skills.rest
byteplus-sa
byteplus-saOFFICIAL
Explore all skills by this author →
GitHub

polym-eval-generate-gpt-image

Generate or edit images from natural-language prompts via ByteDance AIDP GPT Image endpoints.

8|Updated May 13, 2026
Search Tags:#image generation#image editing#prompting#gpt-image-1#tos upload#byteDance AIDP#masked edits
One-click install
npx skills add https://github.com/byteplus-sa/polym --skill polym-eval-generate-gpt-image
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: polym-eval-generate-gpt-image
Source: https://github.com/byteplus-sa/polym/tree/main/skills/polym-eval-generate-gpt-image
Command: npx skills add https://github.com/byteplus-sa/polym --skill polym-eval-generate-gpt-image

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires Pillow, requests, python-dotenv, tos, and includes scripts (resource) components.

What problem does it solve?

This Skill helps you quickly turn text prompts into images and perform prompt-guided edits on existing images, including targeted masked changes, without manually calling the underlying AIDP endpoints.

Core Features & Use Cases

  • Text-to-image generation: Create new images from prompts using the gpt-image-1 model through ByteDance AIDP.
  • Image editing/compositing: Apply a new prompt to one or more reference images using AIDP’s edits endpoint.
  • Masked edits: Provide a mask image to limit where changes should occur for more precise results (e.g., background replacement or object retouching).
  • Practical use case: Produce multiple variations of a concept image, then refine specific regions (like swapping the sky or dressing a subject) by running edit mode with an input image and an optional mask.

Quick Start

Run the skill in generate mode with your prompt to produce an image.

Frequently Asked Questions about polym-eval-generate-gpt-image

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate images from text prompts using gpt-image-1?▼

To generate images from text prompts, the Skill sends natural-language descriptions to the ByteDance AIDP GPT Image endpoint, producing newly saved image files without manual API calls.

Can I use masked edits to modify specific regions of an existing image?▼

Yes, masked edits are supported by providing a reference image and a mask to the AIDP edits endpoint, limiting prompt-guided changes to targeted areas for precise object retouching or background replacement.

Do I need an AIDP_API_KEY to perform image generation and editing?▼

Yes, an AIDP_API_KEY is required and must be configured in your environment to authenticate text-to-image generation and image-to-image editing requests through the ByteDance AIDP endpoints.

What image output formats and delivery methods does this Skill return?▼

The Skill returns a saved image file locally and optionally provides a presigned TOS URL, allowing you to access and share the generated or edited image output directly.

Can I configure model quality and size when generating multiple image variations?▼

Yes, you can configure model, quality, size, and the number of variations when generating images, enabling production workflows that produce multiple concept iterations from a single prompt.

Related Skills

Explore More Design & Creative Skills→
0xHoneyJar0xHoneyJar
1

loa-credentials

Manage API credentials across environment variables, encrypted stores, and dotenv files.

Official
Intermediate
El3tar-cmdEl3tar-cmd
18

object-storage

Provides web app storage with managed upload and delivery of files and assets via Blazor's built-in UploadFile component.

Community
Advanced
trungdo9trungdo9
3

ai-multimodal

Process and generate multimedia content using the Google Gemini API.

Community
Advanced
byteplus-sabyteplus-sa
8

polym-eval-generate-gemini

Generate PNG images from text prompts using Google Gemini/Imagen or ByteDance AIDP backends.

Official
Intermediate