SwiftVR

About

What SwiftVR is

SwiftVR is the first generative video restoration model to reach real-time 1080p streaming on a consumer-grade GPU (≈26 FPS on a single RTX 5090), sustains 31 FPS at QHD (2560×1440) and 14 FPS at 4K (3840×2160) on a single H100, and streams at resolutions where every compared diffusion-based VR baseline runs out of memory. SwiftVR is a streaming one-step generative video restoration (VR) framework presented in SwiftVR: Real-Time One-Step Generative Video Restoration. Updates - [2026/06] Release the inference code and pretrained weights 🎉 ✨ Highlights - Mask-free shifted-window self-attention (MFSWA). Each spatial window is pre-gathered into a dense tensor, so every attention call reduces to a single standard scaled-dot-product (SDPA) call — no attention mask, cyclic shift, or padding ever enters the graph. This gives a 1.62× throughput gain over its full-attention teacher at essentially identical quality, with no dedicated sparse kernel. - Restoration-aware Autoencoder (ReAE). A lightweight encoder–decoder jointly fine-tuned with the DiT in pixel space removes the heavy-3D-VAE / tiled-decoding bottleneck. - Causal chunk-wise streaming. A minimal causal protocol (no rolling KV cache, no overlapped DiT inference) bounds the temporal axis, confining the residual \(\mathcal{O}(N^2)\) cost to the spatial axes. 📊 Results Efficiency at 2560×1440 (single H100, causal streaming, 24 frames) At 3840×2160, every compared diffusion-based VR baseline OOMs on a single H100; SwiftVR sustains 14 FPS. Qualitative comparison 🛠 Installation - Server: single H100-80G reproduces the QHD/4K numbers above. - Consumer: single RTX 5090 reaches ≈26 FPS at 1080p with the same checkpoint (default PyTorch SDPA path, bfloat16, causal chunk protocol). - No hardware-specific retraining or kernel rewrite is required on any platform. 🗂 Model Zoo Expected checkpoint layout (the directory passed to frompretrained): 🚀 Quick Start Python API restorevideo also accepts an image folder as input and can write a PNG sequence with pngsave=True. Tunable knobs include: cliplen: middle chunk size, multiple of 4 ditoverlap: overlap for DiT inference fps: output video frame rate quality: 0–100, mapped to x265 C

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

How it works

How video models work

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys swiftvr for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (swiftvr below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/videos/generations \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"swiftvr","prompt":"a drone shot over a forest"}'

Details

Languages, data & research

Papers

Licence

Open weights

Sources

Weights & code

Explore

More video models