/ernie-image

name: ernie-image
description: 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).
globs:
  - "**/*.json"

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 and 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 at 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 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.

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, and the rename avoids a filename clash.

Source of truth & a provenance warning

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.sh`

> Installer 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`, and `ae.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 mirror `huggingface.co/Aitrepreneur/FLX`, not the official `huggingface.co/Comfy-Org/ERNIE-Image` (which hosts the same filenames; see Official sources).

Models

ERNIE-Image (the files ERNIE actually uses)

Confirmed from the workflow's virtual wires (`Set_*`/`GetNode`): the nodes tagged "ERNIE" resolve to these exact files.

| Component | Node (type) | File (in workflow) | Folder | Notes | |-----------|-------------|--------------------|--------|-------| | **UNet (GGUF)** | `UnetLoaderGGUF` | `ernie-image-turbo-Q8_0.gguf` | `models/unet/` | Turbo DiT. Q5_K_S / Q6_K / Q8_0 quants offered by installer | | **Text encoder** | `CLIPLoader` (type=`flux2`) | `ministral-3-3b.safetensors` | `models/text_encoders/` | **Ministral-3-3B** is ERNIE's text encoder. Loaded with CLIP type `flux2` | | **VAE** | `VAELoader` | `flux2-vae.safetensors` | `models/vae/` | ERNIE reuses the **Flux 2 VAE** | | **Prompt enhancer** | `CLIPLoader` (type=`flux2`) → `TextGenerate` | `ernie-image-prompt-enhancer.safetensors` | `models/text_encoders/` | 3B LLM that auto-expands a short prompt into a rich description (see Prompt enhancer). Optional, toggled per-pipeline |

> 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+.

Z-Image Turbo (bundled in the same pack — the "ZIT" half)

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:

| Component | Node | File | Folder | |-----------|------|------|--------| | UNet (GGUF) | `UnetLoaderGGUF` | `z_image_turbo-Q8_0.gguf` | `models/unet/` | | Text encoder | `CLIPLoaderGGUF` (type=`lumina2`) | `Qwen3-4B-UD-Q6_K_XL.gguf` | `models/text_encoders/` | | VAE | `VAELoader` | `ae.safetensors` | `models/vae/` |

LoRAs (referenced in the Power Lora Loader, off by default)

`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.

Upscalers / post (shared)

`4x-ClearRealityV1.pth`, `RealESRGAN_x4plus_anime_6B.pth` → `models/upscale_models/`.

Installation

Custom nodes