Your privacy choices

Allow optional cookies for referral attribution, visit analytics, and Google Ads purchase measurement.

gpt-image-2 Image Generation Setup Guide

Learn how to use gpt-image-2 with Cherry Studio, Skills, and scripts.

Recommended approach: If you are a regular user, start with the web app for one-click image generation. Use the image generation endpoint https://api.llm-token.cn/v1/images/generations only when connecting a client or automation tool, and set the model ID to gpt-image-2.

ItemValueDescription
Web apphttps://image2.gpt-agent.cc/The recommended option. Beginners do not need to manage API parameters.
API endpointhttps://api.llm-token.cn/v1/images/generationsFor Cherry Studio, Skills, scripts, and similar tools.
Model IDgpt-image-2Enter the complete ID exactly as shown.
API Keysk-xxxxxxxxUse your own API key.

About timeouts: High-resolution or 4K images may take 70-150 seconds to generate. If a client such as Cherry Studio has a fixed timeout, it may decide that the request failed and retry while the image is still being generated. If this happens, use the web app to avoid duplicate requests.

1. Use the Web App

  1. Open https://image2.gpt-agent.cc/ in your browser.
  2. Click Settings in the upper-right corner and enter your API Key.
  3. Select gpt-image-2 and enter your prompt.
  4. Choose the format, quality, aspect ratio, and number of images as needed, then click Generate.

The GPT Image Playground web interface. A red arrow points to the Settings icon in the upper-right corner. Click this icon to enter your API Key and complete the initial web app setup.The GPT Image Playground web interface. A red arrow points to the Settin…

The gpt-image-2 setup screen in the web app. Key settings such as API URL, API Key, and the gpt-image-2 model are highlighted. The API URL shown is https://gpt - agent .cc/v1. A Reset All Data button appears in the lower-right corner.The gpt-image-2 setup screen in the web app. Key settings such as API UR…

Common parameters include the prompt, format, quality, aspect ratio, and number of images. If you are new to the tool, keep the defaults and change only the prompt and aspect ratio.

The GPT Image Playground interface with an All Experiments menu and a prompt and parameter search box at the top. Red arrows highlight the Generate button and the auto, high, PNG, 1000, auto, and 1 parameter settings.The GPT Image Playground interface with an All Experiments menu and a pr…

The image generation parameter area in GPT Image Playground. Four parameter fields display auto, auto, PNG, and low, with auto and low highlighted to show the default quality and format-related settings.The image generation parameter area in GPT Image Playground. Four parame…

2. Edit an Existing Image

To make a targeted edit, transfer the style, or improve an existing image, upload the original image first. Then clearly describe what to change, what to preserve, and the desired final style.

The GPT Image Playground interface for editing an existing image. A red arrow points to a Click Here area where users enter their editing instructions. The prompt box contains a request for a 500-character short story about a cat, and format, quality, aspect ratio, and image count settings appear below.The GPT Image Playground interface for editing an existing image. A red…

3. Save the Generated Image

After generation finishes, right-click the image to save it or use the download button on the page.

The GPT Image Playground interface at img.codechase.site with Copy, Download, and Edit actions in a dropdown menu. Two generated images are shown with prompts to make one image darker and create a Battle Through the Heavens plugin cover from another image. The auto, medium, PNG, low, and 1 parameter options and a blue Generate button are visible.The GPT Image Playground interface at img.codechase.site with Copy, Down…

4. Configure Cherry Studio

Recommendation: Cherry Studio works well for standard image sizes. For very high-resolution images, use the web app to avoid client timeout retries.

  1. Open Cherry Studio settings.
  2. Add a provider and select the OpenAI-compatible protocol.
  3. Set the API endpoint to https://api.llm-token.cn/v1/images/generations.
  4. Enter your API Key and set the model to gpt-image-2.
  5. Save the configuration, then select this model to generate images.

