Share button

README.md

@@ -4,7 +4,7 @@ emoji: 🚀
 colorFrom: pink
 colorTo: pink
 sdk: gradio
-sdk_version: 3.23.0
+sdk_version: 3.22.1
 app_file: app.py
 pinned: false
 ---

app.py

@@ -3,75 +3,57 @@
 from __future__ import annotations
 
 import os
+import pathlib
 import random
-import tempfile
+import shlex
+import subprocess
 
 import gradio as gr
-import imageio
-import numpy as np
 import torch
-from diffusers import DiffusionPipeline, DPMSolverMultistepScheduler
+from huggingface_hub import snapshot_download
 
-DESCRIPTION = '# [ModelScope Text to Video Synthesis](https://modelscope.cn/models/damo/text-to-video-synthesis/summary)'
-DESCRIPTION += '\n<p>For Colab usage, you can view <a href="https://colab.research.google.com/drive/1uW1ZqswkQ9Z9bp5Nbo5z59cAn7I0hE6R?usp=sharing" style="text-decoration: underline;" target="_blank">this webpage</a>.（the latest update on 2023.03.21）</p>'
-DESCRIPTION += '\n<p>This model can only be used for non-commercial purposes. To learn more about the model, take a look at the <a href="https://huggingface.co/damo-vilab/modelscope-damo-text-to-video-synthesis" style="text-decoration: underline;" target="_blank">model card</a>.</p>'
-if (SPACE_ID := os.getenv('SPACE_ID')) is not None:
-    DESCRIPTION += f'\n<p>For faster inference without waiting in queue, you may duplicate the space and upgrade to GPU in settings. <a href="https://huggingface.co/spaces/{SPACE_ID}?duplicate=true"><img style="display: inline; margin-top: 0em; margin-bottom: 0em" src="https://bit.ly/3gLdBN6" alt="Duplicate Space" /></a></p>'
+if os.getenv('SYSTEM') == 'spaces':
+    subprocess.run(shlex.split('pip uninstall -y modelscope'))
+    subprocess.run(
+        shlex.split(
+            'pip install git+https://github.com/modelscope/modelscope.git@refs/pull/207/head'
+        ))
 
-MAX_NUM_FRAMES = int(os.getenv('MAX_NUM_FRAMES', '200'))
-DEFAULT_NUM_FRAMES = min(MAX_NUM_FRAMES,
-                         int(os.getenv('DEFAULT_NUM_FRAMES', '16')))
+from modelscope.outputs import OutputKeys
+from modelscope.pipelines import pipeline
 
-pipe = DiffusionPipeline.from_pretrained('damo-vilab/text-to-video-ms-1.7b',
-                                         torch_dtype=torch.float16,
-                                         variant='fp16')
-pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)
-pipe.enable_model_cpu_offload()
-pipe.enable_vae_slicing()
+model_dir = pathlib.Path('weights')
+if not model_dir.exists():
+    model_dir.mkdir()
+    snapshot_download('damo-vilab/modelscope-damo-text-to-video-synthesis',
+                      repo_type='model',
+                      local_dir=model_dir)
 
+DESCRIPTION = '# [ModelScope Text to Video Synthesis](https://modelscope.cn/models/damo/text-to-video-synthesis/summary)'
+if (SPACE_ID := os.getenv('SPACE_ID')) is not None:
+    DESCRIPTION += f'\n<p>For faster inference without waiting in queue, you may duplicate the space and upgrade to GPU in settings. <a href="https://huggingface.co/spaces/{SPACE_ID}?duplicate=true"><img style="display: inline; margin-top: 0em; margin-bottom: 0em" src="https://bit.ly/3gLdBN6" alt="Duplicate Space" /></a></p>'
 
-def to_video(frames: list[np.ndarray], fps: int) -> str:
-    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
+pipe = pipeline('text-to-video-synthesis', model_dir.as_posix())
 
