agentmods.dev

hunyuan-image-generation

hunyuan-image-generation is a skill for Codex from linkprint/local-ai-movie-workspace. It costs 65 tokens per session (405 once invoked), scanned A, original, MIT.

A tool for creating images from text with the HunyuanImage-3.0-Instruct model, also known as 混元. It runs the image job through the movie-ai service and provides the completed download.

In plain words
What is it for?
Use it when a request explicitly names Hunyuan or 混元 and needs a 1024-by-1024 text-to-image result with optional generation settings.
Why use it?
It gives Hunyuan-specific image generation a defined job format and workflow instead of treating it like an unspecified image tool.

Skill for Codex

Written for Codex: agents/openai.yaml present.

not rated 1repo +1 2mo ago A scan 65 tokens original MIT

Good fit Use it when a request explicitly names Hunyuan or 混元 and needs a 1024-by-1024 text-to-image result with optional generation settings.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/linkprint/local-ai-movie-workspace/hunyuan-image-generation
View source ↗ linkprint/local-ai-movie-workspace
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 linkprint/local-ai-movie-workspace --skill hunyuan-image-generation
Clone the repo
git clone --depth 1 https://github.com/linkprint/local-ai-movie-workspace

Made for: 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.

agentmods badge for hunyuan-image-generation

README.md
[![agentmods](https://agentmods.dev/badge/skills/linkprint/local-ai-movie-workspace/hunyuan-image-generation/github.svg)](https://agentmods.dev/skills/linkprint/local-ai-movie-workspace/hunyuan-image-generation)
Your own site
<a href="https://agentmods.dev/skills/linkprint/local-ai-movie-workspace/hunyuan-image-generation"><img src="https://agentmods.dev/badge/skills/linkprint/local-ai-movie-workspace/hunyuan-image-generation/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.

agentmods 80×15 button for hunyuan-image-generation

Your own site · 80×15
<a href="https://agentmods.dev/skills/linkprint/local-ai-movie-workspace/hunyuan-image-generation"><img src="https://agentmods.dev/badge/skills/linkprint/local-ai-movie-workspace/hunyuan-image-generation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 405 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00065 $0.00405
Opus 5.5 $0.00026 $0.00162
Sonnet 5.5 $0.00013 $0.00081
Haiku 4.5 $0.00006 $0.00040

Measured 2mo ago against content hash c68e46a96041, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

hunyuan-image-generation 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 2mo 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.

images/workspace/admin-skills/hunyuan-image-generation/SKILL.md · 29 lines

What it actually says

Hunyuan Image Generation

Use only movie-ai; never contact ComfyUI, the host, or a LAN address directly.

Invoke this skill only when the current user request explicitly names Hunyuan/混元. Do not select Hunyuan based on prompt complexity, composition, or quality judgment alone. A local-language-model session otherwise uses Z-Image-Turbo, while an OpenAI-language-model session otherwise uses gpt-image-2.

Save a JSON spec under /workspace with:

  • model: HunyuanImage-3.0-Instruct.
  • prompt: the approved image prompt.
  • resolution: currently 1024x1024.
  • seed: optional non-negative integer.
  • steps: 4 through 12; default 8.
  • guidance_scale: 1 through 5; default 2.5.
  • flow_shift: 1 through 5; default 2.3.

Run movie-ai image generate --model HunyuanImage-3.0-Instruct --spec SPEC.json, then movie-ai job wait JOB_ID. After the job is completed, download it with movie-ai job download JOB_ID --output /outputs/NAME.png and verify the reported SHA-256. The download result includes an absolute url; always give that Portal URL to the user, never only the /outputs path.

The Broker may keep the shared fixed ComfyUI worker running between H3 and Hunyuan jobs. If preflight or generation fails, report the job status and do not retry automatically or bypass the Broker.

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. 2mo ago First seen · 29 lines · 65 tokens per session scan A c68e46a96041

Subscribe to this mod's changes

hunyuan-image-generation is a skill published in the GitHub repository linkprint/local-ai-movie-workspace (1 stars, last pushed 2mo ago), licensed MIT. It adds 65 tokens to every session and 405 once invoked, about $0.0003 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.

AI PlatformClaude CodeCreative and mediaai-filmmakingai-infrastructureai-server-reservationai-workspace
Related

hunyuan-image-generation compared with skills from other repositories

hunyuan-image-generation next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
hunyuan-image-generationlinkprint/local-ai-movie-workspaceSkill12mo agoMITA65Codex
tape-opensenricoros/big-AGISkill7.2ktodayMITA60Claude Code
x-signal-agentomnara-ai/omnaraSkill3.4ktodayApache-2.0A53Claude Code, Codex
agent-notesCherryHQ/cherry-studioSkill53ktodayAGPL-3.0A51Claude Code, Codex
cherry-electron-devCherryHQ/cherry-studioSkill53ktodayAGPL-3.0A68Claude Code, Codex
issue-reporterCherryHQ/cherry-studioSkill53ktodayAGPL-3.0A35Claude Code
code-mate-antigravityCherryHQ/cherry-studioSkill53ktodayAGPL-3.0A32Claude Code, Codex