OpenImagingLab / OpenImagingLab/FlashVSR
Doesnt work here yet
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 1.9k
- Forks
- 152
- PR merge metrics
- No merged PRs in 30d
Description
Hi - using Flash VSR Upscaler and WanGP2 via Pinokio. I think the necessary files are downloaded successfully but not much happens when loading a video and hitting Upscale Video. I get "Loading Video..." and that's it. Nothing happens.
Limited specs but everything else works fine, abeit slowly on my RTX 2060 (6GB VRAM) with 64G Sytem RAM. So I use Processing Settings, Data Type Ff16.
What should I do?
..........Connected!
[FlashVSR] Pre-flight check: Model: 2.5GB, DiT: 0.0GB(tiled), VAE: 1.0GB(tiled), Output RAM: 14.9GB
[FlashVSR] Available: VRAM=4.9GB, RAM=57.7GB
[FlashVSR] Incomplete model files detected, re-downloading...
[FlashVSR] Downloading models from HuggingFace (JunhaoZhuang/FlashVSR-v1.1)...
[FlashVSR] This may take several minutes depending on your internet connection.
Fetching 6 files: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 6/6 [00:00<00:00, 1199.86steps/s]
[FlashVSR] Models downloaded successfully to: C:\pinokio\api\wan.git\app\ckpts\flashvsr
Thank you.
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Reproduce the Flash VSR Upscaler/WanGP2 flow through Pinokio with the reported RTX 2060 settings, starting from the “Loading Video...” stage and the included pre-flight/download log. Done means identifying a concrete failure and reproducible scope; the issue currently names no source file, test, or expected code change.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision, machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100