OpenImagingLab / OpenImagingLab/FlashVSR

2X Upscaling Error in A-100

Open
#35 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
1.9k
Forks
152
PR merge metrics
No merged PRs in 30d

Description

Image Image **Issue:** Attempting to upscale a video using FlashVSR results in a 500 Internal Server Error.

Log Details:

  • Video URL: Provided in payload
  • Seed: 374941, Scale: 2.0, Sparse Ratio: 2.0
  • Original Resolution: 1920x1080, Frames: 150, FPS: 30
  • Scaled Resolution: 3840x2160 -> Target 3840x2048

Warning Observed:
UserWarning: The given NumPy array is not writable, and PyTorch does not support non-writable tensors.
(tensor_numpy.cpp:203)

Steps to Reproduce:

  1. Send POST request to /upscale-video endpoint with payload containing video URL.
  2. Observe the server logs.
  3. Endpoint returns 500 Internal Server Error.

Screenshot / Log:
server-log

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start at the /upscale-video POST entry point and reproduce the request using the reported 1920x1080 video, scale 2.0, and sparse ratio 2.0. Inspect the server traceback and the NumPy/PyTorch non-writable-array warning to identify why the request returns 500. Done means the same upscale request completes without a 500 error and the relevant logs no longer show the failure.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
api, computer-vision, machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
32/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.