cd /news/generative-ai/diffvc-one-diffusion-based-generativ… · home topics generative-ai article
[ARTICLE · art-108282] src=arxiv.org ↗ pub= topic=generative-ai verified=true sentiment=↑ positive

DiffVC-ONE: Diffusion-based Generative Video Compression with One-Step Video Diffusion Transformer

Researchers propose DiffVC-ONE, a diffusion-based generative video compression framework built on a one-step Video Diffusion Transformer, achieving state-of-the-art perceptual quality and temporal consistency with low inference cost. The framework introduces a Unified Unidirectional Latent Compressor, a Video DiT-based One-Step Diffusion Enhancer, and a Hybrid Condition Generator to efficiently compress latent slices and perform single-step spatio-temporal enhancement. Experiments on standard benchmarks confirm its performance.

read1 min views1 publishedAug 24, 2026

arXiv:2608.20515v1 Announce Type: new Abstract: Generative video compression can recover rich visual details at low bitrates, but simultaneously achieving high temporal consistency and low inference cost remains challenging. To address this issue, we propose DiffVC-ONE, a diffusion-based generative video compression framework built on a one-step Video Diffusion Transformer. First, we introduce a Unified Unidirectional Latent Compressor that uses a shared model to efficiently and uniformly compress compact latent slices. We then develop a Video DiT-based One-Step Diffusion Enhancer that uses the reconstructed latent slices as content anchors and performs single-step spatio-temporal perceptual enhancement over an entire group of pictures. Finally, a Hybrid Condition Generator extracts structural, strength, and semantic conditions from the reconstructed content and quantization information. These conditions preserve faithful regions, control the degree of generative enhancement, and supplement content-aware perceptual details during one-step diffusion enhancement. Extensive experiments on multiple standard benchmarks demonstrate that DiffVC-ONE achieves state-of-the-art perceptual quality and temporal consistency with low inference cost.

── more in #generative-ai 4 stories · sorted by recency
── more on @diffvc-one 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/diffvc-one-diffusion…] indexed:0 read:1min 2026-08-24 ·