ernie-image

ernie-image is a skill for Claude Code from sandyup/comfyui-mcp. It costs 98 tokens per session (5,435 once invoked), scanned A, a copy of ernie-image, MIT.

A workflow guide for Baidu ERNIE-Image and ERNIE-Image-Turbo, image-generation models used through ComfyUI. It focuses on making new images from text, especially images with readable multilingual text, posters, manga panels, or complex scenes.

In plain words
What is it for?
Use it to create posters, signs, UI mockups, manga or anime storyboards, and structured multi-object scenes. It also covers denoise-based refinement, but not instruction-based photo editing.
Why use it?
It helps choose and configure ERNIE for jobs where text placement, layout, or following a detailed scene description matters. It also clarifies that its image-to-image mode refines an image by denoising rather than following instructions such as changing a shirt or background.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the comfy plugin — 32 skills, 11 commands, 4 agents, 2 hooks shipped together

Good fit Use it to create posters, signs, UI mockups, manga or anime storyboards…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sandyup/comfyui-mcp/ernie-image
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 sandyup/comfyui-mcp --skill ernie-image
Clone the repo
git clone --depth 1 https://github.com/sandyup/comfyui-mcp

Made for: Claude Code.

Or install comfy, the plugin that ships this one along with the rest of its 32 skills, 11 commands, 4 agents, 2 hooks.

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 ernie-image

README.md
[![agentmods](https://agentmods.dev/badge/skills/sandyup/comfyui-mcp/ernie-image.svg)](https://agentmods.dev/skills/sandyup/comfyui-mcp/ernie-image)
Your own site
<a href="https://agentmods.dev/skills/sandyup/comfyui-mcp/ernie-image"><img src="https://agentmods.dev/badge/skills/sandyup/comfyui-mcp/ernie-image.svg" alt="Measured on agentmods" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,435 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 88% copy Near-identical to another mod 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 $0.00098 $0.05435
Opus 5 $0.00049 $0.02717
Sonnet 5 $0.00020 $0.01087
Haiku 4.5 $0.00010 $0.00543

Measured 6d ago against content hash 3cf4e7311556, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ernie-image 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 6d 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.

Origin

This is a copy

88% identical to ernie-image — 104 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

plugin/skills/ernie-image/SKILL.md · 238 lines

How it starts

The opening of the file, as written. The whole thing — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ERNIE-Image / ERNIE-Image-Turbo Workflows

What this is (read first)

ERNIE-Image is Baidu's open-weight TEXT-TO-IMAGE model — an ~8B single-stream Diffusion Transformer (DiT), Apache-2.0, released April 2026, repackaged for ComfyUI by Comfy-Org. It is not an instruction-based image editor.

  • ERNIE-Image (base): ~50 steps for peak quality.
  • ERNIE-Image-Turbo: distilled (Distribution Matching Distillation + RL), high-fidelity in ~8 steps, cfg 1. The downloaded pack uses Turbo (ernie-image-turbo-*.gguf).

Pick ERNIE when the job is: precise text/typography rendering (multilingual, including Chinese), posters/signage/UI mockups, manga/anime storyboards and multi-panel layouts, or structured multi-object scenes from a complex prompt. Do NOT pick ERNIE for "edit this photo / change the shirt / swap the background" — that is instruction-grounded editing, which ERNIE does not do. Use qwen-image-edit or Flux Kontext for those. ERNIE's "image-to-image" here is plain denoise-based refinement (style pass / detail pass), not reference-grounded editing.

Niche vs siblings: ERNIE = best open-weight text rendering + layout T2I. Qwen-Image-Edit = instruction editing. Flux Kontext = reference editing. Z-Image Turbo = fast general T2I (and this same pack pairs the two — see Combo pipelines).

Separated packs (render-verified)

The original ernie monolith was a single toggle-template graph (every pipeline shipped bypassed; you activated one via the rgthree group toggles). It's now split into standalone, single-purpose packs — each a clean activated graph that renders headlessly with no group-toggling:

Pack Use Models VRAM
ernie-txt2img text-to-image (flagship) ERNIE only (4) <8GB
ernie-img2img denoise refine of a source image ERNIE only (4) <8GB
ernie-combo ERNIE × Z-Image-Turbo combo pipelines ERNIE + Z-Image (7, ~32GB) 12GB+

Working details verified live: the prompt-enhancer LLM is OFF by default (the ENHANCE PROMPT boolean is false; leave it off unless you want the 3B enhancer to rewrite the prompt). The grain/sharpen post-proc (FastFilmGrain/FastLaplacianSharpen, comfyui-vrgamedevgirl) needs librosa installed. In ernie-combo the Z-Image half's VAE is saved as z-image-ae.safetensors (its weights differ from Flux/ERNIE's ae.safetensors despite the same size — avoids a filename clash).

Read the full file on GitHub · 238 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.

  1. 6d ago First seen · 238 lines · 98 tokens per session scan A 3cf4e7311556

Subscribe to this mod's changes

ernie-image is a skill published in the GitHub repository sandyup/comfyui-mcp (1 stars, last pushed 2mo ago), licensed MIT. It adds 98 tokens to every session and 5,435 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to ernie-image, differing in 104 lines, and is treated as a copy.

Related

Other skills, from other repositories

webgl-holographic-foil

A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.

nexu-io/open-design · 41 tokens

general-video

Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…

heygen-com/hyperframes · 92 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

html-ppt-taste-brutalist

16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).

nexu-io/open-design · 78 tokens

diagnostic-stem-delivery

Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.

HKUDS/OpenSpace · 23 tokens

chengfeng-check-updates

An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.

Agentchengfeng/chengfeng-videocut-skills · 120 tokens