AOpen
Wan 2.1
Alibaba (Tongyi Lab)
The foundation that started it all. 1.3B variant runs on virtually any GPU. First open model to beat closed-source across benchmarks.
AOpen
SkyReels V2
Skywork AI
First open model for infinite-length video. Best human rendering in open source.
Pick Wan 2.1 if…
You want consumer GPU workflows, academic research, or Chinese + English text-in-video.
Pick SkyReels V2 if…
You want long-form AI films, human-centric content, or short films and ads.
Specifications
Maker
Alibaba (Tongyi Lab)
Skywork AI
Source Type
Open Source
Open Source
License
Apache 2.0
Open Source
Architecture
Flow Matching DiT + 3D Causal VAE
AR Diffusion-Forcing
Parameters
14B (also 1.3B variant)
14B
Max Resolution
720p
720p
Max Duration
5s
30s+ (infinite)
FPS
24
24
Native Audio
No
No
ComfyUI Support
Yes
No
Fine-tunable
Yes
Yes
Min VRAM
8.19GB (1.3B) / 24GB+ (14B)
40GB+ (A100/H100)
Cost / Second
Self-host
Self-host
Inputs
T2V (14B/1.3B), I2V (14B), FLF2V, VACE, V2A
T2V, I2V
On Floyo
Yes
No
Strengths & Trade-offs
Wan 2.1
Strengths
- +SOTA open-source at launch
- +1.3B model runs on any consumer GPU (8.19GB VRAM)
- +first video model with Chinese + English text generation
- +Wan-VAE encodes unlimited-length 1080P
- +T2V/I2V/Video Editing/T2I/V2A all supported
Trade-offs
- -720p max
- -5s duration
- -1.3B quality limited
- -no native audio generation
- -superseded by 2.2 on quality
Best For
- →Budget local deployment
- →consumer GPU workflows
- →academic research
- →Chinese + English text-in-video
SkyReels V2
Strengths
- +First infinite-length open model
- +10M+ film/TV training
- +best open human faces
Trade-offs
- -Heavy GPU req
- -no ComfyUI
- -newer community
- -720p cap
Best For
- →Long-form AI films
- →human-centric content
- →short films and ads