Nodes/ComfyUI-FlashVSR-Stock/FlashVSR Tiny Decode
ComfyUI Node

FlashVSR Tiny Decode

Decodes TCDecoder output with four-frame conditioning streamed from CPU, reusable temporal-state buffers, native compute-dtype weights, a true frame-sequential low-VRAM path, and bounded temporal/output batches. Use temporal_batch_size=1 and output_chunk_size=1 for minimum VRAM.

By Pizzawookiee·Created 14 days ago·Updated 4 days ago· 2
FlashVSR Tiny Decode
  • samples
  • decoder
  • video
  • IMAGE
output_chunk_size4
temporal_batch_size1
profile_cuda_eventsfalse
CategoryFlashVSR/decoding

Inputs (6)

NameTypeDefaultDescription
samplesLATENT
decoderFLASHVSR_DECODER
videoFLASHVSR_VIDEO
output_chunk_sizeoptINT41–16Decoded frames staged on the GPU before one copy to the final IMAGE tensor. 1 minimizes VRAM; 4 matches TCDecoder's temporal output group.
temporal_batch_sizeoptINT11–4Latent timesteps decoded together. 1 uses a true depth-first path with one generated high-resolution frame active at a time; 2 often improves GPU utilization substantially; 4 is faster when it fits but can use roughly 1.5-3x the decoder activation VRAM. This remains bounded and does not grow with the complete clip duration.
profile_cuda_eventsoptBOOLEANfalsePrint TCDecoder CUDA-event timings grouped by resolution for conditioning transfer, pixel unshuffle, convolutions, MemBlocks, TGrow, state updates, crop/clamp and output copies, plus wall time and peak allocated/reserved VRAM. Profiling adds a final CUDA synchronization.

Outputs (1)

NameTypeDescription
IMAGEIMAGE