Spaces:
Runtime error
Runtime error
File size: 4,315 Bytes
62f5cce 965498b adfea12 62f5cce 965498b 62f5cce 9699b30 62f5cce 965498b c5d49dc 965498b 62f5cce 965498b 62f5cce adfea12 62f5cce a9c0e29 62f5cce 9699b30 25423bd 9699b30 25423bd dd86f00 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 |
#!/usr/bin/env python
from __future__ import annotations
import os
import pathlib
import random
import shlex
import subprocess
import gradio as gr
import torch
from huggingface_hub import snapshot_download
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@fe67395')
)
from modelscope.outputs import OutputKeys
from modelscope.pipelines import pipeline
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>'
pipe = pipeline('text-to-video-synthesis', model_dir.as_posix())
def generate(prompt: str, seed: int) -> str:
if seed == -1:
seed = random.randint(0, 1000000)
torch.manual_seed(seed)
return pipe({'text': prompt})[OutputKeys.OUTPUT_VIDEO]
examples = [
['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):
seed = gr.Slider(
label='Seed',
minimum=-1,
maximum=1000000,
step=1,
value=-1,
info='If set to -1, a different seed will be used each time.')
inputs = [prompt, seed]
gr.Examples(examples=examples,
inputs=inputs,
outputs=result,
fn=generate,
cache_examples=os.getenv('SYSTEM') == 'spaces')
prompt.submit(fn=generate, inputs=inputs, outputs=result)
run_button.click(fn=generate, inputs=inputs, outputs=result)
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. The model is meant for research purposes.
</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()
|