search

deepseek-ai / DreamCraft3D

[ICLR 2024] Official implementation of DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior
https://mrtornado24.github.io/DreamCraft3D/
MIT License
1.9k stars 81 forks source link

GPU requirements #8

Closed violag closed 8 months ago

violag commented 8 months ago

Hi!

Thank you for the amazing work!

Can you share more information on the compute requirements. How many GPUs did you use for the Geometry Sculpting phase and also for the Texture Boosting phase?

What was the memory size of the GPU that was required?

Thank you!

MrTornado24 commented 8 months ago

We employed 8 units of 40G A100 for all stages of the process. However, the number of GPUs required is flexible, ranging from 1 to 8. For optimal performance, we recommend a memory size of at least 24G.

maocaixia commented 7 months ago

When we run "python launch.py --config configs/dreamcraft3d-coarse-neus.yaml --train system.prompt_processor.prompt="$prompt" data.image_path="$image_path" system.weights="$ckpt" ", there is an error "out of memory", the gpu is 4090 with 24G.

Any Suggestion? Thanks! @MrTornado24

maocaixia commented 7 months ago

Would we use multiple gpus to infer the model?

CHDTevior commented 4 months ago

Would we use multiple gpus to infer the model?

we also have the same problem.