libai-lab

Is there a way to integrate and use the LCM model? It can be used on the CPU, and it only takes a few minutes for me to generate images....

i got error # stage 1 %run main.py --config configs/image.yaml input=data/{IMAGE_PROCESSED} save_path={NAME} elevation={Elevation} force_cuda_rast=True mesh_format=glb # # stage 2 %run main2.py --config configs/image.yaml input=data/{IMAGE_PROCESSED} save_path={NAME} elevation={Elevation} force_cuda_rast=True mesh_format=glb #%run multi-cam.py...

> Other models also possible I will release LCM version but it will be slower 3 steps minimum. OpenVINO is taking too much memory around 30GB RAM required I'm thinking...

> Theoretically any diffusion inference acceleration work can be used, we don't have enough time to do acceleration for inference. If you can help, we'd really appreciate it! there is...

> 非蒸馏模型的设置有问题，它会分解成颗粒状，蒸馏后不会发生这种情况。我在 3090，win10。 Distilled 9.6How many VRAMs are needed and how long can a video be generated