 
-def generate(prompt: str, seed: int, num_frames: int,
-             num_inference_steps: int) -> str:
+def generate(prompt: str, seed: int) -> str:
     if seed == -1:
         seed = random.randint(0, 1000000)
-    generator = torch.Generator().manual_seed(seed)
-    frames = pipe(prompt,
-                  num_inference_steps=num_inference_steps,
-                  num_frames=num_frames,
-                  generator=generator).frames
-    return to_video(frames, 8)
+    torch.manual_seed(seed)
+    return pipe({'text': prompt})[OutputKeys.OUTPUT_VIDEO]
 
 
 examples = [
-    ['An astronaut riding a horse.', 0, 16, 25],
-    ['A panda eating bamboo on a rock.', 0, 16, 25],
-    ['Spiderman is surfing.', 0, 16, 25],
+    ['An astronaut riding a horse.', 0],
+    ['A panda eating bamboo on a rock.', 0],
+    ['Spiderman is surfing.', 0],
 ]
 
 with gr.Blocks(css='style.css') as demo:
     gr.Markdown(DESCRIPTION)
-    with gr.Group():
-        with gr.Box():
-            with gr.Row(elem_id='prompt-container').style(equal_height=True):
-                prompt = gr.Text(
-                    label='Prompt',
-                    show_label=False,
-                    max_lines=1,
-                    placeholder='Enter your prompt',
-                    elem_id='prompt-text-input').style(container=False)
-                run_button = gr.Button('Generate video').style(
-                    full_width=False)
-        result = gr.Video(label='Result', show_label=False, elem_id='gallery')
-        with gr.Accordion('Advanced options', open=False):
+    with gr.Row():
+        with gr.Column():
+            prompt = gr.Text(label='Prompt', max_lines=1)
             seed = gr.Slider(
                 label='Seed',
                 minimum=-1,
@@ -79,27 +61,11 @@ with gr.Blocks(css='style.css') as demo:
                 step=1,
                 value=-1,
                 info='If set to -1, a different seed will be used each time.')
-            num_frames = gr.Slider(
-                label='Number of frames',
-                minimum=16,
-                maximum=MAX_NUM_FRAMES,
-                step=1,
-                value=16,
-                info=
-                'Note that the content of the video also changes when you change the number of frames.'
-            )
-            num_inference_steps = gr.Slider(label='Number of inference steps',
-                                            minimum=10,
-                                            maximum=50,
-                                            step=1,
-                                            value=25)
-
-    inputs = [
-        prompt,
-        seed,
-        num_frames,
-        num_inference_steps,
-    ]
+            run_button = gr.Button('Run')
+        with gr.Column():
+            result = gr.Video(label='Result')
+
+    inputs = [prompt, seed]
     gr.Examples(examples=examples,
                 inputs=inputs,
                 outputs=result,
@@ -109,32 +75,4 @@ with gr.Blocks(css='style.css') as demo:
     prompt.submit(fn=generate, inputs=inputs, outputs=result)
     run_button.click(fn=generate, inputs=inputs, outputs=result)
 
-
-    with gr.Accordion(label='We are hiring(Based in Beijing / Hangzhou, China.)', open=False):
-        gr.HTML("""<div class="acknowledgments">
-                    <p>
-                        If you're looking for an exciting challenge and the opportunity to work with cutting-edge technologies in AIGC and large-scale pretraining, then we are the place for you. We are looking for talented, motivated and creative individuals to join our team. If you are interested, please send your CV to us.
-                    </p>
-                    <p>
-                        <b>EMAIL: yingya.zyy@alibaba-inc.com</b>.
-                    </p>
-                   </div>
-                """)
-    
-    with gr.Accordion(label='Biases and content acknowledgment', open=False):
-        gr.HTML("""<div class="acknowledgments">
-                    <h4>Biases and content acknowledgment</h4>
-                    <p>
-                        Despite how impressive being able to turn text into video is, beware to the fact that this model may output content that reinforces or exacerbates societal biases. The training data includes LAION5B, ImageNet, Webvid and other public datasets. The model was not trained to realistically represent people or events, so using it to generate such content is beyond the model's capabilities.
-                    </p>
-                    <p>
-                        It is not intended to generate content that is demeaning or harmful to people or their environment, culture, religion, etc. Similarly, it is not allowed to generate pornographic, violent and bloody content generation. <b>The model is meant for research purposes</b>.
-                    </p>
-                    <p>
-                        To learn more about the model, head to its <a href="https://huggingface.co/damo-vilab/modelscope-damo-text-to-video-synthesis" style="text-decoration: underline;" target="_blank">model card</a>.
-                    </p>
-                   </div>
-                """)
-
-        
 demo.queue(api_open=False, max_size=15).launch()

