infery
← All models

FlashVSR+

flashvsr-plus

Video generationby Openimaginglab

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.

Details

Accepts
video

Pricing

Price
0.063 cr / megapixel

Prices in credits (1 credit = $0.01).

Data schema

Input

FieldTypeDescription
seed—The random seed used for the generation process.
modelstringenum: turbo, base, v1turbo: fastest (hybrid sliding attention). base: highest quality. v1: FlashVSR v1.1 weights with the base configuration.
color_fixbooleanApply low-frequency wavelet color correction.
sync_modebooleanIf `True`, the media will be returned inline and not stored in history.
video_urlrequiredstringThe input video to upscale.
video_qualitystringenum: low, medium, high, maximumOutput encoding quality.
preserve_audiobooleanCopy the input audio track into the output.
upscale_factornumberSpatial upscaling factor. Output is capped at about 4K.
video_write_modestringenum: fast, balanced, smallOutput write mode.
video_output_typestringenum: X264 (.mp4), VP9 (.webm), PRORES4444 (.mov), GIF (.gif)Output container/codec.
temporal_compressionintegerenum: 1, 2, 4Input frames per latent frame. Use 2 or 1 for large motion; inference cost rises about 2x or 4x.
enable_safety_checkerbooleanAuthorized callers may set false to request relaxed screening.

Output

FieldTypeDescription
seedintegerThe random seed used for the generation process.
video—The upscaled video.