Duplicate from AttendAndExcite/Attend-and-Excite

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

.gitattributes

@@ -0,0 +1,34 @@
+*.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
+*.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 +1,163 @@
+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 +1,37 @@
+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

.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
+}

README.md

@@ -0,0 +1,15 @@
+---
+title: Attend And Excite
+emoji: 💻
+colorFrom: gray
+colorTo: pink
+sdk: gradio
+sdk_version: 3.34.0
+python_version: 3.10.11
+app_file: app.py
+pinned: false
+license: mit
+duplicated_from: AttendAndExcite/Attend-and-Excite
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,215 @@
+#!/usr/bin/env python
+
+from __future__ import annotations
+
+import os
+
+import gradio as gr
+import PIL.Image
+
+from model import Model
+
+DESCRIPTION = '''# Attend-and-Excite
+This is a demo for [Attend-and-Excite](https://arxiv.org/abs/2301.13826).
+Attend-and-Excite performs attention-based generative semantic guidance to mitigate subject neglect in Stable Diffusion.
+Select a prompt and a set of indices matching the subjects you wish to strengthen (the `Check token indices` cell can help map between a word and its index).
+'''
+
+model = Model()
+
+
+def process_example(
+    prompt: str,
+    indices_to_alter_str: str,
+    seed: int,
+    apply_attend_and_excite: bool,
+) -> tuple[list[tuple[int, str]], PIL.Image.Image]:
+    num_steps = 50
+    guidance_scale = 7.5
+
+    token_table = model.get_token_table(prompt)
+    result = model.run(prompt, indices_to_alter_str, seed,
+                       apply_attend_and_excite, num_steps, guidance_scale)
+    return token_table, result
+
+
+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,
+                placeholder=
+                'A pod of dolphins leaping out of the water in an ocean with a ship on the background'
+            )
+            with gr.Accordion(label='Check token indices', open=False):
+                show_token_indices_button = gr.Button('Show token indices')
+                token_indices_table = gr.Dataframe(label='Token indices',
+                                                   headers=['Index', 'Token'],
+                                                   col_count=2)
+            token_indices_str = gr.Text(
+                label=
+                'Token indices (a comma-separated list indices of the tokens you wish to alter)',
+                max_lines=1,
+                placeholder='4,16')
+            seed = gr.Slider(label='Seed',
+                             minimum=0,
+                             maximum=100000,
+                             value=0,
+                             step=1)
+            apply_attend_and_excite = gr.Checkbox(
+                label='Apply Attend-and-Excite', value=True)
+            num_steps = gr.Slider(label='Number of steps',
+                                  minimum=0,
+                                  maximum=100,
+                                  step=1,
+                                  value=50)
+            guidance_scale = gr.Slider(label='CFG scale',
+                                       minimum=0,
+                                       maximum=50,
+                                       step=0.1,
+                                       value=7.5)
+            run_button = gr.Button('Generate')
+        with gr.Column():
+            result = gr.Image(label='Result')
+
+    with gr.Row():
+        examples = [
+            [
+                'A mouse and a red car',
+                '2,6',
+                2098,
+                True,
+            ],
+            [
+                'A mouse and a red car',
+                '2,6',
+                2098,
+                False,
+            ],
+            [
+                'A horse and a dog',
+                '2,5',
+                123,
+                True,
+            ],
+            [
+                'A horse and a dog',
+                '2,5',
+                123,
+                False,
+            ],
+            [
+                'A painting of an elephant with glasses',
+                '5,7',
+                123,
+                True,
+            ],
+            [
+                'A painting of an elephant with glasses',
+                '5,7',
+                123,
+                False,
+            ],
+            [
+                'A playful kitten chasing a butterfly in a wildflower meadow',
+                '3,6,10',
+                123,
+                True,
+            ],
+            [
+                'A playful kitten chasing a butterfly in a wildflower meadow',
+                '3,6,10',
+                123,
+                False,
+            ],
+            [
+                'A grizzly bear catching a salmon in a crystal clear river surrounded by a forest',
+                '2,6,15',
+                123,
+                True,
+            ],
+            [
+                'A grizzly bear catching a salmon in a crystal clear river surrounded by a forest',
+                '2,6,15',
+                123,
+                False,
+            ],
+            [
+                'A pod of dolphins leaping out of the water in an ocean with a ship on the background',
+                '4,16',
+                123,
+                True,
+            ],
+            [
+                'A pod of dolphins leaping out of the water in an ocean with a ship on the background',
+                '4,16',
+                123,
+                False,
+            ],
+        ]
+        gr.Examples(examples=examples,
+                    inputs=[
+                        prompt,
+                        token_indices_str,
+                        seed,
+                        apply_attend_and_excite,
+                    ],
+                    outputs=[
+                        token_indices_table,
+                        result,
+                    ],
+                    fn=process_example,
+                    cache_examples=os.getenv('CACHE_EXAMPLES') == '1',
+                    examples_per_page=20)
+
+    show_token_indices_button.click(
+        fn=model.get_token_table,
+        inputs=prompt,
+        outputs=token_indices_table,
+        queue=False,
+    )
+
+    inputs = [
+        prompt,
+        token_indices_str,
+        seed,
+        apply_attend_and_excite,
+        num_steps,
+        guidance_scale,
+    ]
+    prompt.submit(
+        fn=model.get_token_table,
+        inputs=prompt,
+        outputs=token_indices_table,
+        queue=False,
+    ).then(
+        fn=model.run,
+        inputs=inputs,
+        outputs=result,
+    )
+    token_indices_str.submit(
+        fn=model.get_token_table,
+        inputs=prompt,
+        outputs=token_indices_table,
+        queue=False,
+    ).then(
+        fn=model.run,
+        inputs=inputs,
+        outputs=result,
+    )
+    run_button.click(
+        fn=model.get_token_table,
+        inputs=prompt,
+        outputs=token_indices_table,
+        queue=False,
+    ).then(
+        fn=model.run,
+        inputs=inputs,
+        outputs=result,
+        api_name='run',
+    )
+
+demo.queue(max_size=10).launch()

model.py

@@ -0,0 +1,67 @@
+from __future__ import annotations
+
+import PIL.Image
+import torch
+from diffusers import (StableDiffusionAttendAndExcitePipeline,
+                       StableDiffusionPipeline)
+
+
+class Model:
+    def __init__(self):
+        self.device = torch.device(
+            'cuda:0' if torch.cuda.is_available() else 'cpu')
+        model_id = 'CompVis/stable-diffusion-v1-4'
+        self.ax_pipe = StableDiffusionAttendAndExcitePipeline.from_pretrained(
+            model_id)
+        self.ax_pipe.to(self.device)
+        self.sd_pipe = StableDiffusionPipeline.from_pretrained(model_id)
+        self.sd_pipe.to(self.device)
+
+    def get_token_table(self, prompt: str):
+        tokens = [
+            self.ax_pipe.tokenizer.decode(t)
+            for t in self.ax_pipe.tokenizer(prompt)['input_ids']
+        ]
+        tokens = tokens[1:-1]
+        return list(enumerate(tokens, start=1))
+
+    def run(
+        self,
+        prompt: str,
+        indices_to_alter_str: str,
+        seed: int = 0,
+        apply_attend_and_excite: bool = True,
+        num_steps: int = 50,
+        guidance_scale: float = 7.5,
+        scale_factor: int = 20,
+        thresholds: dict[int, float] = {
+            10: 0.5,
+            20: 0.8,
+        },
+        max_iter_to_alter: int = 25,
+    ) -> PIL.Image.Image:
+        generator = torch.Generator(device=self.device).manual_seed(seed)
+
+        if apply_attend_and_excite:
+            try:
+                token_indices = list(map(int, indices_to_alter_str.split(',')))
+            except Exception:
+                raise ValueError('Invalid token indices.')
+            out = self.ax_pipe(
+                prompt=prompt,
+                token_indices=token_indices,
+                guidance_scale=guidance_scale,
+                generator=generator,
+                num_inference_steps=num_steps,
+                max_iter_to_alter=max_iter_to_alter,
+                thresholds=thresholds,
+                scale_factor=scale_factor,
+            )
+        else:
+            out = self.sd_pipe(
+                prompt=prompt,
+                guidance_scale=guidance_scale,
+                generator=generator,
+                num_inference_steps=num_steps,
+            )
+        return out.images[0]

requirements.txt

@@ -0,0 +1,5 @@
+accelerate==0.20.3
+diffusers==0.17.0
+Pillow==9.5.0
+torch==2.0.1
+transformers==4.30.1

style.css

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