Irodori-TTS is a state-of-the-art Japanese text-to-speech system built on rectified flow diffusion over DACVAE audio latents. It provides a complete training and inference stack: `train.py` supports full fine-tuning, LoRA, speaker inversion, and MeanFlow distillation with distributed training and WSD scheduling; `infer.py` offers a rich CLI with CFG, Sway Sampling, duration scaling, and watermarking; `gradio_app.py` and `gradio_app_voicedesign.py` expose interactive UIs for reference-based cloning and caption-conditioned voice design. The architecture is modular (`irodori_tts` package) with attention dispatch (FA3/SDPA), a hybrid Muon+AdamW optimizer, codec abstraction, and caching-friendly `InferenceRuntime`. While highly engineered for production use (INT4/INT8 quantization, safetensors, HuggingFace Hub integration), it remains a research-oriented codebase with experimental sampling algorithms and many YAML configs for different model sizes/versions. The code is clean and well-factored, though `train.py` is a large monolith and external dependencies (DACVAE, silentcipher) are pinned to specific commits, creating ecosystem fragility.
RectifiedFlow is a unified PyTorch library for implementing Rectified Flow models, a type of generative model that learns ordinary differential equations to transform data between distributions. The library provides a modular framework for training various architectures (MLP, UNet, DiT, LightningDiT) on different datasets, with support for multiple sampling algorithms and interpolation schemes. Key features include a symbolic solver for affine interpolation equations, utilities for converting between different interpolation schemes while preserving rectified flow properties, and a flexible sampler base class for implementing custom integration methods. The codebase demonstrates strong software engineering practices with clear separation of components, comprehensive documentation through examples, and active maintenance.
FlowEdit is a PyTorch-based implementation of the FlowEdit algorithm for inversion-free text-guided image editing using pre-trained flow models (Stable Diffusion 3 and FLUX). The system takes an input image and source/target prompts, and edits the image by solving an ODE that combines the source and target trajectories in the latent space. The core algorithm is implemented in FlowEdit_utils.py, with run_script.py orchestrating the experiment execution based on YAML configurations. The repository includes a dataset of images and prompts for numerical evaluation.