init

.github/workflows/build-release.yml

@@ -0,0 +1,56 @@
+name: CD | Build-Release
+
+on:
+  push:
+    branches:
+      - "main"
+    paths-ignore:
+      - "README.md"
+      - "**/*.md"
+      - "docs/**"
+      - "**/*.yml"
+  release:
+    types: [published]
+  workflow_dispatch:
+    inputs:
+      image_tag:
+        description: "Docker Image Tag"
+        required: false
+        default: "dev"
+
+jobs:
+  docker-build:
+    runs-on: self-hosted
+
+    steps:
+      - name: Free disk space
+        run: |
+          sudo rm -rf /usr/share/dotnet
+          sudo rm -rf /usr/local/lib/android
+          sudo rm -rf /opt/ghc
+          sudo rm -rf "/usr/local/share/boost"
+          sudo rm -rf "$AGENT_TOOLSDIRECTORY"
+          sudo apt-get clean
+          df -h  # Check available space
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v2
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v2
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@v2
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      # Build and push step
+      - name: Build and push
+        uses: docker/build-push-action@v4
+        with:
+          push: true
+          build-args: |
+            HUGGINGFACE_TOKEN=${{ secrets.HUGGINGFACE_TOKEN }}
+          tags: ${{ vars.DOCKERHUB_REPO }}/${{ vars.DOCKERHUB_IMG }}:${{ (github.event_name == 'release' && github.event.release.tag_name) || (github.event_name == 'workflow_dispatch' && github.event.inputs.image_tag) || 'dev' }}
+

.gitignore

@@ -0,0 +1,160 @@
+# 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/

Dockerfile

@@ -0,0 +1,19 @@
+# Base image -> https://github.com/runpod/containers/blob/main/official-templates/base/Dockerfile
+# DockerHub -> https://hub.docker.com/r/runpod/base/tags
+FROM runpod/base:0.4.0-cuda11.8.0
+
+# Add build argument
+ARG HUGGINGFACE_TOKEN
+# Set it as an environment variable
+ENV HUGGINGFACE_TOKEN=$HUGGINGFACE_TOKEN
+
+COPY builder/requirements.txt /requirements.txt
+RUN python3.11 -m pip install --upgrade pip && \
+    python3.11 -m pip install --upgrade -r /requirements.txt --no-cache-dir && \
+    rm /requirements.txt
+
+ADD src .
+
+RUN python3.11 /handler.py
+
+CMD python3.11 -u /handler.py

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 Path On AI
+
+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 +1,88 @@
+<div align="center">
+
+<h1>Stable Diffusion 3.5 Medium Worker Template</h1>
+
+A specialized worker template for building custom RunPod Endpoint API workers utilizing the Stable Diffusion 3.5 Medium model. This implementation supports various aspect ratios, guidance scales, and inference steps customization.
+
+</div>
+
+## Docker Container
+
+The ready-to-use Docker container is available on Docker Hub:
+```bash
+thehunter911/stbldiff3.5-medium-runpod-serverless
+```
+which can be used to deploy onto Runpod Serverless endpoint directly.
+
+
+You can also pull it using:
+```bash
+docker pull thehunter911/stbldiff3.5-medium-runpod-serverless
+```
+
+
+
+## Input Parameters
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| prompt | string | required | The text description of the image you want to generate |
+| aspect_ratio | string | "1:1" | Image aspect ratio. See supported values below |
+| guidance_scale | float | 0.0 | How closely the model follows the prompt |
+| num_inference_steps | integer | 1 | Number of denoising steps |
+
+### Supported Aspect Ratios
+- "16:9" - Widescreen (1024×576)
+- "1:1" - Square (1024×1024)
+- "21:9" - Ultra-wide (1024×439)
+- "2:3" - Portrait (683×1024)
+- "3:2" - Landscape (1024×683)
+- "4:5" - Portrait (819×1024)
+- "5:4" - Landscape (1024×819)
+- "9:16" - Vertical/Mobile (576×1024)
+- "9:21" - Vertical ultra-wide (439×1024)
+
+## Example Input
+
+```json
+{
+    "input": {
+        "prompt": "An image of a cat with a hat on",
+        "aspect_ratio": "16:9",
+        "guidance_scale": 0.0,
+        "num_inference_steps": 1
+    }
+}
+```
+
+## Example Output
+
+The output is a base64 encoded string of the generated image. Example:
+
+```
+data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAA...
+```
+
+### Viewing the Output
+
+To view the generated image, you can decode the base64 string using Python:
+
+```python
+import base64
+from PIL import Image
+import io
+
+# Replace 'base64_string' with your actual base64 string
+base64_string = "iVBORw0KGgoAAAANSUhEUgAA..."
+image_data = base64.b64decode(base64_string)
+image = Image.open(io.BytesIO(image_data))
+image.show()
+```
+
+## Performance Notes
+
+This implementation uses torch.float16 with fp16 variant for optimal inference performance on consumer GPUs. This configuration provides:
+- Faster inference speed
+- Lower memory usage
+- Better hardware compatibility
+- Optimal for generation tasks

builder/requirements.txt

@@ -0,0 +1,14 @@
+# Required Python packages get listed here, one per line.
+# Reccomended to lock the version number to avoid unexpected changes.
+
+# You can also install packages from a git repository, e.g.:
+# git+https://github.com/runpod/runpod-python.git
+# To learn more, see https://pip.pypa.io/en/stable/reference/requirements-file-format/
+
+runpod~=1.7.0
+diffusers
+transformers
+accelerate
+hf_transfer
+sentencepiece
+protobuf