comfyui-mcp
Version:
Local-first, agent-native control plane for ComfyUI — MCP server + autonomous sidebar agent that drives your live graph in natural language on ANY LLM: Claude/ChatGPT/Gemini on your subscription (no API key), free local models via Ollama (fully offline),
39 lines (38 loc) • 1.8 kB
YAML
name: ernie-txt2img
display_name: ERNIE-Image — Text to Image
family: ernie
kind: txt2img
description: >-
ERNIE-Image Ultra (Baidu, ~8B single-stream DiT, Apache-2.0) text-to-image,
distilled Turbo GGUF — high fidelity in ~8 steps at cfg 1, under 8GB VRAM.
Standout strength is precise multilingual TEXT RENDERING (incl. Chinese) for
posters/signage/UI mockups and structured multi-panel layouts. Single-purpose
txt2img graph sliced from the ERNIE monolith (one pipeline, no group toggles).
An optional 3B prompt-enhancer LLM expands short prompts (toggle the ENHANCE
PROMPT boolean). Not an instruction editor.
vram: "<8GB"
workflow: workflow.json
skill: ernie-image
launch_args: []
# User-supplied example LoRAs referenced by the (off-by-default) Power Lora Loader.
external_models:
- hirohiko-araki-style-ERNIE_000001250.safetensors
- ernie-anime-v1.safetensors
sources:
model: https://huggingface.co/Comfy-Org/ERNIE-Image
original: https://github.com/baidu/ERNIE-Image
docs: https://docs.comfy.org/tutorials/image/ernie-image/ernie-image
mirror: https://huggingface.co/Aitrepreneur/FLX
notes:
- Run the generated installer from your ComfyUI root (folder with custom_nodes/
and models/).
- Text-to-image only — ERNIE excels at literal text/typography (write the exact
string in quotes) and structured layouts.
- Turbo defaults (from the shipped graph) — 8 steps, cfg 1, euler/simple,
1920x1088. Sliced + un-bypassed from the monolith's "ERNIE TEXT TO IMAGE".
- Weights mirrored from huggingface.co/Aitrepreneur/FLX; prefer the official
Comfy-Org/ERNIE-Image repo (same filenames) when possible.
post_install:
- Restart ComfyUI (or ComfyUI-Manager -> Install missing custom nodes for any
node Python deps).
- Load workflow.json.