#3030th of 30 in Image and videoFor image, video and design, video and animation
skyreels-v2
Open-weight video diffusion models for long text- and image-to-video generation
Live demo ↗
(opens in a new tab)Documentation ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 7.7k
- License
- custom license
- Last commit
- Jan 2026
- Language
- Python
6,569 on 1 Apr 20267,712 on 21 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
SkyReels V2 provides weights and Python inference scripts for autoregressive diffusion-forcing video models at 1.3B and 14B parameters, at 540P and 720P. It supports text-to-video, image-to-video, video extension and start/end frame control, with clips generated in chunks to reach 30 to 60 seconds. Models are on Hugging Face and ModelScope, and Diffusers pipelines are included.
Who it is for: Engineers with large-VRAM GPUs running open video generation models
Strengths
- Diffusion-forcing models extend length by chunking; README gives frame counts for 10s to 60s clips
- Covers T2V, I2V, video extension and start/end frame control from one script
- Diffusers pipelines provided alongside native scripts
- Peak VRAM documented: about 14.7GB for 1.3B at 540P
Weaknesses
- 14B at 540P needs about 43 to 51GB peak VRAM, per the README
- 5B checkpoints and Camera Director models are still listed as coming soon
- Async mode needs frame counts divisible by causal_block_size, and is slower than sync
- No web UI or API server; inference runs through command-line scripts
What it needs
- GPU required
- Needs PyTorch, Hugging Face model weights, diffusers (optional)
- Models: SkyReels-V2-DF 1.3B/14B, SkyReels-V2-T2V 14B, SkyReels-V2-I2V 1.3B/14B, SkyCaptioner-V1
Also in Image and video
See all 30| Rank | Project | Score |
|---|---|---|
| 1 | MoneyPrinterTurboTurns a topic into a short video with script, footage, voiceover and subtitles | 76 out of 100 |
| 2 | ComfyUINode-graph editor for running diffusion image, video, audio and 3D workflows | 75 out of 100 |
| 3 | toonflow-appInfinite-canvas tool for AI short drama and comic video production | 72 out of 100 |
| #4 | InvokeAIWeb UI for diffusion image generation with inpainting canvas and node workflows | 68 out of 100 |
| #5 | infinite-canvasBrowser-based infinite canvas for AI image and video generation | 66 out of 100 |