You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
When I super-resolution a 1024 * 1024 image into 4096 * 4096, I used 70GB of GPU memory and spent 18 minutes, which seems to contradict the advantages stated in the paper. I wonder if this is normal?
@peki12345 Fig. 2 shows the memory usage when parallel size=1. You can change the default inference_type in the script to reduce memory usage.
We tested the speed and GPU usage of various models on the H800. For Inf-DiT, the settings are: Inference_type="ar2", block_batch (parallel size)=16, step=15. We will update this table in the paper later.
The speed of Inf-DiT is indeed relatively slow because it is a pixel space diffusion model. We look forward to future work that can improve it to a latent space.
Same question, on 3090 graphics card, 512x512 image as input, using approximately 22GB of memory and inference takes 20 minutes @zdyshine
Hi, did you optimize the code of inference stage? In my case, I met 'out of memory' on my 4090 graphics card with 512x512 image.
Activity
zdyshine commentedon May 20, 2024
Same question, on 3090 graphics card, 512x512 image as input, using approximately 22GB of memory and inference takes 20 minutes
yzy-thu commentedon May 20, 2024
@peki12345 Fig. 2 shows the memory usage when parallel size=1. You can change the default inference_type in the script to reduce memory usage.

We tested the speed and GPU usage of various models on the H800. For Inf-DiT, the settings are: Inference_type="ar2", block_batch (parallel size)=16, step=15. We will update this table in the paper later.
yzy-thu commentedon May 20, 2024
The speed of Inf-DiT is indeed relatively slow because it is a pixel space diffusion model. We look forward to future work that can improve it to a latent space.
bruinxiong commentedon Jun 7, 2024