init

.gitignore

@@ -0,0 +1,185 @@
+# Byte-compiled / optimized / DLL files
+model/
+__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/
+
+*.swp
+
+
+diffusers
+
+*/*.png
+
+tests/data
+
+wandb
+
+.vscode 
+*.zip
+*.npz 
+*.tar.gz
+*.pyc
+*.pb
+*.pkl
+*.npz
+ignored_cache
+
+*.jpg
+*.png

README.md

@@ -0,0 +1,122 @@
+# Improved Distribution Matching Distillation for Fast Image Synthesis
+
+Few-step Text-to-Image Generation.
+
+![image/jpeg](docs/teaser.jpg)
+
+> [**Improved Distribution Matching Distillation for Fast Image Synthesis**](https://tianweiy.github.io/dmd2/dmd2.pdf),            
+> Tianwei Yin, Michaël Gharbi, Taesung Park, Richard Zhang, Eli Shechtman, Frédo Durand, William T. Freeman        
+> *arXiv technical report ([arXiv xxxx.xxxxx](https://arxiv.org/abs/xxxx.xxxxx))*  
+
+## Contact 
+
+Feel free to contact us if you have any questions about the paper!
+
+Tianwei Yin [[email protected]](mailto:[email protected])
+
+## Abstract
+
+Recent approaches have shown promises distilling diffusion models into
+efficient one-step generators. Among them, Distribution Matching Distillation
+(DMD) produces one-step generators that match their teacher in distribution,
+without enforcing a one-to-one correspondence with the sampling trajectories of
+their teachers. However, to ensure stable training, DMD requires an additional
+regression loss computed using a large set of noise-image pairs generated by
+the teacher with many steps of a deterministic sampler. This is costly for
+large-scale text-to-image synthesis and limits the student's quality, tying it
+too closely to the teacher's original sampling paths. We introduce DMD2, a set
+of techniques that lift this limitation and improve DMD training. First, we
+eliminate the regression loss and the need for expensive dataset construction.
+We show that the resulting instability is due to the fake critic not estimating
+the distribution of generated samples accurately and propose a two time-scale
+update rule as a remedy. Second, we integrate a GAN loss into the distillation
+procedure, discriminating between generated samples and real images. This lets
+us train the student model on real data, mitigating the imperfect real score
+estimation from the teacher model, and enhancing quality. Lastly, we modify the
+training procedure to enable multi-step sampling. We identify and address the
+training-inference input mismatch problem in this setting, by simulating
+inference-time generator samples during training time. Taken together, our
+improvements set new benchmarks in one-step image generation, with FID scores
+of 1.28 on ImageNet-64x64 and 8.35 on zero-shot COCO 2014, surpassing the
+original teacher despite a 500X reduction in inference cost. Further, we show
+our approach can generate megapixel images by distilling SDXL, demonstrating
+exceptional visual quality among few-step methods.
+
+## Environment Setup
+
+```.bash
+# In conda env 
+conda create -n dmd2 python=3.8 -y 
+conda activate dmd2 
+
+pip install --upgrade anyio
+pip install torch==2.0.1  torchvision==0.15.2
+pip install  --upgrade diffusers wandb lmdb transformers accelerate==0.23.0 lmdb datasets evaluate  scipy opencv-python matplotlib imageio piq==0.7.0 safetensors gradio
+python setup.py  develop
+```
+
+## Inference Example
+
+To reproduce our ImageNet results, run:
+
+```.bash
+python demo/imagenet_example.py  --checkpoint_path IMAGENET_CKPT_PATH 
+```
+
+To try our text-to-image generation demo, run:
+
+```.bash
+python demo/text_to_image_sdxl.py --checkpoint_path SDXL_CKPT_PATH 
+```
+
+Pretrained models can be found in [ImageNet](experiments/imagenet/README.md) and [SDXL](experiments/sdxl/README.md). 
+
+## Training and Evaluation 
+
+### ImageNet-64x64 
+
+Please refer to [ImageNet-64x64](experiments/imagenet/README.md) for details.
+
+### SDXL
+
+Please refer to [SDXL](experiments/sdxl/README.md) for details.
+
+### SDv1.5 
+
+Please refer to [SDv1.5](experiments/sdv1.5/README.md) for details.
+
+## License
+
+Improved Distribution Matching Distillation is released under [Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License](LICENSE.md).
+
+## Known Issues 
+
+- [ ] Current FSDP for SDXL training is really slow; help is greatly appreciated!
+
+## Citation 
+
+If you find DMD2 useful or relevant to your research, please kindly cite our papers:
+
+```bib
+@article{yin2024improved,
+    title={Improved Distribution Matching Distillation for Fast Image Synthesis},
+    author={Yin, Tianwei and Gharbi, Micha{\"e}l and Park, Taesung and Zhang, Richard and Shechtman, Eli and Durand, Fredo and Freeman, William T},
+    journal={arXiv:xxxx.xxxxx},
+    year={2024}
+}
+
+@inproceedings{yin2024onestep,
+    title={One-step Diffusion with Distribution Matching Distillation},
+    author={Yin, Tianwei and Gharbi, Micha{\"e}l and Zhang, Richard and Shechtman, Eli and Durand, Fr{\'e}do and Freeman, William T and Park, Taesung},
+    booktitle={CVPR},
+    year={2024}
+}
+```
+
+## Third-part Code
+
+[EDM](https://github.com/NVlabs/edm/tree/main) for [dnnlib](dnnlib), [torch_utils](torch_utils) and [edm](third_party/edm) folders.
+
+## Acknowledgments 
+
+This work was done while Tianwei Yin was a full-time student at MIT. It was developed based on our reimplementation of the original DMD paper. This work was supported by the National Science Foundation under Cooperative Agreement PHY-2019786 (The NSF AI Institute for Artificial Intelligence and Fundamental Interactions, http://iaifi.org/), by NSF Grant 2105819, by NSF CISE award 1955864, and by funding from Google, GIST, Amazon, and Quanta Computer.