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: Cv Diffusion Text-to-image-synthesis Tiny
+title: ModelScope Chinese text2image (tiny)
 emoji: 👀
 colorFrom: yellow
 colorTo: indigo
 sdk: gradio
-sdk_version: 3.20.0
+sdk_version: 3.20.1
 app_file: app.py
 pinned: false
 license: mit

app.py

@@ -0,0 +1,111 @@
+#!/usr/bin/env python
+
+from __future__ import annotations
+
+import os
+import shlex
+import subprocess
+
+import gradio as gr
+import numpy as np
+import torch
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+
+if os.getenv('SYSTEM') == 'spaces':
+    subprocess.run(
+        shlex.split(
+            'pip install git+https://github.com/modelscope/modelscope.git@refs/pull/173/head'
+        ))
+
+DESCRIPTION = '# [ModelScope Chinese text2image (tiny)](https://www.modelscope.cn/models/damo/cv_diffusion_text-to-image-synthesis_tiny/summary)'
+
+SPACE_ID = os.getenv('SPACE_ID')
+if SPACE_ID is not None:
+    DESCRIPTION += f'<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(Tasks.text_to_image_synthesis,
+                'damo/cv_diffusion_text-to-image-synthesis_tiny')
+
+
+def run(
+    text: str,
+    seed: int,
+    num_steps_generator: int,
+    num_steps_upscaler1: int,
+    num_steps_upscaler2: int,
+    guidance_scale: float,
+) -> np.ndarray:
+    torch.manual_seed(seed)
+    results = pipe({
+        'text': text,
+        'solver': 'ddim',
+        'generator_ddim_timesteps': num_steps_generator,
+        'upsampler_256_ddim_timesteps': num_steps_upscaler1,
+        'upsampler_1024_ddim_timesteps': num_steps_upscaler2,
+        'generator_guide_scale': guidance_scale,
+    })
+    return results['output_imgs'][0]
+
+
+examples = [
+    ['中国山水画', 0, 250, 50, 20, 5.0],
+]
+
+with gr.Blocks(css='style.css') as demo:
+    gr.Markdown(DESCRIPTION)
+    with gr.Row():
+        with gr.Column():
+            text = gr.Text(label='Prompt')
+            seed = gr.Slider(label='Seed',
+                             minimum=0,
+                             maximum=100000,
+                             value=0,
+                             step=1,
+                             randomize=True)
+            run_button = gr.Button('Run')
+            with gr.Accordion('Advanced options', open=False):
+                num_steps_generator = gr.Slider(label='Steps (Generator)',
+                                                minimum=1,
+                                                maximum=1000,
+                                                value=250,
+                                                step=1)
+                num_steps_upscaler1 = gr.Slider(
+                    label='Steps (Upscaler 64=>256)',
+                    minimum=1,
+                    maximum=50,
+                    value=50,
+                    step=1)
+                num_steps_upscaler2 = gr.Slider(
+                    label='Steps (Upscaler 256=>1024)',
+                    minimum=1,
+                    maximum=20,
+                    value=20,
+                    step=1)
+                guidance_scale = gr.Slider(label='Guidance scale',
+                                           minimum=0,
+                                           maximum=100,
+                                           value=5.0,
+                                           step=0.1)
+        with gr.Column():
+            result = gr.Image(label='Output')
+
+    inputs = [
+        text,
+        seed,
+        num_steps_generator,
+        num_steps_upscaler1,
+        num_steps_upscaler2,
+        guidance_scale,
+    ]
+    with gr.Row():
+        gr.Examples(examples=examples,
+                    inputs=inputs,
+                    outputs=result,
+                    fn=run,
+                    cache_examples=True)
+
+    text.submit(fn=run, inputs=inputs, outputs=result)
+    run_button.click(fn=run, inputs=inputs, outputs=result)
+
+demo.queue(api_open=False).launch()

requirements.txt

@@ -0,0 +1,3 @@
+decord==0.6.0
+fairseq==0.12.2
+modelscope[multi-modal]==1.3.2

style.css

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