Workflow description
This is a very basic ERNIE workflow for ComfyUI, available in two variants: base and turbo.
No prompt enhancers, no detailers, no extra nodes. Just the core setup to generate images.
The goal is simple: give you a clean, stable foundation that you can expand yourself. Add your own prompt enhancers, detailers, LoRAs, or refinements on top of this.
If you are getting started with ERNIE or want a minimal workflow without noise, this is exactly that.
Access All My Workflows
Want access to all my workflows, LoRA dataset training setups, and more?
Check: https://huslyo123.carrd.co/
You will find all details there. Fanvue members get automatic access to my private Discord.
Models and setup
Diffusion models
Base:
https://huggingface.co/Comfy-Org/ERNIE-Image/resolve/main/diffusion_models/ernie-image.safetensors
Text encoder
VAE
Folder structure
ComfyUI/
└── models/
├── diffusion_models/
│ ├── ernie-image.safetensors
│ └── ernie-image-turbo.safetensors
├── text_encoders/
│ └── ministral-3-3b.safetensors
└── vae/
└── flux2-vae.safetensorsRecommended settings
Base model
Steps: 50
CFG: 4.0
Sampler: Euler
Turbo model
Steps: 8
CFG: 1.0
Sampler: res_multistep
Supported resolutions
1024x1024
848x1264
1264x848
768x1376
896x1200
1376x768
1200x896
More info
Clip loader error?
Update ComfyUI to the latest release. Reboot.
Update both .bat and manager if problem still exists. Reboot.
Access All My Workflows
Want access to all my workflows, LoRA dataset training setups, and more?
Check: https://huslyo123.carrd.co/
You will find all details there. Fanvue members get automatic access to my private Discord.
Description
v1.0 initial release.
More testing will follow, including samplers and settings optimizations.
If you like this workflow, consider following me on Civitai.