📹 A more flexible framework that can generate videos at any resolution and creates videos from images.

AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:

Controlnet extension of AnimateDiff.

🔊 Text-prompted Generative Audio Model - With the ability to clone voices

Fork of Controlnet for 2 input channels

Instruct-tune LLaMA on consumer hardware

Optimized Stable Diffusion modified to run on lower GPU VRAM

Install Java (Open-JDK-8) in Termux without root!