Duplicate from Linaqruf/Animagine-XL

Co-authored-by: Linaqruf <[email protected]>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,162 @@
+gradio_cached_examples/
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

.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

@@ -0,0 +1,17 @@
+---
+title: Animagine-XL
+emoji: 🌍
+colorFrom: gray
+colorTo: purple
+sdk: gradio
+sdk_version: 3.39.0
+app_file: app.py
+license: mit
+pinned: false
+suggested_hardware: a10g-small
+duplicated_from: Linaqruf/Animagine-XL
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+
+https://arxiv.org/abs/2307.01952

app.py

@@ -0,0 +1,329 @@
+#!/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.models import AutoencoderKL
+from diffusers import StableDiffusionXLPipeline, EulerAncestralDiscreteScheduler
+
+DESCRIPTION = '# Animagine XL'
+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', '2048'))
+USE_TORCH_COMPILE = os.getenv('USE_TORCH_COMPILE') == '1'
+ENABLE_CPU_OFFLOAD = os.getenv('ENABLE_CPU_OFFLOAD') == '1'
+
+MODEL = "Linaqruf/animagine-xl"
+
+device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
+if torch.cuda.is_available():
+    pipe = StableDiffusionXLPipeline.from_pretrained(
+        MODEL,
+        torch_dtype=torch.float16,
+        use_safetensors=True,
+        variant='fp16')
+
+    pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config)
+    
+    if ENABLE_CPU_OFFLOAD:
+        pipe.enable_model_cpu_offload()
+    else:
+        pipe.to(device)
+
+    if USE_TORCH_COMPILE:
+        pipe.unet = torch.compile(pipe.unet,
+                                  mode='reduce-overhead',
+                                  fullgraph=True)
+else:
+    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 = '',
+             prompt_2: str = '',
+             negative_prompt_2: str = '',
+             use_prompt_2: bool = False,
+             seed: int = 0,
+             width: int = 1024,
+             height: int = 1024,
+             target_width: int = 1024,
+             target_height: int = 1024,
+             original_width: int = 4096,
+             original_height: int = 4096,
+             guidance_scale_base: float = 12.0,
+             num_inference_steps_base: int = 50) -> PIL.Image.Image:
+    
+    generator = torch.Generator().manual_seed(seed)
+
+    if negative_prompt == '':
+        negative_prompt = None  # type: ignore
+    if not use_prompt_2:
+        prompt_2 = None  # type: ignore
+        negative_prompt_2 = None  # type: ignore
+    if negative_prompt_2 == '':
+        negative_prompt_2 = None  
+
+    return pipe(prompt=prompt,
+                    negative_prompt=negative_prompt,
+                    prompt_2=prompt_2,
+                    negative_prompt_2=negative_prompt_2,
+                    width=width,
+                    height=height,
+                    target_size=(target_width, target_height),
+                    original_size=(original_width, original_height),
+                    guidance_scale=guidance_scale_base,
+                    num_inference_steps=num_inference_steps_base,
+                    generator=generator,
+                    output_type='pil').images[0]
+
+
+examples = [
+    'face focus, cute, masterpiece, best quality, 1girl, green hair, sweater, looking at viewer, upper body, beanie, outdoors, night, turtleneck',
+    'face focus, bishounen, masterpiece, best quality, 1boy, green hair, sweater, looking at viewer, upper body, beanie, outdoors, night, turtleneck',
+]
+
+# choices = [
+#     "Vertical (9:16)",
+#     "Portrait (4:5)",
+#     "Square (1:1)",
+#     "Photo (4:3)",
+#     "Landscape (3:2)",
+#     "Widescreen (16:9)",
+#     "Cinematic (21:9)",
+# ]
+
+# choice_to_size = {
+#     "Vertical (9:16)": (768, 1344),
+#     "Portrait (4:5)": (912, 1144),
+#     "Square (1:1)": (1024, 1024),
+#     "Photo (4:3)": (1184, 888),
+#     "Landscape (3:2)": (1256, 832),
+#     "Widescreen (16:9)": (1368, 768),
+#     "Cinematic (21:9)": (1568, 672),
+# }
+
+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.Row():
+        with gr.Column(scale=1):
+            prompt = gr.Text(
+                label='Prompt',
+                max_lines=1,
+                placeholder='Enter your prompt',
+            )
+            negative_prompt = gr.Text(
+                label='Negative Prompt',
+                max_lines=1,
+                placeholder='Enter a negative prompt',
+                value='lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry',
+            )
+            use_prompt_2 = gr.Checkbox(
+                label='Use prompt 2', 
+                value=False
+            )   
+            prompt_2 = gr.Text(
+                label='Prompt 2',
+                max_lines=1,
+                placeholder='Enter your prompt',
+                visible=False,
+            )
+            negative_prompt_2 = gr.Text(
+                label='Negative prompt 2',
+                max_lines=1,
