {
const deployment = getDeployment(model);
const size = args.size || getOpenAISize(model, args.aspectRatio, args.quality);
if (args.referenceImages.length > 0) {
return generateWithAzureEdits(prompt, deployment, size, args.referenceImages, args.quality);
}
return generateWithAzureGenerations(prompt, deployment, size, args.quality);
}
async function generateWithAzureGenerations(
prompt: string,
deployment: string,
size: string,
quality: CliArgs["quality"]
): Promise<Uint8Array> {
const body: Record<string, any> = {
prompt,
size,
n: 1,
quality: getAzureQuality(quality),
};
const res = await fetch(buildURL(deployment, "/images/generations"), {
method: "POST",
headers: {
"Content-Type": "application/json",
...authHeaders(),
},
body: JSON.stringify(body),
});
if (!res.ok) {
const err = await res.text();
throw new Error(`Azure OpenAI API error: ${err}`);
}
const result = (await res.json()) as OpenAIImageResponse;
return extractImageFromResponse(result);
}
async function generateWithAzureEdits(
prompt: string,
deployment: string,
size: string,
referenceImages: string[],
quality: CliArgs["quality"]
): Promise<Uint8Array> {
const form = new FormData();
form.append("prompt", prompt);
form.append("size", size);
form.append("n", "1");
form.append("quality", getAzureQuality(quality));
for (const refPath of referenceImages) {
const bytes = await readFile(refPath);
const filename = path.basename(refPath);
const mimeType = path.extname(filename).toLowerCase() === ".png" ? "image/png" : "image/jpeg";
const blob = new Blob([bytes], { type: mimeType });
form.append("image[]", blob, filename);
}
const res = await fetch(buildURL(deployment, "/images/edits"), {
method: "POST",
headers: {
...authHeaders(),
},
body: form,
});
if (!res.ok) {
const err = await res.text();
throw new Error(`Azure OpenAI edits API error: ${err}`);
}
const result = (await res.json()) as OpenAIImageResponse;
return extractImageFromResponse(result);
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |