- name
SKILL.md
Le fichier du skill reste dans le dépôt de l'éditeur.
Collez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add artokun/comfyui-mcp --skill ernie-image -a cursor -yCollez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add artokun/comfyui-mcp --skill ernie-image -a claude-code -yCollez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add artokun/comfyui-mcp --skill ernie-image -a codex -yCollez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add artokun/comfyui-mcp --skill ernie-image -a grok -yEnvoyez le message copié dans un chat Grok Bot. Le Bot récupère ce SKILL.md sur GitHub et l'ajoute aux skills que partagent tous vos Bots.
Install this skill: https://github.com/artokun/comfyui-mcp/tree/HEAD/plugin/skills/ernie-imageDe l'éditeur
ERNIE-Image is Baidu's open-weight TEXT-TO-IMAGE model, an ~8B single-stream Diffusion Transformer (DiT), Apache-2.0, released April 2026 and repackaged for ComfyUI by Comfy-Org. It is not an instruction-based image editor.
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 is the best open-weight text rendering + layout T2I. Qwen-Image-Edit does instruction editing. Flux Kontext does reference editing. Z-Image Turbo does fast general T2I, and this same pack pairs the two; see Combo pipelines.
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:
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, and the rename avoids a filename clash.
This skill is derived from the actual pack files in C:\Users\Artokun\Downloads\:
ERNIE-IMAGE-ULTRA-WORKFLOW.json (authoritative; the ComfyUI graph)ERNIE-IMAGE_ULTRA-MODELS-NODES_INSTALL.bat, ...-COMFYUI-MANAGER_AUTO_INSTALL.bat, ...-AUTO_INSTALL-RUNPOD.shInstaller warning (verified). The three install scripts are copy-pasted from a Z-Image pack. Their headers literally say "Z-IMAGE-BASE"/"Z-IMAGE Base", and they download both ERNIE and Z-Image files. The model URLs/folders below are taken from those scripts but mirror this confusion. They pull
z_image_turbo-*.gguf,Qwen3-4B-*.gguf, andae.safetensors, which belong to the Z-Image half of the combo, not ERNIE. The ERNIE-only files are flagged below. All weights come from a third-party mirrorhuggingface.co/Aitrepreneur/FLX, not the officialhuggingface.co/Comfy-Org/ERNIE-Image(which hosts the same filenames; see Official sources).
Confirmed from the workflow's virtual wires (Set_*/GetNode): the nodes tagged "ERNIE" resolve to these exact files.
Quant guidance from the installer: Q5_K_S for GPUs <8 GB · Q6_K for 8 to 12 GB · Q8_0 for 12 to 16 GB+.
The workflow also wires a parallel Z-Image Turbo pipeline for ERNIE→ZIT / ZIT→ERNIE combos. These files are Z-Image's, not ERNIE's. Do not confuse them:
hirohiko-araki-style-ERNIE_000001250.safetensors and ernie-anime-v1.safetensors are community ERNIE style LoRAs, loaded via Power Lora Loader (rgthree) (both toggled off in the shipped graph). Not in the installer; user-supplied.
4x-ClearRealityV1.pth, RealESRGAN_x4plus_anime_6B.pth → models/upscale_models/.
ComfyUI/custom_nodes/)All three installers clone the same set:
The graph also uses TextGenerate, TextBox1, StringReplace, ComfySwitchNode, PreviewAny, SetNode/GetNode, PrimitiveBoolean, ModelSamplingAuraFlow, ConditioningZeroOut, EmptySD3LatentImage, EmptyFlux2LatentImage. Most are builtin or come from the packs above. SetNode/GetNode are from KJNodes. TextGenerate (runs the prompt-enhancer LLM) has an unverified pack origin; verify which pack provides it via ComfyUI-Manager if it shows as missing.
Base URL HF = https://huggingface.co/Aitrepreneur/FLX/resolve/main (third-party mirror). !MODEL_VERSION! ∈ {Q5_K_S, Q6_K, Q8_0}.
