|
--- |
|
license: creativeml-openrail-m |
|
language: |
|
- zh |
|
- en |
|
library_name: diffusers |
|
pipeline_tag: text-to-image |
|
tags: |
|
- art |
|
- tensorRT |
|
--- |
|
# Model Card for fast_sd_1.5 |
|
|
|
fast_sd_1.5 is a tensorRT implementation of Stable diffusion model, with stable 1.5 weights. Main features |
|
|
|
- weights: original stable diffusion 1.4 weights |
|
- input image size range: 256~640 （min 256x256, max 640x640） |
|
- device requirements: Nvidia Ampere architecture or newer (A100) |
|
- super-resultion: 4x by default, optional. |
|
|
|
fast_sd_1.5 is a part of TME lyralab Fast Model Plan. |
|
|
|
|
|
### Model Sources [optional] |
|
|
|
- **Repository:** [https://huggingface.co/runwayml/stable-diffusion-v1-5] |
|
|
|
## Uses |
|
|
|
```python |
|
from fast_sd_1.5 import FSD |
|
from PIL import Image |
|
|
|
|
|
inference_model = FSD(plan="path/to/plan/dir", superres="4x") |
|
|
|
# text input |
|
text = "A red ballon flying in the sky" |
|
output_img = inference_model.infer(text=text) |
|
|
|
# img input |
|
img = Image.open("test.jpg") |
|
output_img = inference_model.infer(img=img) |
|
``` |
|
|
|
|
|
|
|
|
