FlashDecoder: Real-Time Latent-to-Pixel Streaming Decoder with Transformers
Ranking
Overall
78
Content
95
Popularity
40
Observed public metrics from 1 member.
Merged summary
TL;DR - FlashDecoder is a pure-Transformer video decoder that streams latent representations to pixels frame-by-frame, enabling real-time video generation with constant latency and bounded memory regardless of video length.
- Replaces slow, memory-heavy 3D convolutional decoders in latent video diffusion; each frame attends to a fixed-size window of past frames via a rolling KV cache for constant-latency streaming.
- Sequential frame processing enforces temporal causality without explicit attention masks, supporting training at resolutions up to 1080p.
- Matches convolutional decoder reconstruction quality on Wan2.1/Wan2.2 latent spaces (e.g., 41.55dB vs. 41.49dB PSNR at 1080p).
- Decodes 3.6x–4.7x faster with up to 11x less memory on a single H100; architecture-aware inference optimizations widen the speedup to 12x.
Sources (1)
FlashDecoder: Real-Time Latent-to-Pixel Streaming Decoder with Transformers
Public signals
Hugging Face upvotes 0 · Semantic Scholar citations 0 · Semantic Scholar influential citations 0
TL;DR - FlashDecoder is a pure-Transformer video decoder that streams latent representations to pixels frame-by-frame, enabling real-time video generation with constant latency and bounded memory regardless of video length.
- Replaces slow, memory-heavy 3D convolutional decoders in latent video diffusion; each frame attends to a fixed-size window of past frames via a rolling KV cache for constant-latency streaming.
- Sequential frame processing enforces temporal causality without explicit attention masks, supporting training at resolutions up to 1080p.
- Matches convolutional decoder reconstruction quality on Wan2.1/Wan2.2 latent spaces (e.g., 41.55dB vs. 41.49dB PSNR at 1080p).
- Decodes 3.6x–4.7x faster with up to 11x less memory on a single H100; architecture-aware inference optimizations widen the speedup to 12x.