# OpenImagingLab/FlashVSR_Plus

> Official implementation of FlashVSR+, a one-step diffusion framework for video super-resolution that enables spatially untiled 4K inference on a single 24GB RTX 4090. It ships inference code, pretrained models, and the training dataset.

- Magnitude: 3.2 out of 10 — Early signal
- Stars: 83 total · +1 star measured 2026-10-16, 00:05–01:32 UTC, ≈ 23 by evening
- Star trust: star growth looks organic
- Category: Generative media · Language: Python · License: Apache-2.0 · Created: 2026-10-14 · Last push: 2026-10-14
- GitHub: https://github.com/OpenImagingLab/FlashVSR_Plus · Page: https://gitnova.dev/en/r/OpenImagingLab/FlashVSR_Plus

## Useful for

- Run 4K video upscaling on a single RTX 4090 via CLI or Python API
- Pick the Turbo, Base, or V1 preset and an attention backend (BSA, Triton, SDPA) for your GPU
- Process long videos in segments by setting the --decode-every option

## Why it’s here

- Star-counter measurements on 2026-10-16 (UTC), 00:05–01:32: 82 → 83 stars (+1). This is the change over that interval.
- Estimated end-of-day forecast: about +23 stars, using observed gains and the previous day.
- The repository is 2 days old and already has 83 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #195.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 1
- Issues and pull requests: 2
- Watchers: 3
- Average over the last week: 36 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 1

## Stars per day, last 3 days (oldest → newest, today is partial)

2026-10-14 … 2026-10-16: 60, 24, 1

## Spotted in now

- Top new repositories this week: #195

## More in this category

1. **jub0t/concat** — 6.9 · Breakout · Generative media · Rust · +53 stars measured 2026-10-16, 00:05–01:30 UTC, ≈ 920 by evening
   Cross-platform Rust video editor — a free CapCut replacement with no watermarks, subscriptions or accounts, running entirely locally. Supports multi-track editing, auto-captions, TTS and templates.
   Full card: https://gitnova.dev/en/r/jub0t/concat.md
2. **Arekejoker/qwen21-nsfw-pose-skill** — 5.9 · Peaking · Generative media · Python · +45 stars measured 2026-10-16, 00:04–01:30 UTC, ≈ 569 by evening
   A set of recipes and scripts for local NSFW image generation and pose control with Qwen-Image 2.1 via ComfyUI, including an NSFW LoRA and a library of 136 3D poses.
   Full card: https://gitnova.dev/en/r/Arekejoker/qwen21-nsfw-pose-skill.md
3. **debpalash/VoiceStudio** — 5.7 · Steady · Generative media · Python · +119 stars measured 2026-10-16, 00:05–01:30 UTC, ≈ 1,948 by evening
   A fully local, open-source ElevenLabs alternative for voice cloning, voice design, video dubbing, dictation, transcription and audiobook creation on your own hardware, with no account or API key. Supports 16 TTS and 11 ASR engines, a…
   Full card: https://gitnova.dev/en/r/debpalash/VoiceStudio.md
4. **YIAN6557/eian-riso-broll** — 5.5 · Early signal · Generative media · JavaScript · +6 stars measured 2026-10-16, 00:06–01:30 UTC, ≈ 149 by evening
   A set of templates and an AI workflow for turning a talking-head video script into vertical info animations (1080×1920 mp4) in a two-color risograph print style. Works with Claude Code, Codex, Cursor, Gemini CLI.
   Full card: https://gitnova.dev/en/r/YIAN6557/eian-riso-broll.md
5. **xibushu/UniForge3D** — 5.2 · Early signal · Generative media · Python · +12 stars measured 2026-10-16, 00:05–01:30 UTC, ≈ 101 by evening
   Official implementation of UniForge3D, a method that builds a complete 3D asset from sparse, unposed multi-view images by jointly modeling reconstruction and generation in a shared anchor-guided space. Aimed at researchers and 3D content…
   Full card: https://gitnova.dev/en/r/xibushu/UniForge3D.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-16 01:42 UTC, updated every 30 minutes.