CogVideoX1.5-5B
Zhipu's 5B open video model — text-to-video and image-to-video from the CogVideo lineage.
About
CogVideoX1.5-5B (November 2024) is Zhipu AI's 5-billion-parameter open video model: text-to-video and image-to-video generation in the CogVideo lineage (successor to CogVideoX-5B, already in the catalog). A mid-size open checkpoint practical for experimentation.
Licensing: the Hugging Face checkpoint carries a custom "other" license (Zhipu) — not OSI open source. Review terms before commercial use; Zhipu's model licenses have historically limited commercial deployment. Direct adoption is small (959 HF downloads). As a 2024 5B model it is superseded on quality by 2025-2026 releases, but remains a usable open checkpoint for pipelines already built on the CogVideoX family.
Specs
Context window
Pricing
Free quota
API access
Weights
Released
Benchmarks
Provider-claimed (Zhipu): improved quality over CogVideoX-5B — treat as provider-claimed and dated. No current leaderboard presence.
Provider-reported unless a source says otherwise. Benchmarks are marketing-adjacent by nature — treat them as directional.
Use cases
Trust score — 5/10
Scored 5/10 (metrics tier). A usable 5B open video checkpoint for the CogVideoX family, but limited: (1) custom Zhipu license — not open source; (2) small adoption (959 HF downloads); (3) 2024-era, superseded on quality; (4) quality claims are dated provider reports. Keep for existing CogVideoX pipelines; new builds should look at LTX-2 or WAN 2.2.
How the trust score is built
Full methodology →- Adoption · stars/downloads, log-scaled vs peers
- 4.9/10
- Maintenance · recency, releases, issue load
- 5.0/10
- Openness · license + docs
- 4.6/10
- Manual review · sanity read + red-flag check
- 5.0/10
- · HF downloads 959 (peer-normalized)
- · released 701 days ago
- · manual review: usable 5B checkpoint for CogVideoX pipelines; 2024-era, superseded on quality; license: custom Zhipu license — not OSI; commercial terms unclear