LynnReal-AI/LynnReal-Omni
LynnReal-Omni brings text-to-video, image-to-video, human- and hand-pose guided generation, structural control, omni-reference generation, style transfer, video editing, degraded-video restoration and streaming long-video generation into a single framework, all at four-step fast generation.
Older snapshot: check the original source for current information.
From the publisher
README & documentation
Source previewRead the project’s overview, installation instructions and usage examples. The original README is the source of truth.
Video generation, references, motion controls and editing. Paper🔥HOT · Introduction · Overview · Models · Quick start · ComfyUI · Tasks · Usage guides · Roadmap · Changelog · Organization · Acknowledgments · Citation For limited VRAM, we strongly recommend Standard Lite to preserve Standard quality, or Flash Lite for a much smaller memory footprint and very fast generation. Start with the matching Lite checkpoint and lite.json ComfyUI workflow when choosing a memory-saving setup. At the shipped 4 steps, each preserves its corresponding original checkpoint's tested outputs; the BF16/INT8 switch remains available. VAE and shipped 3-step workflows. It retains Flash's fast generation and tested quality; Lite reduces the checkpoint footprint rather than promising extra speed over full Flash. These are DiT file sizes, not total runtime VRAM requirements. See the ComfyUI Lite setup and checkpoints. https://github.com/user-attachments/assets/25b49015-cf5a-4eb3-b7f9-165c3176db3e Preview compressed to 10 MB for this repository; for the full-quality demo, click the…
Read the full README ↗ · Preview checked 2026-10-30T17:34:56.561Z
Inside the original README — Document outline
- Recommended models for limited VRAM
- Paper
- Demo
- Introduction
- Overview
- Models
- Quick start
- 1. Install
- 2. Generate a video
- 3. Try visual inputs
- ComfyUI 🧩
- ⚡🔥 Flash three-step is live — and it is fast!
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the README
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: Other. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
What this repository does
LynnReal-Omni brings text-to-video, image-to-video, human- and hand-pose guided generation, structural control, omni-reference generation, style transfer, video editing, degraded-video restoration and streaming long-video generation into a single framework, all at four-step fast generation.
Repository facts
- Owner
- LynnReal-AI
- Primary language
- Python
- Stars
- 197
- Forks
- 8
- Open issues + pull requests
- 2
- License
- Other
- Archived
- No
- Default branch
- main
- Created
- 2026-09-13T11:11:45.000Z
- Last push
- 2026-09-19T09:21:29.000Z
Topics and intended use
Owner-supplied topics: benchmark, long-video-generation, multimodal, vae, video-dataset, video-generation, world-model
Review the README for scope, installation, examples and limitations. We do not run repository code or certify it.
Evaluate before installing
Review licensing and dependencies, inspect recent commits and unresolved issues, and test in an isolated environment before production use. Stars and forks alone cannot answer these questions.
Source and freshness
Source: GitHub. Metadata observed 2026-09-20T06:40:45.138Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related repositories
EbookFoundation/free-programming-books
donnemartin/system-design-primer