|
--- |
|
license: mit |
|
language: |
|
- en |
|
tags: |
|
- 'openvino ' |
|
- text-to-image |
|
pipeline_tag: text-to-image |
|
--- |
|
|
|
## Model Descriptions: |
|
|
|
This repo contains OpenVino model files for SimianLuo's LCM_Dreamshaper_v7 int8 quantized. |
|
This 8 bit model is **1.4x** faster than `float32` model. |
|
|
|
## Generation Results: |
|
|
|
<p align="center"> |
|
<img src="teaser-int8.jpg"> |
|
</p> |
|
|
|
## Usage |
|
You can try out model using [Fast SD CPU](https://github.com/rupeshs/fastsdcpu) |
|
|
|
To run the model yourself, you can leverage the 🧨 Diffusers library: |
|
1. Install the dependencies: |
|
``` |
|
pip install optimum-intel openvino diffusers onnx |
|
``` |
|
2. Run the model: |
|
```py |
|
from optimum.intel import OVLatentConsistencyModelPipeline |
|
|
|
pipe = OVLatentConsistencyModelPipeline.from_pretrained( |
|
"rupeshs/LCM-dreamshaper-v7-openvino-int8", |
|
ov_config={"CACHE_DIR": ""}, |
|
) |
|
prompt = "sailing ship in storm by Leonardo da Vinci" |
|
images = pipe( |
|
prompt=prompt, |
|
width=512, |
|
height=512, |
|
num_inference_steps=4, |
|
guidance_scale=8.0, |
|
).images |
|
images[0].save("out_image.png") |
|
``` |
|
|