Spaces:
Running
on
A10G
Running
on
A10G
Update README.md
Browse files
README.md
CHANGED
@@ -11,6 +11,26 @@ pinned: false
|
|
11 |
|
12 |
This demo showcases [Latent Consistency Model (LCM)](https://huggingface.co/SimianLuo/LCM_Dreamshaper_v7) using [Diffusers](https://github.com/huggingface/diffusers/tree/main/examples/community#latent-consistency-pipeline) with a MJPEG stream server.
|
13 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
# Demo on Hugging Face
|
15 |
https://huggingface.co/spaces/radames/Real-Time-Latent-Consistency-Model
|
16 |
|
|
|
11 |
|
12 |
This demo showcases [Latent Consistency Model (LCM)](https://huggingface.co/SimianLuo/LCM_Dreamshaper_v7) using [Diffusers](https://github.com/huggingface/diffusers/tree/main/examples/community#latent-consistency-pipeline) with a MJPEG stream server.
|
13 |
|
14 |
+
## Running Locally
|
15 |
+
|
16 |
+
You need CUDA and Python
|
17 |
+
`TIMEOUT`: limit user session timeout
|
18 |
+
`SAFETY_CHECKER`: disabled if you want NSFW filter off
|
19 |
+
|
20 |
+
```bash
|
21 |
+
python -m venv venv
|
22 |
+
source venv/bin/activate
|
23 |
+
pip install -r requirements.txt
|
24 |
+
TIMEOUT=0 SAFETY_CHECKER=False uvicorn "app:app" --host 0.0.0.0 --port 7860 --reload
|
25 |
+
```
|
26 |
+
|
27 |
+
## Docker
|
28 |
+
You need NVIDIA Container Toolkit for Docker
|
29 |
+
|
30 |
+
```bash
|
31 |
+
docker build -t lcm-live .
|
32 |
+
docker run -ti -e TIMEOUT=0 -e SAFETY_CHECKER=False -p 7860:7860 --gpus all lcm-live
|
33 |
+
```
|
34 |
# Demo on Hugging Face
|
35 |
https://huggingface.co/spaces/radames/Real-Time-Latent-Consistency-Model
|
36 |
|