Hi, thanks for releasing FlashVSR.
I’m observing noticeable visual artifacts when running the official infer_flashvsr_v1.1_tiny_long_video.py script on a REDS video with bicubic degradation. The input resolution is 320×180, and the output resolution is 1280×640. I attached a few example frames below.
I also observe artifacts with infer_flashvsr_v1.1_full.py, but the attached screenshots here are from the tiny long video script.
Is this expected behavior, or could something be wrong in the inference setup?
Hi, thanks for releasing FlashVSR.
I’m observing noticeable visual artifacts when running the official infer_flashvsr_v1.1_tiny_long_video.py script on a REDS video with bicubic degradation. The input resolution is 320×180, and the output resolution is 1280×640. I attached a few example frames below.
I also observe artifacts with infer_flashvsr_v1.1_full.py, but the attached screenshots here are from the tiny long video script.
Is this expected behavior, or could something be wrong in the inference setup?