Spaces:
Running
on
A10G
Running
on
A10G
| import gradio as gr | |
| 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() | |
| caption = gr.load(name="spaces/fffiloni/CoCa-clone") | |
| def create_image_caption(image_init): | |
| cap = caption(image_init, "Nucleus sampling", 1.2, 0.5, 5, 20, fn_index=0) | |
| print("cap: " + cap) | |
| return cap | |
| 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(image_init): | |
| prompt = create_image_caption(image_init) | |
| video_frames = pipe(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 prompt, 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: 13rem; | |
| } | |
| #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: block; | |
| margin: auto; | |
| } | |
| """ | |
| with gr.Blocks(css=css) as demo: | |
| with gr.Column(elem_id="col-container"): | |
| gr.Markdown( | |
| """ | |
| <h1 style="text-align: center;">Zeroscope Image-to-Video</h1> | |
| <p style="text-align: center;"> | |
| A watermark-free Modelscope-based video model optimized for producing high-quality 16:9 compositions and a smooth video output. <br /> | |
| This demo is a variation that lets you upload an image as reference for video generation. | |
| </p> | |
| [](https://huggingface.co/spaces/fffiloni/zeroscope-img-to-video?duplicate=true) | |
| """ | |
| ) | |
| image_init = gr.Image(label="Image Init",type="filepath", source="upload", elem_id="image-init") | |
| #inference_steps = gr.Slider(label="Inference Steps", minimum=10, maximum=100, step=1, value=40, interactive=False) | |
| submit_btn = gr.Button("Submit") | |
| coca_cap = gr.Textbox(label="Caption", placeholder="CoCa Caption will be displayed here", elem_id="coca-cap-in") | |
| video_result = gr.Video(label="Video Output", elem_id="video-output") | |
| submit_btn.click(fn=infer, | |
| inputs=[image_init], | |
| outputs=[coca_cap, video_result]) | |
| demo.queue(max_size=12).launch() | |