1 dépôt
Tools and methodologies for adapting pretrained video diffusion models to specific styles or tasks.
Distinct from Video Diffusion Models: Focuses on the act of adapting weights via LoRA or full training, not the model architecture itself
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Finetuning Frameworks. Refine with filters or upvote what's useful.
FastVideo is a comprehensive system for accelerated video generation, serving as a video generation inference engine, a video diffusion training framework, and a modular pipeline orchestrator. It provides a distributed transformer optimizer and a distillation toolkit designed to reduce denoising steps and model complexity to increase frame rates. The project distinguishes itself through specialized acceleration techniques, including joint distillation and sparse attention training. It implements low-step video generation and weight quantization to FP8 or FP4 precision to increase throughput a
Provides full and LoRA training methods to adapt video diffusion models to specific styles or tasks.