app.py

import gradio as gr
import torch
from diffusers import DiffusionPipeline, DPMSolverMultistepScheduler
from diffusers.utils import export_to_video

pipe = DiffusionPipeline.from_pretrained("cerspense/zeroscope_v2_576w", torch_dtype=torch.float16)
pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)
pipe.enable_model_cpu_offload()

def infer(prompt, num_inference_steps):
    #prompt = "Darth Vader is surfing on waves"
    video_frames = pipe(prompt, num_inference_steps=40, height=320, width=576, num_frames=24).frames
    video_path = export_to_video(video_frames)
    print(video_path)
    return video_path

css = """
#col-container {max-width: 510px; margin-left: auto; margin-right: auto;}
a {text-decoration-line: underline; font-weight: 600;}
"""

with gr.Blocks(css=css) as demo:
    with gr.Column(elem_id="col-container"):
        gr.HTML("""<div style="text-align: center; max-width: 700px; margin: 0 auto;">
                <div
                style="
                    display: inline-flex;
                    align-items: center;
                    gap: 0.8rem;
                    font-size: 1.75rem;
                "
                >
                <h1 style="font-weight: 900; margin-bottom: 7px; margin-top: 5px;">
                    Zeroscope Text-to-Video
                </h1>
                </div>
                <p style="margin-bottom: 10px; font-size: 94%">
                A watermark-free Modelscope-based video model optimized for producing high-quality 16:9 compositions and a smooth video output. <br />
                This model was trained using 9,923 clips and 29,769 tagged frames at 24 frames, 576x320 resolution.
                [![Duplicate this Space](https://huggingface.co/datasets/huggingface/badges/raw/main/duplicate-this-space-sm.svg)](https://huggingface.co/spaces/fffiloni/zeroscope?duplicate=true)
                </p>
            </div>""")

        prompt_in = gr.Textbox(label="Prompt", placeholder="Darth Vader is surfing on waves")
        inference_steps = gr.Slider(label=Inference Steps, minimum=10, maximum=100, step=1, value=40, interactive=False)
        submit_btn = gr.Button("Submit")
        video_result = gr.Video(label="Video Output")

    submit_btn.click(fn=infer,
                    inputs=[prompt_in, inference_steps],
                    outputs=[video_result])

demo.queue(max_size=12).launch()