comfyui-mcp/packs/ernie-img2img/pack.yaml

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),

name: ernie-img2img
display_name: ERNIE-Image — Image to Image
family: ernie
kind: img2img
description: >-
  ERNIE-Image Ultra (Baidu, ~8B single-stream DiT, Apache-2.0) image-to-image,
  distilled Turbo GGUF. Feed a source image (LoadImage) and a prompt to restyle
  or refine it; ERNIE's strength is precise multilingual TEXT RENDERING and
  structured layouts. Single-purpose img2img graph sliced from the ERNIE
  monolith (one pipeline, no group toggles). Optional 3B prompt-enhancer LLM.
vram: "<8GB"
workflow: workflow.json
skill: ernie-image
launch_args: []
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/).
  - Load your source image into the LoadImage node, then queue. Denoise controls
    how much it deviates from the source.
  - Sliced + un-bypassed from the monolith's "ERNIE IMAGE TO IMAGE". Same ERNIE
    weights as the txt2img pack.
  - 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 and set the LoadImage node to your source image.