request python version of file is compatable to run on huggingface spaces gradio sdk

[bugbounted]

Hi Nathan Raw,
please make python file compatable to run on huggingface spaces gradio sdk.
waiting for your response
finest regards

[Atomic-Germ]

I believe the code you're looking for is in the README.MD file:

from stable_diffusion_videos import StableDiffusionWalkPipeline, Interface
import torch

pipeline = StableDiffusionWalkPipeline.from_pretrained(
    "CompVis/stable-diffusion-v1-4",
    torch_dtype=torch.float16,
    revision="fp16",
).to("cuda")

interface = Interface(pipeline)
interface.launch()

or for MacOS on an M1:

from stable_diffusion_videos import StableDiffusionWalkPipeline, Interface
import torch

pipeline = StableDiffusionWalkPipeline.from_pretrained(
    "CompVis/stable-diffusion-v1-4",
    torch_dtype=torch.float32,
    revision="fp16",
).to("mps")

interface = Interface(pipeline)
interface.launch()

This gets you:

~> python3 app.py 
Fetching 16 files: 100%|████████████████████████████████████████████████████████████████| 16/16 [00:00<00:00, 17581.57it/s]
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.

and then put that http://127.0.0.1:7860 in the browser:

[nateraw]

Yea you would need to upgrade your space to have a GPU, though, which you can do in the "settings" tab of the space you created. You can see some options here below: