Zeroscope v2

Community · 2023 · Video Generation · USA

A to Z

A · App: No
B · Built By: Community
C · CEO & Politics: [UNKNOWN]
D · Date: 2023
E · Expertise: Intermediate+
F · Free Tier: Yes
G · Generates: Video
H · Deployment: Cloud + Local (open weights)
I · Inputs: Text
J · Jurisdiction: USA
K · Key Staffers: cerspense (Pseudonymous creator)
L · Languages: English-primary
M · Model Type: Video Generation
N · Safety Issues: None reported
O · Open Source: Yes — open weights
P · Pricing: Free (open weights, CC BY-NC 4.0, non-commercial)
Q · AIDb Rating: [UNKNOWN]
R · What Makes It Special: Watermark-free ModelScope-based text-to-video model (zeroscope_v2 576w), fine-tuned on 9,923 clips and 29,769 tagged frames at 24 frames and 576x320, meant for drafting before upscaling with zeroscope_v2_XL; it uses about 7.9 GB of VRAM for 30 frames.
S · Stock / Status: Research / open-source project
T · Training Cutoff: [UNKNOWN]
U · Users: [UNKNOWN]
V · Voice Chat: No
W · Weights: Downloadable
X · X Handle: [UNKNOWN]
Y · Year Founded: [UNKNOWN]
Z · Bottom Line: Open-weights Video Generation from Community, released 2023.

Data completeness 77% · Last verified 2026-05-12 · Primary source ↗

“Zeroscope v2.” AIDb — The AI Database. Verified 2026-05-12. https://theaidatabase.com/m/zeroscope-v2.html