ERNIE-Image

1. Model Introduction

ERNIE-Image is Baidu’s text-to-image family with separate standard and Turbo checkpoints. The standard model is the quality-oriented path; Turbo is the lower-latency choice, and both load through SGLang’s native ErnieImagePipeline. This integration currently targets text-only image generation rather than image editing or reference conditioning. Choose it for a straightforward single-GPU T2I deployment; use a dedicated editing model when preserving source-image structure is part of the task.

Model	Hugging Face model ID	Notes
ERNIE-Image	`baidu/ERNIE-Image`	Regular text-to-image checkpoint
ERNIE-Image-Turbo	`baidu/ERNIE-Image-Turbo`	Turbo text-to-image checkpoint

2. Installation

Follow the SGLang Diffusion installation guide. Docker is recommended for Linux GPU deployments; run the commands below inside the container or your installed Python environment.

3. Serve the model

The commands below target a single supported NVIDIA CUDA or AMD ROCm GPU. Start with --performance-mode auto; use speed only when the full pipeline fits comfortably on the selected GPU(s), and use memory when you need lower peak GPU memory. Serve ERNIE-Image:

Command

sglang serve \
  --model-path baidu/ERNIE-Image \
  --num-gpus 1 \
  --performance-mode auto \
  --port 30010

Serve ERNIE-Image-Turbo:

Command

sglang serve \
  --model-path baidu/ERNIE-Image-Turbo \
  --num-gpus 1 \
  --performance-mode auto \
  --port 30010

4. Generate an image

Use the OpenAI-compatible image generation API after the server starts:

Python

import base64
from openai import OpenAI

client = OpenAI(api_key="EMPTY", base_url="http://127.0.0.1:30010/v1")

response = client.images.generate(
    model="baidu/ERNIE-Image-Turbo",
    prompt="A cinematic photo of a quiet lakeside cabin at sunrise",
    n=1,
    response_format="b64_json",
)

image_bytes = base64.b64decode(response.data[0].b64_json)
with open("ernie_image.png", "wb") as f:
    f.write(image_bytes)

5. Configuration tips

ERNIE-Image is a text-to-image pipeline; do not pass --image-path.
--performance-mode auto keeps conservative defaults while preserving explicit user flags.
If the checkpoint includes a PE component, SGLang loads it automatically with the native Ministral3 runtime. Use --layerwise-offload-components pe when the local PE decoder needs to trade latency for lower GPU memory usage.
Treat FSDP, SP/Ulysses/Ring, and TP as explicit benchmark knobs. Measure the target resolution, step count, and GPU type before making them production defaults.

Cookbook

1. Model Introduction

2. Installation

3. Serve the model

4. Generate an image

5. Configuration tips

6. Run in ComfyUI

​1. Model Introduction

​2. Installation

​3. Serve the model

​4. Generate an image

​5. Configuration tips

​6. Run in ComfyUI

1. Model Introduction

2. Installation

3. Serve the model

4. Generate an image

5. Configuration tips

6. Run in ComfyUI