Refactor diffusionsat source code to be more clean and update with latest huggingface/diffusers

.gitignore

@@ -0,0 +1,213 @@
+ckpt
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$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
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.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
+#poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+#pdm.lock
+#pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+#pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# 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
+.envrc
+.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/
+
+# Abstra
+# Abstra is an AI-powered process automation framework.
+# Ignore directories containing user credentials, local state, and settings.
+# Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#  and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#  you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Cursor
+#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
+#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
+#  refer to https://docs.cursor.com/context/ignore-files
+.cursorignore
+.cursorindexingignore
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+./discard/
+
+
+test_image_generation.py

.gitmodules

@@ -0,0 +1,3 @@
+[submodule "libs/diffusers"]
+	path = libs/diffusers
+	url = https://github.com/huggingface/diffusers

Makefile

@@ -1,7 +1,8 @@
 .PHONY: deps_table_update modified_only_fixup extra_style_checks quality style fixup fix-copies test test-examples
 
 # make sure to test the local checkout in scripts and not the pre-installed one (don't use quotes!)
-export PYTHONPATH = src
+# In development mode, use libs/diffusers; otherwise use pip-installed diffusers
+export PYTHONPATH = libs
 
 check_dirs := examples scripts src tests utils
 
@@ -15,13 +16,13 @@ modified_only_fixup:
 		echo "No library .py files were modified"; \
 	fi
 
-# Update src/diffusers/dependency_versions_table.py
+# Update libs/diffusers/dependency_versions_table.py
 
 deps_table_update:
 	@python setup.py deps_table_update
 
 deps_table_check_updated:
-	@md5sum src/diffusers/dependency_versions_table.py > md5sum.saved
+	@md5sum libs/diffusers/dependency_versions_table.py > md5sum.saved
 	@python setup.py deps_table_update
 	@md5sum -c --quiet md5sum.saved || (printf "\nError: the version dependency table is outdated.\nPlease run 'make fixup' or 'make style' and commit the changes.\n\n" && exit 1)
 	@rm md5sum.saved
@@ -42,14 +43,14 @@ repo-consistency:
 quality:
 	black --check $(check_dirs)
 	ruff $(check_dirs)
-	doc-builder style src/diffusers docs/source --max_len 119 --check_only --path_to_docs docs/source
+	doc-builder style libs/diffusers docs/source --max_len 119 --check_only --path_to_docs docs/source
 	python utils/check_doc_toc.py
 
 # Format source code automatically and check is there are any problems left that need manual fixing
 
 extra_style_checks:
 	python utils/custom_init_isort.py
-	doc-builder style src/diffusers docs/source --max_len 119 --path_to_docs docs/source
+	doc-builder style libs/diffusers docs/source --max_len 119 --path_to_docs docs/source
 	python utils/check_doc_toc.py --fix_and_overwrite
 
 # this target runs checks on all files and potentially modifies some of them

README.md

@@ -25,7 +25,8 @@ conda create -n diffusionsat python=3.10
 
 # if you want cuda 11.8, replace the index url with https://download.pytorch.org/whl/cu118
 pip install torch==2.2.2 torchvision==0.17.2 --index-url https://download.pytorch.org/whl/cu121
-pip install -e ".[torch]"  # install editable diffusers
+pip install diffusers  # install latest diffusers from PyPI
+# For development mode, diffusers can be found under ./libs/diffusers
 pip install -r requirements_remaining.txt
 ```
 

custom_pipelines/README.md

@@ -0,0 +1,87 @@
+# DiffusionSat Custom Pipelines
+
+Custom community pipelines for loading DiffusionSat checkpoints directly with `diffusers.DiffusionPipeline.from_pretrained()`.
+
+> See [Diffusers Community Pipeline Documentation](https://huggingface.co/docs/diffusers/using-diffusers/custom_pipeline_overview)
+
+## Available Pipelines
+
+This directory contains two custom pipelines:
+
+1. **`pipeline_diffusionsat.py`**: Standard text-to-image pipeline with DiffusionSat metadata support.
+2. **`pipeline_diffusionsat_controlnet.py`**: ControlNet pipeline with DiffusionSat metadata and conditional metadata support.
+
+## Setup
+
+The checkpoint folder (`ckpt/diffusionsat/`) should contain the standard diffusers components (unet, vae, scheduler, etc.). You can reference these pipeline files directly from this directory or copy them to your checkpoint folder.
+
+## Usage
+
+### 1. Text-to-Image Pipeline
+
+Use `pipeline_diffusionsat.py` for standard generation.
+
+```python
+import torch
+from diffusers import DiffusionPipeline
+
+# Load pipeline
+pipe = DiffusionPipeline.from_pretrained(
+    "path/to/ckpt/diffusionsat",
+    custom_pipeline="./custom_pipelines/pipeline_diffusionsat.py",  # Path to this file
+    torch_dtype=torch.float16,
+    trust_remote_code=True,
+)
+pipe = pipe.to("cuda")
+
+# Optional: Metadata (normalized lat, lon, timestamp, GSD, etc.)
+# metadata = [0.5, -0.3, 0.7, 0.2, 0.1, 0.0, 0.5] 
+
+# Generate
+image = pipe(
+    "satellite image of farmland",
+    metadata=None,  # Optional
+    num_inference_steps=30,
+).images[0]
+```
+
+### 2. ControlNet Pipeline
+
+Use `pipeline_diffusionsat_controlnet.py` for ControlNet generation.
+
+```python
+import torch
+from diffusers import DiffusionPipeline, ControlNetModel
+from diffusers.utils import load_image
+
+# 1. Load ControlNet
+controlnet = ControlNetModel.from_pretrained(
+    "path/to/ckpt/diffusionsat/controlnet",
+    torch_dtype=torch.float16
+)
+
+# 2. Load Pipeline with ControlNet
+pipe = DiffusionPipeline.from_pretrained(
+    "path/to/ckpt/diffusionsat",
+    controlnet=controlnet,
+    custom_pipeline="./custom_pipelines/pipeline_diffusionsat_controlnet.py", # Path to this file
+    torch_dtype=torch.float16,
+    trust_remote_code=True,
+)
+pipe = pipe.to("cuda")
+
+# 3. Prepare Control Image
+control_image = load_image("path/to/conditioning_image.png")
+
+# 4. Generate
+# metadata: Target image metadata (optional)
+# cond_metadata: Conditioning image metadata (optional)
+
+image = pipe(
+    "satellite image of farmland",
+    image=control_image,
+    metadata=None,       
+    cond_metadata=None,
+    num_inference_steps=30,
+).images[0]
+```