metadata
license: apache-2.0
pipeline_tag: text-to-image
library_name: diffusers
tags:
- text-to-image
- 8B
- nf4
- 4bit
- quantized
model_size: 7B
quantized_by: Abhishek Dujari
base_model:
- baidu/ERNIE-Image
base_model_relation: quantized
ERNIE-Image
Ovedrive version of mixed precision targetting 12GB VRAM (full model in memory) or less than. It is not widely tested, please do share your results and optimal steps. Minimum VRAM required is 6GB.
thank you Justlab.ai for the GPUs
Steps 20, CFG 4 for both (random seed)
| Original ERNIE-Image | Ovedrive NF4 quantized |
|---|---|
 |
 |
| Full precision baseline | Mixed precision NF4 |
Quick Start
Recommended Parameters
- Resolution:
- 1024x1024
- 848x1264
- 1264x848
- 768x1376
- 896x1200
- 1376x768
- 1200x896
- Guidance scale: 4.0
- Inference steps: 50
Diffusers
pip install git+https://github.com/huggingface/diffusers
import torch
from diffusers import ErnieImagePipeline
pipe = ErnieImagePipeline.from_pretrained(
"ovedrive/ERNIE-Image-nf4",
torch_dtype=torch.bfloat16,
).to("cuda")
image = pipe(
prompt="This is a photograph depicting an urban street scene. Shot at eye level, it shows a covered pedestrian or commercial street. Slightly below the center of the frame, a cyclist rides away from the camera toward the background, appearing as a dark silhouette against backlighting with indistinct details. The ground is paved with regular square tiles, bisected by a prominent tactile paving strip running through the scene, whose raised textures are clearly visible under the light. Light streams in diagonally from the right side of the frame, creating a strong backlight effect with a distinct Tyndall effect—visible light beams illuminating dust or vapor in the air and casting long shadows across the street. Several pedestrians appear on the left side and in the distance, some with their backs to the camera and others walking sideways, all rendered as silhouettes or semi-silhouettes. The overall color palette is warm, dominated by golden yellows and dark browns, evoking the atmosphere of dusk or early morning.",
height=1264,
width=848,
num_inference_steps=50,
guidance_scale=4.0,
use_pe=True # use prompt enhancer
).images[0]
image.save("output.png")
SGLang
Install the latest version of sglang:
git clone https://github.com/sgl-project/sglang.git
Start the server:
sglang serve --model-path baidu/ERNIE-Image
Send a generation request:
curl -X POST http://localhost:30000/v1/images/generations \
-H "Content-Type: application/json" \
-d '{
"prompt": "This is a photograph depicting an urban street scene. Shot at eye level, it shows a covered pedestrian or commercial street. Slightly below the center of the frame, a cyclist rides away from the camera toward the background, appearing as a dark silhouette against backlighting with indistinct details. The ground is paved with regular square tiles, bisected by a prominent tactile paving strip running through the scene, whose raised textures are clearly visible under the light. Light streams in diagonally from the right side of the frame, creating a strong backlight effect with a distinct Tyndall effect—visible light beams illuminating dust or vapor in the air and casting long shadows across the street. Several pedestrians appear on the left side and in the distance, some with their backs to the camera and others walking sideways, all rendered as silhouettes or semi-silhouettes. The overall color palette is warm, dominated by golden yellows and dark browns, evoking the atmosphere of dusk or early morning.",
"height": 1264,
"width": 848,
"num_inference_steps": 50,
"guidance_scale": 4.0,
"use_pe": true
}' \
--output output.png