Generate Images with Nano Banana 2
Teams need fast text-to-image drafts with clear controls for aspect ratio, resolution, and web grounding. This skill guides Claude, Codex, and Claude Code to use RunComfy Nano Banana 2 with documented prompts and CLI options.
Stop for confirmation before installing.
Review the plan and obtain explicit user consent before changing files.
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/runcomfy-com-nano-banana-2.md and its manifest at https://skillstore.io/api/skills/runcomfy-com-nano-banana-2/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.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". Generate four vertical thumbnail drafts for a fitness app launch.
Expected outcome:
Four 9:16 draft images are saved to the selected folder, with settings suited for fast review.
Using "nano-banana-2". Create a product card for a black mug with the headline Brewed Quietly.
Expected outcome:
A 16:9 brand card image is produced with the mug centered and the quoted headline placed clearly.
Using "nano-banana-2". Create a web-grounded image about a current product announcement.
Expected outcome:
A still image is generated using web grounding, with a note that external context increased latency and cost.
Most static findings are Markdown false positives from inline code, tables, and sample prompts. Confirmed risks are legitimate but security-relevant: external RunComfy CLI execution, prompt upload to RunComfy model endpoints, and a repository mismatch in install instructions. No prompt injection or hidden exfiltration instructions were 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/runcomfy-com-nano-banana-2/audits/6?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report[](https://skillstore.io/skills/runcomfy-com-nano-banana-2?utm_source=security_passport_badge)<a href="https://skillstore.io/skills/runcomfy-com-nano-banana-2?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/runcomfy-com-nano-banana-2/security.svg" alt="Skillstore security assessment" loading="lazy"></a><iframe src="https://skillstore.io/embed/skills/runcomfy-com-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>runcomfy-com. (2026). nano-banana-2 security audit report (audit version 6) [Author version unspecified]. Skillstore. https://skillstore.io/skills/runcomfy-com-nano-banana-2/audits/6@techreport{runcomfy-com-runcomfy-com-nano-banana-2-2026,
author = {runcomfy-com},
title = {nano-banana-2 security audit report (audit version 6)},
institution = {Skillstore},
year = {2026},
number = {6},
url = {https://skillstore.io/skills/runcomfy-com-nano-banana-2/audits/6},
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 6)"
version: "unspecified"
type: report
authors:
- name: "runcomfy-com"
date-released: "2026-07-09"
url: "https://skillstore.io/skills/runcomfy-com-nano-banana-2/audits/6"
identifiers:
- type: other
value: "skillstore:runcomfy-com-nano-banana-2:audit:6"
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
2026-08-21
agentspace-so-nano-banana-2
2026-08-21
toolshell-nano-banana-2
2026-08-21
inference-shell-nano-banana-2
2026-08-21
tul-sh-nano-banana-2
2026-08-21
doany-ai-nano-banana-2
2026-08-21
inference-sh-9-nano-banana-2
2026-08-21
runcomfy-com-nano-banana-2
2026-08-21
Generate four vertical thumbnail concepts quickly, then select one for refinement.
Create product cards and posters that include quoted in-image text and controlled framing.
Use seeds and resolution tiers to move from rough concepts to final still images.
Generate a 1K square PNG with Nano Banana 2 for: [describe subject]. Save the output in [folder].
Use Nano Banana 2 to create four 9:16 draft variants at 0.5K for: [campaign idea]. Keep the composition simple.
Create a 16:9 2K final image using seed [number]. Preserve the main composition and improve: [specific detail].
Use Nano Banana 2 with web search enabled to create current-event imagery about [entity or event]. Avoid unsupported claims.
Author
runcomfy-comLicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
0519034dad657fb1f7706e0550e962beeda73fdf
Maintenance freshness
7/18/2026
Usage
5 downloads · 0 views
File structure
📄 SKILL.md
Generate ACE Step Music on RunComfy
Creating affordable AI music often needs endpoint selection, structured lyrics, and repeatable CLI inputs. This skill guides ACE Step generation, inpainting, and outpainting through RunComfy.
Generate Music with ElevenLabs on RunComfy
Creating production-ready music prompts and CLI calls can be slow and error-prone. This skill guides Claude, Codex, and Claude Code through ElevenLabs Music generation on RunComfy with clear parameters and workflow advice.
Create Pose-Controlled Images and Videos
Pose-controlled generation often requires choosing the right model and input format. This skill routes image and video requests to RunComfy workflows.
Create AI Avatar Videos with RunComfy
Creating lip-synced avatar videos often requires choosing the right model and input format. This skill routes requests to RunComfy models and provides ready CLI invocations.
Inpaint Images with RunComfy
Mask-driven image edits can be slow when prompts, masks, and model choices are handled manually. This skill guides Claude, Codex, or Claude Code to run RunComfy inpainting with the right model and inputs.
Animate Images with RunComfy Video Models
Still images need the right model and prompt to become useful video clips. This skill routes image-to-video requests to RunComfy models with matching settings and examples.
Run RunComfy Models from the CLI
by doany-ai
Creative teams and developers need a reliable way to run RunComfy models from automated terminal workflows. This skill explains authentication, schema discovery, job submission, polling, downloads, and safer scripting with the RunComfy CLI.
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 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.
Create Premium Google Stitch Design Systems
by leonxlnx
Generic AI screens often look inconsistent and hard to refine. This skill turns project direction into a structured DESIGN.md that guides Google Stitch, Claude, Codex, and Claude Code.
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.