fast-stable-diffusion

Implements a two-stage DreamBooth training pipeline that separates UNet and text encoder training, with persistent session management stored in Google Drive. The system manages training configuration (steps, learning rates, resolution), instance image preprocessing with smart cropping, and automatic model checkpoint export from Diffusers format to CKPT format. Training state is preserved across Colab session interruptions through Drive-backed session folders containing instance images, captions, and intermediate checkpoints.

Deploys the AUTOMATIC1111 Stable Diffusion web UI in Google Colab with integrated model loading (predefined, custom path, or download-on-demand), extension support including ControlNet with version-specific models, and multiple remote access tunneling options (Ngrok, localtunnel, Gradio share). The system handles model conversion between formats, manages VRAM allocation, and provides a persistent web interface for image generation without requiring local GPU hardware.

Manages complex dependency installation for Colab environment by using precompiled wheels optimized for Colab's CUDA version, reducing setup time from 10+ minutes to <2 minutes. The system installs PyTorch, diffusers, transformers, and other dependencies with correct CUDA bindings, handles version conflicts, and validates installation. Supports both DreamBooth and AUTOMATIC1111 workflows with separate dependency sets.

Implements a hierarchical folder structure in Google Drive that persists training data, model checkpoints, and generated images across ephemeral Colab sessions. The system mounts Google Drive at session start, creates session-specific directories (Fast-Dreambooth/Sessions/), stores instance images and captions in organized subdirectories, and automatically saves trained model checkpoints. Supports both personal and shared Google Drive accounts with appropriate mount configuration.

Converts trained models from Diffusers library format (PyTorch tensors) to CKPT checkpoint format compatible with AUTOMATIC1111 and other inference UIs. The system handles weight mapping between format specifications, manages memory efficiently during conversion, and validates output checkpoints. Supports conversion of both base models and fine-tuned DreamBooth models, with automatic format detection and error handling.

Preprocesses training images for DreamBooth by applying smart cropping to focus on the subject, resizing to target resolution, and generating or accepting captions for each image. The system detects faces or subjects, crops to square aspect ratio centered on the subject, and stores captions in separate files for training. Supports batch processing of multiple images with consistent preprocessing parameters.

Provides abstraction layer for selecting and loading different Stable Diffusion base model versions (1.5, 2.1-512px, 2.1-768px, SDXL, Flux) with automatic weight downloading and format detection. The system handles model-specific configuration (resolution, architecture differences) and prevents incompatible model combinations. Users select model version via notebook dropdown or parameter, and the system handles all download and initialization logic.

Integrates ControlNet extensions into AUTOMATIC1111 web UI with automatic model selection based on base model version. The system downloads and configures ControlNet models (pose, depth, canny edge detection, etc.) compatible with the selected Stable Diffusion version, manages model loading, and exposes ControlNet controls in the web UI. Prevents incompatible model combinations (e.g., SD 1.5 ControlNet with SDXL base model).

Provides multiple tunneling options (Ngrok, localtunnel, Gradio share) to expose the AUTOMATIC1111 web UI running in Colab to the public internet. The system handles authentication, URL generation, and connection management for each tunnel type. Users select preferred tunnel method, and the system configures and launches the appropriate tunnel with automatic URL display.

Provides interface for configuring DreamBooth training hyperparameters (learning rate, training steps, resolution, batch size, gradient accumulation) with validation to prevent invalid combinations. The system exposes parameters via notebook cells or UI controls, validates ranges (e.g., learning rate 1e-6 to 1e-3), and prevents configurations that would exceed GPU memory. Stores configuration alongside training session for reproducibility.

Monitors DreamBooth training progress by logging loss metrics, generation quality, and training speed. The system saves intermediate checkpoints at specified intervals, displays training curves, and provides test generation capability to evaluate model quality during training. Checkpoints are saved to Google Drive for resumption if training is interrupted.