Update

.pre-commit-config.yaml

@@ -0,0 +1,36 @@
+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

.vscode/settings.json

@@ -0,0 +1,18 @@
+{
+    "python.linting.enabled": true,
+    "python.linting.flake8Enabled": true,
+    "python.linting.pylintEnabled": false,
+    "python.linting.lintOnSave": true,
+    "python.formatting.provider": "yapf",
+    "python.formatting.yapfArgs": [
+        "--style={based_on_style: pep8, indent_width: 4, blank_line_before_nested_class_or_def: false, spaces_before_comment: 2, split_before_logical_operator: true}"
+    ],
+    "[python]": {
+        "editor.formatOnType": true,
+        "editor.codeActionsOnSave": {
+            "source.organizeImports": true
+        }
+    },
+    "editor.formatOnSave": true,
+    "files.insertFinalNewline": true
+}

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 hysts
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -1,5 +1,5 @@
 ---
-title: Kandinsky 2 1
+title: Kandinsky 2.1
 emoji: 📚
 colorFrom: purple
 colorTo: green
@@ -7,6 +7,8 @@ sdk: gradio
 sdk_version: 3.36.1
 app_file: app.py
 pinned: false
+license: mit
+suggested_hardware: t4-small
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,211 @@
+#!/usr/bin/env python
+
+from __future__ import annotations
+
+import os
+import random
+
+import gradio as gr
+import numpy as np
+import PIL.Image
+import torch
+from diffusers import DDPMScheduler, DiffusionPipeline
+
+DESCRIPTION = '# Kandinsky 2.1'
+if not torch.cuda.is_available():
+    DESCRIPTION += '\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>'
+
+MAX_SEED = np.iinfo(np.int32).max
+CACHE_EXAMPLES = torch.cuda.is_available() and os.getenv(
+    'CACHE_EXAMPLES') == '1'
+MAX_IMAGE_SIZE = int(os.getenv('MAX_IMAGE_SIZE', '768'))
+USE_TORCH_COMPILE = os.getenv('USE_TORCH_COMPILE') == '1'
+
+device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
+if torch.cuda.is_available():
+    pipe_prior = DiffusionPipeline.from_pretrained(
+        'kandinsky-community/kandinsky-2-1-prior', torch_dtype=torch.float16)
+    pipe_prior.to(device)
+
+    scheduler = DDPMScheduler.from_pretrained(
+        'kandinsky-community/kandinsky-2-1', subfolder='ddpm_scheduler')
+    pipe = DiffusionPipeline.from_pretrained(
+        'kandinsky-community/kandinsky-2-1',
+        scheduler=scheduler,
+        torch_dtype=torch.float16)
+    pipe.to(device)
+    if USE_TORCH_COMPILE:
+        pipe.unet.to(memory_format=torch.channels_last)
+        pipe.unet = torch.compile(pipe.unet,
+                                  mode='reduce-overhead',
+                                  fullgraph=True)
+else:
+    pipe_prior = None
+    pipe = None
+
+
+def randomize_seed_fn(seed: int, randomize_seed: bool) -> int:
+    if randomize_seed:
+        seed = random.randint(0, MAX_SEED)
+    return seed
+
+
+def generate(prompt: str,
+             negative_prompt: str = 'low quality, bad quality',
+             seed: int = 0,
+             width: int = 768,
+             height: int = 768,
+             guidance_scale_prior: float = 1.0,
+             guidance_scale: float = 4.0,
+             num_inference_steps_prior: int = 50,
+             num_inference_steps: int = 100) -> PIL.Image.Image:
+    generator = torch.Generator().manual_seed(seed)
+    image_embeds, negative_image_embeds = pipe_prior(
+        prompt,
+        negative_prompt,
+        generator=generator,
+        guidance_scale=guidance_scale_prior,
+        num_inference_steps=num_inference_steps_prior,
+    ).to_tuple()
+    image = pipe(
+        prompt=prompt,
+        image_embeds=image_embeds,
+        negative_image_embeds=negative_image_embeds,
+        height=height,
+        width=width,
+        generator=generator,
+        guidance_scale=guidance_scale,
+        num_inference_steps=num_inference_steps,
+    ).images[0]
+    return image
+
+
+examples = [
+    'An astronaut riding a horse',
+    'portrait of a young woman, blue eyes, cinematic',
+    'A alien cheeseburger creature eating itself, claymation, cinematic, moody lighting',
+    'bird eye view shot of a full body woman with cyan light orange magenta makeup, digital art, long braided hair her face separated by makeup in the style of yin Yang surrealism, symmetrical face, real image, contrasting tone, pastel gradient background',
+    'A car exploding into colorful dust',
+    'editorial photography of an organic, almost liquid smoke style armchair',
+    'birds eye view of a quilted paper style alien planet landscape, vibrant colours, Cinematic lighting',