requirements.txt

@@ -1,8 +1,5 @@
-accelerate==0.17.1
-git+https://github.com/huggingface/diffusers@9dc8444
-gradio==3.23.0
-huggingface-hub==0.13.3
-imageio[ffmpeg]==2.26.1
-torch==2.0.0
-torchvision==0.15.1
-transformers==4.27.2
+decord==0.6.0
+fairseq==0.12.2
+gradio==3.22.1
+modelscope[multi-modal]==1.4.1
+open_clip_torch==2.16.0

style.css

@@ -1,191 +1,3 @@
-/*
-This CSS file is copied from here:
-https://huggingface.co/spaces/stabilityai/stable-diffusion/blob/2794a3c3ba66115c307075098e713f572b08bf80/app.py
-*/
-
 h1 {
-    text-align: center;
-}
-
-.gradio-container {
-    font-family: 'IBM Plex Sans', sans-serif;
-}
-
-.gr-button {
-    color: white;
-    border-color: black;
-    background: black;
-}
-
-input[type='range'] {
-    accent-color: black;
-}
-
-.dark input[type='range'] {
-    accent-color: #dfdfdf;
-}
-
-.container {
-    max-width: 730px;
-    margin: auto;
-    padding-top: 1.5rem;
-}
-
-#gallery {
-    min-height: 22rem;
-    margin-bottom: 15px;
-    margin-left: auto;
-    margin-right: auto;
-    border-bottom-right-radius: .5rem !important;
-    border-bottom-left-radius: .5rem !important;
-}
-
-#gallery>div>.h-full {
-    min-height: 20rem;
-}
-
-.details:hover {
-    text-decoration: underline;
-}
-
-.gr-button {
-    white-space: nowrap;
-}
-
-.gr-button:focus {
-    border-color: rgb(147 197 253 / var(--tw-border-opacity));
-    outline: none;
-    box-shadow: var(--tw-ring-offset-shadow), var(--tw-ring-shadow), var(--tw-shadow, 0 0 #0000);
-    --tw-border-opacity: 1;
-    --tw-ring-offset-shadow: var(--tw-ring-inset) 0 0 0 var(--tw-ring-offset-width) var(--tw-ring-offset-color);
-    --tw-ring-shadow: var(--tw-ring-inset) 0 0 0 calc(3px var(--tw-ring-offset-width)) var(--tw-ring-color);
-    --tw-ring-color: rgb(191 219 254 / var(--tw-ring-opacity));
-    --tw-ring-opacity: .5;
-}
-
-#advanced-btn {
-    font-size: .7rem !important;
-    line-height: 19px;
-    margin-top: 12px;
-    margin-bottom: 12px;
-    padding: 2px 8px;
-    border-radius: 14px !important;
-}
-
-#advanced-options {
-    display: none;
-    margin-bottom: 20px;
-}
-
-.footer {
-    margin-bottom: 45px;
-    margin-top: 35px;
-    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;
-}
-
-.acknowledgments h4 {
-    margin: 1.25em 0 .25em 0;
-    font-weight: bold;
-    font-size: 115%;
-}
-
-.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;
-    width: 13rem;
-    margin-top: 10px;
-    margin-left: auto;
-}
-
-#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: 0.25rem !important;
-    padding-bottom: 0.25rem !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;
-}
-
-.gr-form {
-    flex: 1 1 50%;
-    border-top-right-radius: 0;
-    border-bottom-right-radius: 0;
-}
-
-#prompt-container {
-    gap: 0;
-}
-
-#prompt-text-input,
-#negative-prompt-text-input {
-    padding: .45rem 0.625rem
-}
-
-#component-16 {
-    border-top-width: 1px !important;
-    margin-top: 1em
-}
-
-.image_duplication {
-    position: absolute;
-    width: 100px;
-    left: 50px
-}
-
-#component-0 {
-    max-width: 730px;
-    margin: auto;
-    padding-top: 1.5rem;
+  text-align: center;
 }