search

Tangshitao / MVDiffusion

MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion, NeurIPS 2023 (spotlight)
480 stars 25 forks source link

GPU resources required for inference #36

Open jmwang0117 opened 10 months ago

jmwang0117 commented 10 months ago

Hello, thank you for your excellent work.

Does text-to-multi-view inference(demo.py) require 4x A6000 GPU to complete?

I'm using a 3090 GPU and inference occurs with CUDA out of memory.

Tangshitao commented 10 months ago

Can you try fp16? You can add fp=16 here