+                placeholder='Enter a negative prompt',
+                visible=False,
+            )
+
+            # with gr.Row():
+            #     aspect_ratio = gr.Dropdown(choices=choices, label="Aspect Ratio Preset", value=choices[2])
+            with gr.Row():
+                width = gr.Slider(
+                    label='Width',
+                    minimum=256,
+                    maximum=MAX_IMAGE_SIZE,
+                    step=32,
+                    value=1024,
+                )
+                height = gr.Slider(
+                    label='Height',
+                    minimum=256,
+                    maximum=MAX_IMAGE_SIZE,
+                    step=32,
+                    value=1024,
+                )
+            with gr.Accordion(label='Advanced Config', open=False):
+                with gr.Accordion(label='Conditioning Resolution', open=False):
+                    with gr.Row():
+                        original_width = gr.Slider(
+                            label='Original Width',
+                            minimum=1024,
+                            maximum=4096,
+                            step=32,
+                            value=4096,
+                        )
+                        original_height = gr.Slider(
+                            label='Original Height',
+                            minimum=1024,
+                            maximum=4096,
+                            step=32,
+                            value=4096,
+                        )
+                    with gr.Row():
+                        target_width = gr.Slider(
+                            label='Target Width',
+                            minimum=1024,
+                            maximum=4096,
+                            step=32,
+                            value=1024,
+                            )
+                        target_height = gr.Slider(
+                            label='Target Height',
+                            minimum=1024,
+                            maximum=4096,
+                            step=32,
+                            value=1024,
+                        )
+                seed = gr.Slider(label='Seed',
+                                minimum=0,
+                                maximum=MAX_SEED,
+                                step=1,
+                                value=0)
+                
+                randomize_seed = gr.Checkbox(label='Randomize seed', value=True)
+                with gr.Row():
+                    guidance_scale_base = gr.Slider(
+                        label='Guidance scale',
+                        minimum=1,
+                        maximum=20,
+                        step=0.1,
+                        value=12.0)
+                    num_inference_steps_base = gr.Slider(
+                        label='Number of inference steps',
+                        minimum=10,
+                        maximum=100,
+                        step=1,
+                        value=50)
+
+        with gr.Column(scale=2):
+            with gr.Blocks():
+                run_button = gr.Button('Generate')
+            result = gr.Image(label='Result', show_label=False)
+
+    gr.Examples(examples=examples,
+                inputs=prompt,
+                outputs=result,
+                fn=generate,
+                cache_examples=CACHE_EXAMPLES)
+    
+    use_prompt_2.change(
+        fn=lambda x: gr.update(visible=x),
+        inputs=use_prompt_2,
+        outputs=prompt_2,
+        queue=False,
+        api_name=False,
+    )
+    use_prompt_2.change(
+        fn=lambda x: gr.update(visible=x),
+        inputs=use_prompt_2,
+        outputs=negative_prompt_2,
+        queue=False,
+        api_name=False,
+    )
+
+    inputs = [
+        prompt,
+        negative_prompt,
+        prompt_2,
+        negative_prompt_2,
+        use_prompt_2,
+        seed,
+        width,
+        height,
+        target_width,
+        target_height,
+        original_width,
+        original_height,
+        guidance_scale_base,
+        num_inference_steps_base,
+    ]
+    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,
+    )
+    prompt_2.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,
+    )
+    negative_prompt_2.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 +1,7 @@
+accelerate==0.21.0
+diffusers==0.19.0
+gradio==3.39.0
+invisible-watermark==0.2.0
+Pillow==10.0.0
+torch==2.0.1
+transformers==4.31.0

style.css

@@ -0,0 +1,25 @@
+h1 {
+  text-align: center;
+  font-size: 10vw; /* relative to the viewport width */
+}
+
+#duplicate-button {
+  margin: auto;
+  color: #fff;
+  background: #1565c0;
+  border-radius: 100vh;
+}
+
+#component-0 {
+  max-width: 80%; /* relative to the parent element's width */
+  margin: auto;
+  padding-top: 1.5rem;
+}
+
+/* You can also use media queries to adjust your style for different screen sizes */
+@media (max-width: 600px) {
+  #component-0 {
+    max-width: 90%;
+    padding-top: 1rem;
+  }
+}