The Cherry Studio interface. A red arrow points to the Models option in the top navigation, showing where to begin configuring a model.The Cherry Studio interface. A red arrow points to the Models option in…

Cherry Studio settings with a list of model providers on the left and API Key and API URL fields on the right. A red arrow points to the Add button below the provider list.Cherry Studio settings with a list of model providers on the left and AP…

The Add Provider dialog in Cherry Studio. An arrow points to the Provider Name field, the Provider Type menu is set to OpenAI, and Cancel and Confirm buttons appear in the lower-right corner.The Add Provider dialog in Cherry Studio. An arrow points to the Provide…

The Cherry Studio settings screen after adding a provider. The provider is enabled, API Key and API URL fields are visible, and the API URL is set to https://api.llm-token.cn/v1/images/generations.The Cherry Studio settings screen after adding a provider. The provider…

The Cherry Studio interface with a red arrow pointing to the current model selector labeled Queen and CherryAI. Click this area to switch models after saving the configuration.The Cherry Studio interface with a red arrow pointing to the current mod…

The Cherry Studio image selection page after configuration. Provider entries for got-image-2 and Qwen appear in the model list with green check marks.The Cherry Studio image selection page after configuration. Provider ent…

A successful gpt-image-2 generation in Cherry Studio. The selected model is shown as gpt-image-2 with the configured provider, and the prompt asks for a photo of a beautiful woman. The generated image confirms that the setup works.A successful gpt-image-2 generation in Cherry Studio. The selected model…

5. OpenClaw / ClawHub Skill

Quick links: This section includes both the Skill package and the complete guide. Install the Skill for automated image generation, or follow the guide for step-by-step setup. Skill package: guishu-gpt-image-2 is available on ClawHub. Its owner is quqi1599, and the current version is 1.0.0. Install it with clawhub install guishu-gpt-image-2. Guide: gpt-image-2 Image Generation Setup Guide. Regular users should start with the web app and Cherry Studio sections. Agent / OpenClaw users can go directly to this section. Web app: https://image2.gpt-agent.cc/ is suitable for beginners and high-resolution image generation, and avoids repeated retries caused by client timeouts.

clawhub install guishu-gpt-image-2

export LLM_TOKEN_API_KEY="sk-xxxxxxxx"

python3 ~/.openclaw/workspace/skills/guishu-gpt-image-2/scripts/generate.py \
  --prompt "一位韩系女团风格的年轻女孩，凌乱但时髦的长发，穿着牛仔外套和休闲服饰，纵向构图，背景虚化，超写实原片质感，自然光照明" \
  --size 1024x1792 \
  --quality high \
  --n 1
ItemDescription
Skill packageguishu-gpt-image-2. Install it from ClawHub with clawhub install guishu-gpt-image-2.
Complete guidegpt-image-2 Image Generation Setup Guide, covering the web app, Cherry Studio, and OpenClaw / ClawHub usage.
Web apphttps://image2.gpt-agent.cc/, recommended for beginners and high-resolution images.
LLM_TOKEN_API_KEYEnter your own API Key. The script also supports GUI_SHU_TOKEN_KEY and OPENAI_API_KEY.
endpointUses https://api.llm-token.cn/v1/images/generations by default.
modelFixed to gpt-image-2 by default.
promptThe image prompt. Describe the subject, style, composition, lighting, camera treatment, and intended use clearly.
sizeThe image dimensions, such as 1024x1024 or 1024x1792.
response_formatUses b64_json by default so the script can save the image directly to a local file.
Test resultA real API call was completed successfully on 2026-06-22, generating a local PNG image and HTML gallery.

Hermes Deployment Guide

Set up Hermes for terminal AI Agent workflows, including installation, model configuration, and troubleshooting.

WorkBuddy Setup Guide

Connect a custom model with the three essentials: Base URL, API Key, and model ID.

Sections on this page

1. Use the Web App2. Edit an Existing Image3. Save the Generated Image4. Configure Cherry Studio5. OpenClaw / ClawHub Skill