Generate Gemini Images with inference.sh
Users need a quick way to run Gemini image models from an AI assistant. This skill provides CLI patterns for generation, edits, ratios, and grounded prompts.
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "nano-banana" from https://skillstore.io/skills/tul-sh-nano-banana.md and its manifest at https://skillstore.io/api/skills/tul-sh-nano-banana/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Your Agent should still show its plan and request any confirmation required by the security policy.
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Using "nano-banana". Generate four minimalist coffee shop logo concepts with Gemini 2.5 Flash Image.
Expected outcome:
The skill prepares an inference.sh request for four Gemini image outputs using a concise logo design prompt.
Using "nano-banana". Create a 4K illustration of a medieval castle with detailed stone textures.
Expected outcome:
The skill selects the higher quality Gemini image model and includes the requested 4K resolution option.
Using "nano-banana". Add a rainbow to an existing landscape image from a URL.
Expected outcome:
The skill formats an image-editing request that passes the source image URL and the edit instruction.
The static Ruby backtick and hardcoded URL alerts are Markdown formatting, examples, and documentation links, so I marked them false positive. The real risk is contextual: the skill grants broad infsh CLI access and sends prompts, image URLs, and optional input files to external inference services. No prompt injection language was found.
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
https://skillstore.io/skills/tul-sh-nano-banana/audits/5?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report[](https://skillstore.io/skills/tul-sh-nano-banana?utm_source=security_passport_badge)<a href="https://skillstore.io/skills/tul-sh-nano-banana?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/tul-sh-nano-banana/security.svg" alt="Skillstore security assessment" loading="lazy"></a><iframe src="https://skillstore.io/embed/skills/tul-sh-nano-banana.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>tul-sh. (2026). nano-banana security audit report (audit version 5) [Author version unspecified]. Skillstore. https://skillstore.io/skills/tul-sh-nano-banana/audits/5@techreport{tul-sh-tul-sh-nano-banana-2026,
author = {tul-sh},
title = {nano-banana security audit report (audit version 5)},
institution = {Skillstore},
year = {2026},
number = {5},
url = {https://skillstore.io/skills/tul-sh-nano-banana/audits/5},
note = {Author version unspecified}
}cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "nano-banana security audit report (audit version 5)"
version: "unspecified"
type: report
authors:
- name: "tul-sh"
date-released: "2026-07-07"
url: "https://skillstore.io/skills/tul-sh-nano-banana/audits/5"
identifiers:
- type: other
value: "skillstore:tul-sh-nano-banana:audit:5"
description: "Skillstore immutable audit report identifier"
Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.
Why this variant is first
tul-sh-nano-banana
2026-09-09
inference-shell-nano-banana
2026-09-09
inferen-sh-nano-banana
2026-09-09
toolshell-nano-banana
2026-09-09
inference-sh-9-nano-banana
2026-09-09
Generate multiple concept images for ads, social posts, or landing pages with controlled aspect ratios.
Draft product scenes, style variations, and background edits before commissioning final assets.
Use CLI requests to create repeatable image generation flows inside assistant-driven work sessions.
Generate a square Gemini image of a modern desk setup with natural light and clean composition.
Use Gemini 3 Pro Image to create a 16:9 cinematic mountain landscape with northern lights.
Edit this image URL by adding a rainbow in the sky while preserving the landscape and lighting.
Create an input file for a search-grounded Gemini image showing current Tokyo weather as an artistic scene.
Author
tul-shLicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
36e07d5e13068e5be64447e8f20b427cf2cbd21a
Maintenance freshness
7/20/2026
Usage
29 downloads · 146 views
File structure
📄 SKILL.md
Generate Images with Qwen Image
Image workflows often need fast visuals and accurate text rendering from one repeatable tool. This skill guides Claude, Codex, and Claude Code to run Qwen-Image through inference.sh.
Generate AI Images With Inference.sh
Image teams need quick access to many hosted generation models. This skill guides Claude, Codex, and Claude Code through inference.sh image workflows.
Create Professional Qwen Images
Teams need reliable image generation for posters, banners, and text-heavy designs. This skill guides Claude, Codex, and Claude Code through Qwen-Image Pro via inference.sh.
Render Remotion Videos from TSX
Rendering Remotion animations can require local setup and build tooling. This skill sends component code to inference.sh and returns an MP4 render.
Create AI Videos with inference.sh
Teams need repeatable prompts for video models without memorizing each CLI app. This skill guides Claude, Codex, and Claude Code through inference.sh video workflows.
Generate Gemini Images with Nano Banana 2
Image teams need quick access to Gemini image generation and editing from an AI assistant. This skill provides infsh commands for prompts, image inputs, size settings, and Google Search grounding.
Create and Edit Project Images
by openai
Producing consistent raster assets requires precise prompts, careful edits, and reliable output handling. This skill structures requests, creates or edits visuals, validates results, and saves project-ready files.
Generate Text-Rich Images with Qwen Pro
by inference-shell
Design teams need image prompts that preserve text and layout details. This skill guides Claude, Codex, or Claude Code to call Qwen-Image-2-Pro through inference.sh.
Generate GPT Image 2 Assets on RunComfy
by runcomfy-com
Teams need image prompts and edits that preserve text, layout, and brand details. This skill guides Claude, Codex, and Claude Code to use RunComfy's GPT Image 2 endpoints with clear size, edit, and privacy rules.
Generate Native-Alpha Transparent Images
by zseven-w
Image generators can return opaque files or painted checkerboards when transparency is required. This skill generates native-alpha assets and validates every untouched output.
Create Consistent Video Storyboards
by supercmohq
Video concepts can lose continuity when clips are planned separately. This skill creates sequential storyboard sheets that preserve characters, products, settings, and visual states.
Create Reusable Photorealistic AI Actors
by supercmohq
Campaign teams need consistent fictional talent without supplying a person photograph. This skill creates one detailed adult identity that can guide later image and video generation.