# ERNIE (the files ERNIE actually uses)
unet/ernie-image-turbo-<Q>.gguf <HF>/ernie-image-turbo-<Q>.gguf?download=true
text_encoders/ministral-3-3b.safetensors <HF>/ministral-3-3b.safetensors?download=true
text_encoders/ernie-image-prompt-enhancer.safetensors <HF>/ernie-image-prompt-enhancer.safetensors?download=true
vae/flux2-vae.safetensors <HF>/flux2-vae.safetensors?download=true
# Z-Image half (bundled; only needed for the ZIT combo pipelines)
unet/z_image_turbo-<Q>.gguf <HF>/z_image_turbo-<Q>.gguf?download=true
text_encoders/Qwen3-4B-UD-Q6_K_XL.gguf <HF>/Qwen3-4B-UD-Q6_K_XL.gguf?download=true
vae/ae.safetensors <HF>/ae.safetensors?download=true
# Upscalers
upscale_models/4x-ClearRealityV1.pth <HF>/4x-ClearRealityV1.pth?download=true
upscale_models/RealESRGAN_x4plus_anime_6B.pth <HF>/RealESRGAN_x4plus_anime_6B.pth?download=true
The same filenames are hosted officially at huggingface.co/Comfy-Org/ERNIE-Image (unet|diffusion_models/, text_encoders/, vae/). Apache-2.0. Original model: github.com/baidu/ERNIE-Image. Comfy day-0 docs: docs.comfy.org/tutorials/image/ernie-image/ernie-image. The official repo also ships non-GGUF ernie-image.safetensors / ernie-image-turbo.safetensors (load with UNETLoader instead of UnetLoaderGGUF).
The big graph is a menu of group-boxed pipelines built from the same blocks. Core ERNIE-Image text-to-image flow:
UnetLoaderGGUF (ernie-image-turbo) ──► Power Lora Loader (rgthree) ──► ModelSamplingAuraFlow (shift=3.1) ──► MODEL
CLIPLoader (ministral-3-3b, type=flux2) ──► CLIP ──► CLIPTextEncode (positive)
└──► ConditioningZeroOut ──► negative (cfg=1, so negative ≈ unused)
VAELoader (flux2-vae) ──► VAE
EmptySD3LatentImage (1920×1088) ──► LATENT
│
KSampler (steps≈8–9, cfg=1, euler, simple, denoise=1) ──► VAEDecode ──► SaveImage / post
In the optional prompt enhancer path, the short user prompt + {width}/{height} are templated into a Chinese system prompt, fed to TextGenerate (which runs ernie-image-prompt-enhancer), and a ComfySwitchNode chooses raw prompt (switch=false) vs. enhanced prompt (switch=true) before CLIPTextEncode.
The image-to-image (refine) path is not editing. The graph's "ERNIE IMAGE TO IMAGE" groups take a LoadImage → ImageResize+ (1024, keep proportion, lanczos) and VAEEncode it, then run KSampler at low denoise (0.35 to 0.4) to refine or restyle. This is a denoise pass over a single source image; it does not follow edit instructions.
About the ~5 LoadImage + ~5 VAEEncode nodes: they are not multi-reference compositing. Each LoadImage feeds a separate pipeline variant (single-image img2img, or the combo refine stages). One source image per pipeline. The extra VAEEncodes are the encode steps for those independent img2img / two-pass refine chains.
The combo pipelines (ERNIE↔ZIT), with group titles ERNIE ---> ZIT COMBO, ZIT ---> ERNIE COMBO, TWO TIMES COMBO ..., chain ERNIE and Z-Image Turbo as a two-pass generate→refine, with optional film-grain (FastFilmGrain) or sharpening (FastLaplacianSharpen) finishing and SIMPLE UPSCALE.
ModelSamplingAuraFlow shift = 3.1 is applied to the ERNIE model before sampling (flow-matching shift). Keep it.ConditioningZeroOut as the negative.EmptySD3LatentImage). ERNIE is a high-res-capable DiT; 1024 to 2048 on the long edge is reasonable. Use EmptySD3LatentImage for ERNIE latents.ernie-image, bump steps to ~50 and raise cfg (e.g. 3.5 to 5) since it is not distilled.ERNIE rewards descriptive, structured natural-language prompts, and is unusually strong at literal text rendering. Write the exact text you want to appear in quotes.
A vintage travel poster of Kyoto in autumn, bold title text reading "KYOTO" at the top,
maple leaves, Mount fuji silhouette, clean vector layout, muted warm palette
A 3-panel manga page: panel 1 a samurai drawing his sword, panel 2 close-up of his eyes,
panel 3 a wide shot of cherry blossoms falling, black-and-white ink, speech bubble "参る"
Derived from the source graph, flattened to API format (no subgraphs/virtual wires). The enhancer is omitted for clarity; CLIPTextEncode takes the prompt directly.
