Generate Gemini Images with inference.sh
Image teams need fast drafts and edits without building a custom image pipeline. This skill guides Claude, Codex, and Claude Code to run Gemini image generation through inference.sh.
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "nano-banana-2" from https://skillstore.io/skills/inference-shell-nano-banana-2.md and its manifest at https://skillstore.io/api/skills/inference-shell-nano-banana-2/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-2". Create a photorealistic widescreen image of a compact electric bike near a city train station.
Expected outcome:
A generated widescreen image is returned with a short model description and image metadata from inference.sh.
Using "nano-banana-2". Edit this product photo to add a neutral studio background and softer lighting.
Expected outcome:
The skill submits the image edit request and returns the edited image output, plus provider metadata.
Using "nano-banana-2". Make four logo moodboard images for a modern coffee shop.
Expected outcome:
Static analysis flagged Markdown backticks and command examples throughout SKILL.md. Most table rows and fence markers are false positives, but several examples intentionally run infsh or npx. No prompt injection or covert data exfiltration intent was found.
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
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/inference-shell-nano-banana-2/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report[](https://skillstore.io/skills/inference-shell-nano-banana-2?utm_source=security_passport_badge)<a href="https://skillstore.io/skills/inference-shell-nano-banana-2?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/inference-shell-nano-banana-2/security.svg" alt="Skillstore security assessment" loading="lazy"></a><iframe src="https://skillstore.io/embed/skills/inference-shell-nano-banana-2.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>inference-shell. (2026). nano-banana-2 security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/inference-shell-nano-banana-2/audits/4@techreport{inference-shell-inference-shell-nano-banana-2-2026,
author = {inference-shell},
title = {nano-banana-2 security audit report (audit version 4)},
institution = {Skillstore},
year = {2026},
number = {4},
url = {https://skillstore.io/skills/inference-shell-nano-banana-2/audits/4},
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-2 security audit report (audit version 4)"
version: "unspecified"
type: report
authors:
- name: "inference-shell"
date-released: "2026-07-05"
url: "https://skillstore.io/skills/inference-shell-nano-banana-2/audits/4"
identifiers:
- type: other
value: "skillstore:inference-shell-nano-banana-2:audit:4"
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
inferen-sh-nano-banana-2
2026-09-09
agentspace-so-nano-banana-2
2026-09-09
toolshell-nano-banana-2
2026-09-09
inference-shell-nano-banana-2
2026-09-09
tul-sh-nano-banana-2
2026-09-09
doany-ai-nano-banana-2
2026-09-09
inference-sh-9-nano-banana-2
2026-09-09
runcomfy-com-nano-banana-2
2026-09-09
Create quick visual directions from text prompts before starting detailed design work.
Generate multiple visual concepts for ads, social posts, and presentation materials.
Edit product photos with new backgrounds, lighting, or composition guidance.
Use nano-banana-2 to create one square image of [subject]. Use [style], [lighting], and a simple background.
Use nano-banana-2 to edit [image path or URL]. Change [specific element], keep [elements to preserve], and return one refined image.
Use nano-banana-2 to create four [aspect ratio] concepts for [campaign or product]. Compare the strongest visual directions after generation.
Use nano-banana-2 with Google Search grounding to visualize [current topic]. Keep the result factual, neutral, and suitable for [audience].
Author
inference-shellLicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
a25199bc7d6b82598536822d1738eb5d5f54025b
Maintenance freshness
7/18/2026
Usage
12 downloads · 300 views
File structure
📄 SKILL.md
Generate Text-Rich Images with Qwen Pro
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.
Create AI Videos with Inference.sh
AI video workflows require many model choices and exact CLI inputs. This skill gives Claude, Codex, and Claude Code clear inference.sh examples for common video tasks.
Generate Images with inference.sh Models
Creating AI visuals across many model providers can require separate prompts and tools. This skill gives Claude, Codex, and Claude Code one inference.sh CLI workflow for image generation, editing, upscaling, and stitching.
Generate Images With Qwen-Image 2
Design teams need fast ways to create and edit visual concepts. This skill guides Claude, Codex, and Claude Code to run Qwen-Image 2 through inference.sh.
Generate Gemini Images with Nano Banana
Image work often needs fast model access without building API plumbing. This skill guides Claude, Codex, and Claude Code through inference.sh commands for Gemini image generation and editing.
Render Remotion Videos from TSX
Programmatic video rendering can be slow to set up for React motion projects. This skill runs Remotion components through inference.sh and returns an MP4.
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 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.
Create Pose-Controlled Images and Videos
by runcomfy-com
Pose-controlled generation often requires choosing the right model and input format. This skill routes image and video requests to RunComfy workflows.