Openimaginglab · Video
FlashVSR Plus
FlashVSR+ upscales video by up to 4x with a one-step diffusion model, offering a fast Turbo mode and a higher-quality Base mode. Output reaches about 4K, and the input audio track is preserved by default.
Evidence and sources
Released 13 Oct 2026
Sources: Fal.ai data, NanoGPT, llminfo researchPrimary data from Fal.ai
from NanoGPT: name
from llminfo research: release date
Input & output
from the model's typeText
Video
Also known as: openimaginglab/flashvsr-plus
Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works