Skip to content

About speed and GPU memory? #4

Open

Description

@peki12345

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?

Activity

  1. zdyshine commented on May 20, 2024

    @zdyshine

    Same question, on 3090 graphics card, 512x512 image as input, using approximately 22GB of memory and inference takes 20 minutes

  2. yzy-thu commented on May 20, 2024

    @yzy-thu
    Contributor

    @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.
    image

  3. yzy-thu commented on May 20, 2024

    @yzy-thu
    Contributor

    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.

  4. bruinxiong commented on Jun 7, 2024

    @bruinxiong

    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.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions