init

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* 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
+*.png filter=lfs diff=lfs merge=lfs -text
+*.mp4 filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,163 @@
+# Extra
+_demo_temp
+
+# 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/

README.md

@@ -5,7 +5,7 @@ colorFrom: pink
 colorTo: yellow
 sdk: gradio
 sdk_version: 4.25.0
-app_file: app.py
+app_file: gradio_demo.py
 pinned: false
 license: mit
 ---

black_box_image_edit/__init__.py

@@ -0,0 +1,46 @@
+from .instructpix2pix import InstructPix2Pix, MagicBrush
+
+from typing import Union, Optional, Tuple
+import numpy as np
+from PIL import Image, ImageOps
+import os
+import requests
+
+
+
+
+def load_image(image: Union[str, Image.Image], format: str = "RGB", size: Optional[Tuple] = None) -> Image.Image:
+    """
+    Load an image from a given path or URL and convert it to a PIL Image.
+
+    Args:
+        image (Union[str, Image.Image]): The image path, URL, or a PIL Image object to be loaded.
+        format (str, optional): Desired color format of the resulting image. Defaults to "RGB".
+        size (Optional[Tuple], optional): Desired size for resizing the image. Defaults to None.
+
+    Returns:
+        Image.Image: A PIL Image in the specified format and size.
+
+    Raises:
+        ValueError: If the provided image format is not recognized.
+    """
+    if isinstance(image, str):
+        if image.startswith("http://") or image.startswith("https://"):
+            image = Image.open(requests.get(image, stream=True).raw)
+        elif os.path.isfile(image):
+            image = Image.open(image)
+        else:
+            raise ValueError(
+                f"Incorrect path or url, URLs must start with `http://` or `https://`, and {image} is not a valid path"
+            )
+    elif isinstance(image, Image.Image):
+        image = image
+    else:
+        raise ValueError(
+            "Incorrect format used for image. Should be an url linking to an image, a local path, or a PIL image."
+        )
+    image = ImageOps.exif_transpose(image)
+    image = image.convert(format)
+    if (size != None):
+        image = image.resize(size, Image.LANCZOS)
+    return image

black_box_image_edit/instructpix2pix.py

@@ -0,0 +1,67 @@
+import torch
+import PIL
+
+from diffusers import StableDiffusionInstructPix2PixPipeline, EulerAncestralDiscreteScheduler
+
+class InstructPix2Pix():
+    """
+    A wrapper around the StableDiffusionInstructPix2PixPipeline for guided image transformation.
+
+    This class uses the Pix2Pix pipeline to transform an image based on an instruction prompt.
+    Reference: https://huggingface.co/docs/diffusers/api/pipelines/pix2pix
+    """
+    def __init__(self, device="cuda", weight="timbrooks/instruct-pix2pix"):
+        """
+        Attributes:
+            pipe (StableDiffusionInstructPix2PixPipeline): The Pix2Pix pipeline for image transformation.
+
+        Args:
+            device (str, optional): Device on which the pipeline runs. Defaults to "cuda".
+            weight (str, optional): Pretrained weights for the model. Defaults to "timbrooks/instruct-pix2pix".
+        """
+        self.pipe = StableDiffusionInstructPix2PixPipeline.from_pretrained(
+            weight,
+            torch_dtype=torch.float16,
+            safety_checker=None,
+        ).to(device)
+        self.pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(
+            self.pipe.scheduler.config)
+
+    def infer_one_image(self, src_image: PIL.Image.Image = None, src_prompt: str = None, target_prompt: str = None, instruct_prompt: str = None, seed: int = 42, negative_prompt=""):
+        """
+        Modifies the source image based on the provided instruction prompt.
+
+        Args:
+            src_image (PIL.Image.Image): Source image in RGB format.
+            instruct_prompt (str): Caption for editing the image.
+            seed (int, optional): Seed for random generator. Defaults to 42.
+
+        Returns:
+            PIL.Image.Image: The transformed image.
+        """
+        src_image = src_image.convert('RGB') # force it to RGB format
+        generator = torch.manual_seed(seed)
+
+        # configs from https://github.com/timothybrooks/instruct-pix2pix/blob/main/edit_cli.py
+        image = self.pipe(instruct_prompt, image=src_image,
+                          num_inference_steps=100,
+                          image_guidance_scale=1.5,
+                          guidance_scale=7.5,
+                          negative_prompt=negative_prompt,
+                          generator=generator
+                          ).images[0]
+        return image
+
+class MagicBrush(InstructPix2Pix):
+    def __init__(self, device="cuda", weight="vinesmsuic/magicbrush-jul7"):
+        """
+        A class for MagicBrush.
+
+        Args:
+            device (str, optional): The device on which the model should run. Default is "cuda".
+            weight (str, optional): The pretrained model weights for MagicBrush. Default is "vinesmsuic/magicbrush-jul7".
+        """
+        super().__init__(device=device, weight=weight)
+
+    def infer_one_image(self, src_image: PIL.Image.Image = None, src_prompt: str = None, target_prompt: str = None, instruct_prompt: str = None, seed: int = 42, negative_prompt=""):
+        return super().infer_one_image(src_image, src_prompt, target_prompt, instruct_prompt, seed, negative_prompt)

demo/A Couple In A Public Display Of Affection.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7df2b31db9cdff7fd07310890a11f670f060bba2950c82e1a8a5ba0aee8790a3
+size 84487

demo/A kitten turning its head on a wooden floor.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16a8639d01d4383f2f83305d01d5147409b679e3c6e6d5326fa3721cc187cfe8
+size 102505

demo/An Old Man Doing Exercises For The Body And Mind.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c36eadbaef9719c7200621a31d2ec79b7cc6e6fa7af8476729153fb1ce60191d
+size 102148