Add files

.pre-commit-config.yaml

@@ -0,0 +1,37 @@
+exclude: patch
+repos:
+- repo: https://github.com/pre-commit/pre-commit-hooks
+  rev: v4.2.0
+  hooks:
+  - id: check-executables-have-shebangs
+  - id: check-json
+  - id: check-merge-conflict
+  - id: check-shebang-scripts-are-executable
+  - id: check-toml
+  - id: check-yaml
+  - id: double-quote-string-fixer
+  - id: end-of-file-fixer
+  - id: mixed-line-ending
+    args: ['--fix=lf']
+  - id: requirements-txt-fixer
+  - id: trailing-whitespace
+- repo: https://github.com/myint/docformatter
+  rev: v1.4
+  hooks:
+  - id: docformatter
+    args: ['--in-place']
+- repo: https://github.com/pycqa/isort
+  rev: 5.12.0
+  hooks:
+    - id: isort
+- repo: https://github.com/pre-commit/mirrors-mypy
+  rev: v0.991
+  hooks:
+    - id: mypy
+      args: ['--ignore-missing-imports']
+      additional_dependencies: ['types-python-slugify']
+- repo: https://github.com/google/yapf
+  rev: v0.32.0
+  hooks:
+  - id: yapf
+    args: ['--parallel', '--in-place']

.style.yapf

@@ -0,0 +1,5 @@
+[style]
+based_on_style = pep8
+blank_line_before_nested_class_or_def = false
+spaces_before_comment = 2
+split_before_logical_operator = true

README.md

@@ -1,10 +1,10 @@
 ---
-title: Modelscope Text To Video Synthesis
+title: ModelScope Text To Video Synthesis
 emoji: 🚀
 colorFrom: pink
 colorTo: pink
 sdk: gradio
-sdk_version: 3.21.0
+sdk_version: 3.22.1
 app_file: app.py
 pinned: false
 ---

app.py

@@ -0,0 +1,66 @@
+#!/usr/bin/env python
+
+from __future__ import annotations
+
+import os
+import shlex
+import subprocess
+
+import gradio as gr
+import torch
+
+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'
+        ))
+
+from modelscope.outputs import OutputKeys
+from modelscope.pipelines import pipeline
+
+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', 'damo/text-to-video-synthesis')
+
+
+def generate(prompt: str, seed: int) -> str:
+    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.Row():
+        with gr.Column():
+            prompt = gr.Text(label='Prompt', max_lines=1)
+            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.')
+            run_button = gr.Button('Run')
+        with gr.Column():
+            result = gr.Video(label='Result')
+
+    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)
+
+demo.queue(api_open=False).launch()

requirements.txt

@@ -0,0 +1,5 @@
+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

@@ -0,0 +1,3 @@
+h1 {
+  text-align: center;
+}