import gradio as gr import cv2 import numpy as np import tempfile import imageio import torch from diffusers import DiffusionPipeline, DPMSolverMultistepScheduler 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 export_to_video(frames: np.ndarray, fps: int) -> str: frames = np.clip((frames * 255), 0, 255).astype(np.uint8) out_file = tempfile.NamedTemporaryFile(suffix=".mp4", delete=False) writer = imageio.get_writer(out_file.name, format="FFMPEG", fps=fps) for frame in frames: writer.append_data(frame) writer.close() return out_file.name def infer(prompt): negative_prompt = "text, watermark, copyright, blurry, nsfw" video_frames = pipe(prompt, negative_prompt=negative_prompt, num_inference_steps=40, height=320, width=576, num_frames=24).frames[0] video_path = export_to_video(video_frames, 12) 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;} .animate-spin { animation: spin 1s linear infinite; } @keyframes spin { from { transform: rotate(0deg); } to { transform: rotate(360deg); } } #share-btn-container { display: flex; padding-left: 0.5rem !important; padding-right: 0.5rem !important; background-color: #000000; justify-content: center; align-items: center; border-radius: 9999px !important; max-width: 15rem; height: 36px; } div#share-btn-container > div { flex-direction: row; background: black; align-items: center; } #share-btn-container:hover { background-color: #060606; } #share-btn { all: initial; color: #ffffff; font-weight: 600; cursor:pointer; font-family: 'IBM Plex Sans', sans-serif; margin-left: 0.5rem !important; padding-top: 0.5rem !important; padding-bottom: 0.5rem !important; right:0; } #share-btn * { all: unset; } #share-btn-container div:nth-child(-n+2){ width: auto !important; min-height: 0px !important; } #share-btn-container .wrap { display: none !important; } #share-btn-container.hidden { display: none!important; } img[src*='#center'] { display: inline-block; margin: unset; } .footer { margin-bottom: 45px; margin-top: 10px; text-align: center; border-bottom: 1px solid #e5e5e5; } .footer>p { font-size: .8rem; display: inline-block; padding: 0 10px; transform: translateY(10px); background: white; } .dark .footer { border-color: #303030; } .dark .footer>p { background: #0b0f19; } """ with gr.Blocks(css=css) as demo: with gr.Column(elem_id="col-container"): gr.Markdown( """

Zeroscope Text-to-Video

A watermark-free Modelscope-based video model optimized for producing high-quality 16:9 compositions and a smooth video output.

""" ) prompt_in = gr.Textbox(label="Prompt", placeholder="Darth Vader is surfing on waves", elem_id="prompt-in") #neg_prompt = gr.Textbox(label="Negative prompt", value="text, watermark, copyright, blurry, nsfw", elem_id="neg-prompt-in") #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", elem_id="video-output") with gr.Row(): gr.Markdown(""" [![Duplicate this Space](https://huggingface.co/datasets/huggingface/badges/raw/main/duplicate-this-space-lg.svg#center)](https://huggingface.co/spaces/fffiloni/zeroscope-cloning?duplicate=true) """) gr.HTML("""

You may also like:

""") submit_btn.click(fn=infer, inputs=[prompt_in], outputs=[video_result], api_name="zrscp") demo.queue(max_size=12).launch(show_api=False)