{
"1": { "class_type": "UnetLoaderGGUF", "inputs": { "unet_name": "ernie-image-turbo-Q8_0.gguf" } },
"2": { "class_type": "CLIPLoader", "inputs": { "clip_name": "ministral-3-3b.safetensors", "type": "flux2", "device": "default" } },
"3": { "class_type": "VAELoader", "inputs": { "vae_name": "flux2-vae.safetensors" } },
"4": { "class_type": "ModelSamplingAuraFlow", "inputs": { "model": ["1", 0], "shift": 3.1 } },
"5": { "class_type": "CLIPTextEncode", "inputs": { "clip": ["2", 0], "text": "A vintage travel poster of Kyoto in autumn, bold title text reading \"KYOTO\" at the top, maple leaves, clean vector layout, muted warm palette" } },
"6": { "class_type": "ConditioningZeroOut", "inputs": { "conditioning": ["5", 0] } },
"7": { "class_type": "EmptySD3LatentImage", "inputs": { "width": 1920, "height": 1088, "batch_size": 1 } },
"8": { "class_type": "KSampler", "inputs": {
"model": ["4", 0], "positive": ["5", 0], "negative": ["6", 0], "latent_image": ["7", 0],
"seed": 997032332094579, "steps": 9, "cfg": 1, "sampler_name": "euler", "scheduler": "simple", "denoise": 1
} },
"9": { "class_type": "VAEDecode", "inputs": { "samples": ["8", 0], "vae": ["3", 0] } },
"10": { "class_type": "SaveImage", "inputs": { "images": ["9", 0], "filename_prefix": "ernie_image" } }
}
Replace the empty latent with an encoded source image and lower denoise. This restyles or refines a single image; it is not instruction editing.
{
"11": { "class_type": "LoadImage", "inputs": { "image": "source.png" } },
"12": { "class_type": "ImageResize+", "inputs": { "image": ["11", 0], "width": 1024, "height": 1024, "interpolation": "lanczos", "method": "keep proportion", "condition": "always", "multiple_of": 0 } },
"13": { "class_type": "VAEEncode", "inputs": { "pixels": ["12", 0], "vae": ["3", 0] } }
}
Then in the KSampler set "latent_image": ["13", 0] and "denoise": 0.4.
Insert a Power Lora Loader (rgthree) between the UNet loader and ModelSamplingAuraFlow (model: ["1",0] → loader → ["4"].model). In API format you can substitute LoraLoaderModelOnly with lora_name: "ernie-anime-v1.safetensors", strength_model: 0.5.
easy cleanGpuUsed / easy clearCacheAll nodes between stages. Keep them for the combo/two-pass pipelines so VRAM is freed before swapping models.UnetLoaderGGUF / CLIPLoaderGGUF missing. Install ComfyUI-GGUF (city96).Power Lora Loader / Image Comparer / Label missing. Install rgthree-comfy.ImageResize+ missing. Install ComfyUI_essentials.TextGenerate missing (prompt enhancer). Install via ComfyUI-Manager search; pack origin unverified. If unavailable, set the ComfySwitchNode to use the raw prompt (switch=false) and skip enhancement.CLIPLoader type is flux2 (not qwen_image/lumina2). The lumina2 type belongs to the Z-Image (Qwen3) encoder, not ERNIE.flux2-vae.safetensors; ae.safetensors is the Z-Image VAE.ModelSamplingAuraFlow shift=3.1 is wired and steps ≥8 for Turbo; for base ernie-image use ~50 steps + higher cfg.qwen-image-edit skill or Flux Kontext for grounded edits.ComfySwitchNode false) when you've written a detailed prompt yourself.get_workflow (action:"analyze") before executing the shipped graph. It has dozens of group-boxed variants gated by Fast Groups Bypasser (rgthree); the analyzer summary is far easier than reading raw JSON.Build Baidu ERNIE-Image / ERNIE-Image-Turbo workflows, primarily TEXT-TO-IMAGE. Pick ERNIE when you need precise multilingual text rendering, posters/signage, manga/anime multi-panel layouts, or stron
---name: ernie-imagedescription: Build Baidu ERNIE-Image / ERNIE-Image-Turbo workflows, primarily TEXT-TO-IMAGE. Pick ERNIE when you need…---# plugin/skills/ernie-image/SKILL.mdVue d'ensemble
Build Baidu ERNIE-Image / ERNIE-Image-Turbo workflows, primarily TEXT-TO-IMAGE. Pick ERNIE when you need precise multilingual text rendering, posters/signage, manga/anime multi-panel layouts, or strong instruction following for complex multi-object scenes. Also supports denoise-based image-to-image refine (NOT instruction-grounded editing; use Qwen-Image-Edit or Flux Kontext for "change X in this photo" edits).
FAQ
Téléchargez plugin/skills/ernie-image/SKILL.md auprès de l'éditeur, ou copiez le chemin et ouvrez le dépôt. PlugMCP répertorie le skill et n'héberge pas le fichier.
L'éditeur le maintient sur https://github.com/artokun/comfyui-mcp.
Claude, Cursor, Codex et Grok Build peuvent lire un SKILL.md que vous ajoutez depuis le dépôt de l'éditeur. Grok Bot l'installe lorsque vous envoyez dans un chat le lien du dossier GitHub du skill.