Vixy
e4294b57e6
- SDXL image generation using RealVisXL_V4.0 - IP-Adapter FaceID integration for consistent face generation - Simplified API (removed client_id requirement) - New params: face_image, face_strength - 'vixy' shortcut for face-locked generation - Queue-based async job processing - FastAPI with proper error handling Co-authored-by: Alex <alex@k4zka.online>
49 lines
1.2 KiB
Docker
Executable File
49 lines
1.2 KiB
Docker
Executable File
# DreamTail - SDXL Image Generation Service for NVIDIA Jetson AGX Orin
|
|
# Based on NVIDIA L4T PyTorch container optimized for Jetson
|
|
|
|
# Try the jetson-containers format (alternative: nvcr.io/nvidia/l4t-pytorch:r35.2.1-pth2.0-py3)
|
|
FROM dustynv/pytorch:2.1-r36.2.0
|
|
|
|
# Set working directory
|
|
WORKDIR /app
|
|
|
|
# Install system dependencies
|
|
RUN apt-get update && apt-get install -y \
|
|
git \
|
|
wget \
|
|
libgl1-mesa-glx \
|
|
libglib2.0-0 \
|
|
&& rm -rf /var/lib/apt/lists/*
|
|
|
|
# Copy requirements first for better caching
|
|
COPY requirements.txt /app/
|
|
|
|
# Install Python dependencies
|
|
# Note: torch and torchvision are already in the base image
|
|
RUN pip3 install --no-cache-dir -r requirements.txt
|
|
|
|
# Copy application code
|
|
COPY config.py /app/
|
|
COPY main.py /app/
|
|
COPY api/ /app/api/
|
|
COPY worker/ /app/worker/
|
|
COPY dreamtail_storage/ /app/dreamtail_storage/
|
|
|
|
# Create storage directories
|
|
RUN mkdir -p /app/storage/images /app/models
|
|
|
|
# Expose API port
|
|
EXPOSE 8765
|
|
|
|
# Set environment variables
|
|
ENV PYTHONUNBUFFERED=1
|
|
ENV DREAMTAIL_STORAGE=/app/storage
|
|
ENV DREAMTAIL_MODELS=/app/models
|
|
|
|
# Health check
|
|
HEALTHCHECK --interval=30s --timeout=10s --start-period=60s --retries=3 \
|
|
CMD curl -f http://localhost:8765/health || exit 1
|
|
|
|
# Run the FastAPI application
|
|
CMD ["python3", "main.py"]
|