Generate or edit images from prompts and up to 14 references, with selectable aspect ratios and sizes up to 4K.
Design & media
图像生成 GPT Image 2
Generate or edit images from prompts and up to five references with configurable size, format, and quality.
What it does
Generate images from text prompts or edit and synthesize visuals using up to five reference images with GPT Image 2. Choose supported dimensions, JPEG/PNG/WebP output, and low, medium, or high quality through the dLazy CLI. Results are returned as hosted image URLs, with dry-run cost estimates and optional asynchronous execution.
When to use it
- Text-to-image asset generation
- Reference-guided image editing
- Multi-image visual synthesis
- Asynchronous image generation workflows
The skill document
图像生成 GPT Image 2
English · 中文
GPT Image 2 model for text-to-image and image editing. Supports generating images from text as well as editing and synthesizing images with reference inputs. GPT Image 2 图像生成与编辑模型。支持文生图,以及通过提供参考图进行图像编辑和合成。
Trigger Keywords
- gpt-image-2
Authentication
All requests require a dLazy API key. The recommended way to authenticate is:
dlazy login
This runs a device-code flow (also works in remote shells) and automatically saves your API key to the local CLI config — no manual copy/paste required.
Alternative: Set the Key Manually
If you already have an API key, you can save it directly:
dlazy auth set YOUR_API_KEY
The CLI saves the key in your user config directory (~/.dlazy/config.json on macOS/Linux, %USERPROFILE%\.dlazy\config.json on Windows), with file permissions restricted to your OS user account. You can also supply the key per-invocation via the DLAZY_API_KEY environment variable.
Getting Your API Key Manually
- Sign in or create an account at dlazy.com
- Go to dlazy.com/dashboard/organization/api-key
- Copy the key shown in the API Key section
Each key is scoped to your dLazy organization and can be rotated or revoked at any time from the same dashboard.
About & Provenance
- CLI source code: github.com/dlazyai/cli
- Maintainer: dlazyai
- npm package:
@dlazy/cli(pinned to1.2.3in this skill's install spec) - Homepage: dlazy.com
You can install on demand without persisting a global binary by running:
npx @dlazy/cli@1.2.3
Or, if you prefer a global install, the skill's metadata.clawdbot.install field declares the exact pinned version (npm install -g @dlazy/cli@1.2.3). Review the GitHub source before installing.
How It Works
This skill is a thin client over the dLazy hosted API. When you invoke it:
- Prompts and parameters you provide are sent to the dLazy API endpoint (
api.dlazy.com) for inference. - Any local file paths you pass to image / video / audio fields are uploaded to dLazy's media storage (
files.dlazy.com) so the model can read them — the same flow as any cloud-based generation API. - Generated output URLs returned by the API are hosted on
files.dlazy.com.
This is the standard SaaS pattern; the skill itself does not access network or filesystem resources beyond what the dLazy CLI already handles. See dlazy.com for the full service terms.
Usage
CRITICAL INSTRUCTION FOR AGENT:
Execute dlazy gpt-image-2 to get the result.
dlazy gpt-image-2 -h
Options:
--prompt [prompt] Prompt
--images [images...] Images [image: url or local path] (max 5)
--size [size] Size [default: auto] (choices: "1024x1024", "1536x1024", "1024x1536", "2048x2048", "2048x1152", "3840x2160", "2160x3840", "auto")
--format [format] Format [default: jpeg] (choices: "jpeg", "png", "webp")
--quality [quality] Quality [default: medium] (choices: "low", "medium", "high")
--dry-run Print payload + cost estimate without calling API
--no-wait Return generateId immediately for async tasks
--timeout Max seconds to wait for async completion (default: "1800")
-h, --help display help for command
Any flag also accepts pipe references —
-(auto-pick from upstream stdin),@N(n-th output),@N.path(jsonpath into output),@*(all primary values),@stdin/@stdin:path(whole envelope). Seedlazy --helpfor details.
Output Format
{
"ok": true,
"result": {
"tool": "gpt-image-2",
"modelId": "gpt-image-2",
"outputs": [
{
"type": "image",
"id": "o_xxxxxxxx",
"url": "https://files.dlazy.com/result.png",
"mimeType": "image/png"
}
]
}
}
Async tasks (when
--no-waitis passed) returnoutputs: []and atask: { generateId, status }field instead. Usedlazy status --waitto poll.
Examples
dlazy gpt-image-2 --prompt 'prompt content'
Error Handling
| Code | Error Type | Example Message |
|---|---|---|
| 401 | Unauthorized (No API Key) | ok: false, code: "unauthorized", message: "API key is missing or invalid" |
| 501 | Missing required parameter | error: required option '--prompt ' not specified |
| 502 | Local file read error | Error: Image file/Video file not found: C:\path\to\your\file |
| 503 | API request failed (no balance) | ok: false, code: "insufficient_balance" |
| 503 | API request failed (server error) | HTTP status code error (500 server crash) |
| 504 | Asynchronous task execution failed | === Generation Failed === / {Specific error reason returned by backend, for example "Prompt violates safety policy"} |
AGENT CRITICAL INSTRUCTION:
- If the execution result returns
code: "insufficient_balance", you MUST explicitly inform the user that their credits are insufficient and guide them to recharge: https://dlazy.com/dashboard/organization/settings?tab=credits- If the execution result returns
code: "unauthorized"or indicates missing API key, you MUST inform the user to get their API key from https://dlazy.com/dashboard/organization/api-key and save it usingdlazy auth setand resume the task.
Tips
Visit https://dlazy.com for more information.
Questions people ask
- Can I provide reference images for editing or synthesis?
- Yes. The `--images` option accepts up to five image URLs or local file paths alongside the prompt.
- Which output settings can I control?
- You can select a listed size or use auto sizing, choose JPEG, PNG, or WebP, and set quality to low, medium, or high.
- What authentication and execution options are required?
- Requests require a dLazy API key, saved through `dlazy login`, `dlazy auth set`, or supplied with `DLAZY_API_KEY`. The CLI also supports dry runs, immediate async task IDs with `--no-wait`, and polling for completion.
Related skills
Generate Vidu Q2 images from prompts and references at configurable aspect ratios and resolutions.
Generate, edit, upscale, segment, replicate, or vectorize images with prompt-based model selection.
Generate single images or parallel batches from prompts and references across multiple image APIs.
Turn text prompts and optional reference images into hosted Jimeng image outputs.
Generate Wan 2.7 videos from text, reference media, or specified first and last frames.