What is image-models?

A set of instructions for choosing image-generation and background-removal models for img-gen-mcp. It covers providers such as OpenRouter, OpenAI, Gemini, and local systems, along with supported model identifiers.

Use it when configuring img-gen-mcp, selecting an image model, comparing provider options, or validating supported model names.

It helps agents choose a suitable image or background-removal backend instead of guessing which provider and model to use.

image-models — Skill for Claude Code and Codex by jgkme/img-gen-mcp

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add jgkme/img-gen-mcp --skill image-models

Clone the repo

git clone --depth 1 https://github.com/jgkme/img-gen-mcp

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jgkme/img-gen-mcp/image-models/github.svg)](https://agentmods.dev/skills/jgkme/img-gen-mcp/image-models)

Your own site

<a href="https://agentmods.dev/skills/jgkme/img-gen-mcp/image-models"><img src="https://agentmods.dev/badge/skills/jgkme/img-gen-mcp/image-models/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/jgkme/img-gen-mcp/image-models"><img src="https://agentmods.dev/badge/skills/jgkme/img-gen-mcp/image-models.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 868 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00032	$0.00868
Opus 5.5	$0.00013	$0.00347
Sonnet 5.5	$0.00006	$0.00174
Haiku 4.5	$0.00003	$0.00087

Measured 1mo ago against content hash b4758d76aa2a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

image-models scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/image-models/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Image Models And Backends

Use this skill when selecting or validating image generation models, local provider backends, and background-removal backends for img-gen-mcp.

Supported OpenRouter image models

Prefer these slugs when prompting OpenRouter image generation:

microsoft/mai-image-2.5
openai/gpt-image-1
openai/gpt-5-image-mini
openai/gpt-5.4-image-2
google/gemini-2.5-flash-image
google/gemini-2.5-flash-image-preview
google/gemini-3-pro-image-preview
x-ai/grok-imagine-image-quality
bytedance-seed/seedream-4.5
sourceful/riverflow-v2.5-fast:free
sourceful/riverflow-v2.5-fast
sourceful/riverflow-v2.5-pro
sourceful/riverflow-v2-fast
sourceful/riverflow-v2-pro
recraft/recraft-v4.1-utility
recraft/recraft-v4.1-vector
recraft/recraft-v4.1-utility-pro
recraft/recraft-v4.1-pro-vector
recraft/recraft-v3
black-forest-labs/flux.2-pro
black-forest-labs/flux.2-flex

Model notes

microsoft/mai-image-2.5 is a strong default for polished photorealistic output.
x-ai/grok-imagine-image-quality is image-only and is good for realistic, prompt-faithful results.
openai/gpt-5-image-mini is useful when lower latency is preferred.
sourceful/riverflow-* models are often useful for stylized or prompt-following generation.
recraft/* models are useful for logo/vector-style work.
provider=auto can infer the backend from the model slug for common OpenAI, Gemini, OpenRouter, and local wrapper families.

Discovery tools

Use list_image_models to inspect provider families, defaults, and output directories.
Use get_provider_status to check which providers are configured, the active defaults, and local bootstrap hints.
Use get_model_capabilities to see which providers can generate, edit, batch, or use local endpoints.

Workflow helpers

Use submit_task and get_task when a client prefers polling instead of waiting synchronously.
Use batch_generate_image when you want multiple variants from a single prompt.

Read the full file on GitHub · 82 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

1mo ago First seen · 82 lines · 32 tokens per session scan A b4758d76aa2a

Subscribe to this mod's changes

image-models is a skill published in the GitHub repository jgkme/img-gen-mcp (3 stars, last pushed 3mo ago), licensed MIT. It adds 32 tokens to every session and 868 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Creative and media

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…

vercel/next.js · 123 tokens