OneDiff: An out-of-the-box acceleration library for diffusion models.

Workflow-to-APP、ScreenShare&FloatingVideo、GPT & 3D、SpeechRecognition&TTS

A microframework on top of PyTorch with first-class citizen APIs for foundation model adaptation

Officail Implementation for "ReNoise: Real Image Inversion Through Iterative Noising"

Consistency Distillation with Target Timestep Selection and Decoupled Guidance

LCM LoRA

This is an experimental app for a webcam-to-AI workflow with ComfyUI.

100x faster text-guided image editing on consumer GPUs (~6s vs ~10min). Combines SSD-1B, LCM-LoRA 4-step inference, and ControlNet-Canny. Benchmarked on PIE-Bench with +23.5% CLIP score over DDIM baseline.

Stable Diffusion for CPU only, CLI only

Real-time generative design workbench mirroring Adobe Firefly. Transforms rough sketches into high-fidelity assets in <1.2s using Latent Consistency Models & ControlNet. Features a multi-style parallel comparison engine.