PedroMarinhoDev/ComfyUI-Hy-Nomas
Tencent's Hy-Nomas video world model natively in ComfyUI: worlds from text or an image, chained segments, camera control and an interactive drive mode. INT8/FP8 kernels, 12 GB cards. Work in progress.
GitHub repository with 16 stars and 1 forks.
Language: Python
Topics: camera-control, comfyui, comfyui-custom-nodes, image-to-video, quantization, video-generation, world-model, hy-nomas