+]
+
+with gr.Blocks(css='style.css') as demo:
+    gr.Markdown(DESCRIPTION)
+    gr.DuplicateButton(value='Duplicate Space for private use',
+                       elem_id='duplicate-button',
+                       visible=os.getenv('SHOW_DUPLICATE_BUTTON') == '1')
+    with gr.Box():
+        with gr.Row():
+            prompt = gr.Text(
+                label='Prompt',
+                show_label=False,
+                max_lines=1,
+                placeholder='Enter your prompt',
+                container=False,
+            )
+            run_button = gr.Button('Run', scale=0)
+        result = gr.Image(label='Result', show_label=False)
+        with gr.Accordion('Advanced options', open=False):
+            negative_prompt = gr.Text(
+                label='Negative prompt',
+                value='low quality, bad quality',
+                max_lines=1,
+                placeholder='Enter a negative prompt',
+            )
+            seed = gr.Slider(label='Seed',
+                             minimum=0,
+                             maximum=MAX_SEED,
+                             step=1,
+                             value=0)
+            randomize_seed = gr.Checkbox(label='Randomize seed', value=True)
+            width = gr.Slider(
+                label='Width',
+                minimum=256,
+                maximum=MAX_IMAGE_SIZE,
+                step=32,
+                value=768,
+            )
+            height = gr.Slider(
+                label='Height',
+                minimum=256,
+                maximum=MAX_IMAGE_SIZE,
+                step=32,
+                value=768,
+            )
+            guidance_scale_prior = gr.Slider(label='Guidance scale for prior',
+                                             minimum=1,
+                                             maximum=20,
+                                             step=0.1,
+                                             value=4.0)
+            guidance_scale = gr.Slider(label='Guidance scale',
+                                       minimum=1,
+                                       maximum=20,
+                                       step=0.1,
+                                       value=4.0)
+            num_inference_steps_prior = gr.Slider(
+                label='Number of inference steps for prior',
+                minimum=10,
+                maximum=100,
+                step=1,
+                value=50)
+            num_inference_steps = gr.Slider(label='Number of inference steps',
+                                            minimum=10,
+                                            maximum=150,
+                                            step=1,
+                                            value=100)
+
+    gr.Examples(examples=examples,
+                inputs=prompt,
+                outputs=result,
+                fn=generate,
+                cache_examples=CACHE_EXAMPLES)
+
+    inputs = [
+        prompt,
+        negative_prompt,
+        seed,
+        width,
+        height,
+        guidance_scale_prior,
+        guidance_scale,
+        num_inference_steps_prior,
+        num_inference_steps,
+    ]
+    prompt.submit(
+        fn=randomize_seed_fn,
+        inputs=[seed, randomize_seed],
+        outputs=seed,
+        queue=False,
+        api_name=False,
+    ).then(
+        fn=generate,
+        inputs=inputs,
+        outputs=result,
+        api_name='run',
+    )
+    negative_prompt.submit(
+        fn=randomize_seed_fn,
+        inputs=[seed, randomize_seed],
+        outputs=seed,
+        queue=False,
+        api_name=False,
+    ).then(
+        fn=generate,
+        inputs=inputs,
+        outputs=result,
+        api_name=False,
+    )
+    run_button.click(
+        fn=randomize_seed_fn,
+        inputs=[seed, randomize_seed],
+        outputs=seed,
+        queue=False,
+        api_name=False,
+    ).then(
+        fn=generate,
+        inputs=inputs,
+        outputs=result,
+        api_name=False,
+    )
+demo.queue(max_size=20).launch()

requirements.txt

@@ -0,0 +1,6 @@
+accelerate==0.20.3
+diffusers==0.18.2
+gradio==3.36.1
+torch==2.0.1
+torchvision==0.15.2
+transformers==4.30.2

style.css

@@ -0,0 +1,16 @@
+h1 {
+  text-align: center;
+}
+
+#component-0 {
+  max-width: 730px;
+  margin: auto;
+  padding-top: 1.5rem;
+}
+
+#duplicate-button {
+  margin: auto;
+  color: white;
+  background: #1565c0;
+  border-radius: 100vh;
+}