skills.rest
Logarn
LogarnCOMMUNITY
Explore all skills by this author →
GitHub

image-studio

Generate images from text prompts and edit existing photos with AI models.

1|Updated Mar 30, 2026
Search Tags:#image generation#photo editing#text-to-image#background removal#variants#ai images#watermark removal
One-click install
npx skills add https://github.com/Logarn/Worklin-ai --skill image-studio-logarn
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: image-studio
Source: https://github.com/Logarn/Worklin-ai/tree/main/assistant/src/config/bundled-skills/image-studio
Command: npx skills add https://github.com/Logarn/Worklin-ai --skill image-studio-logarn

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Creating or editing images normally requires design software and manual effort. This Skill lets you generate new images from text descriptions or edit existing photos (background removal, watermark removal, retouching, restyling, in-painting) directly through conversation. ## Core Features & Use Cases - Text-to-Image Generation: Describe style, composition, lighting, and mood to create new images, with up to 4 variants for exploring options. - AI Image Editing: Modify attached photos with instructions like removing watermarks or backgrounds while preserving subject, framing, and lighting. - Model Tier Selection: Choose between fast, quality, or OpenAI model aliases depending on fidelity and edit-permissiveness needs. - Use Case: Attach a product photo and ask to remove the background while keeping the subject and lighting identical, or request three logo concept variations from a single prompt. ## Quick Start Ask the assistant to generate an image of a sunset over the ocean in golden hour 35mm photo style with two variants.

Frequently Asked Questions about image-studio

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

FAQPage Schema
How do I generate an image from a text description?▼

Provide a prompt describing style, composition, lighting, and mood, not just the subject. The media_generate_image tool creates the image using the configured default model, and you can request up to 4 variants for options.

How do I remove a watermark or background from a photo with AI?▼

Attach the photo, then use edit mode with the source image path and a prompt naming the change plus what must stay the same. Preservation language like "keep subject, framing, and lighting identical" prevents the model from drifting on crop and color.

Which image model should I use for editing photos?▼

Use the openai alias for photo edits since it is the most permissive on edit requests. Omit the model parameter for general generation to use the configured default, or use the quality alias for higher fidelity output.

Why did my image edit time out?▼

Edits on large photos take 60-90 seconds per variant and can exceed the tool execution timeout. Retry with variants set to 1, or fall back to the CLI command which writes output files directly to disk.

What should I do when image generation fails?▼

Switch providers once based on the failed model named in the error: retry with the openai model if a gemini model failed, or the quality alias if a gpt model failed. Do not rephrase the prompt and retry on the same model.

Related Skills

Explore More Design & Creative Skills→
open-octoopen-octo
88

image-gen

Generate, source, or slice image files via AI providers and licensed services.

Official
Advanced
renatoasserenatoasse
2.0k

image-ai-generator

Generate branded AI images from text prompts and save them locally.

Community
Intermediate
MoizIbnYousafMoizIbnYousaf
31

visual-style

Define a persistent visual brand identity and write it to brand/creative-kit.md for consistent image generation.

Community
Intermediate
CoRLab-TechCoRLab-Tech

figma-illustration-import

Import Figma vector illustrations into React components with SVG/PNG assets and Storybook stories.

Official
Intermediate