# CogVideoX

> Model for generating videos from text prompts or images with flexible input options

- **Canonical URI:** https://www.vioscale.ai/software/cogvideox
- **Category:** AI Video Generation
- **Homepage:** https://github.com/THUDM/CogVideo
- **Also known as:** cogvideox
- **Profile claimed by vendor:** no
- **Last updated:** 2026-08-31T14:37:13.497Z

## Vioscale score

**21.6 / 100**, confidence 12% (low). Computed 2026-09-01.

Composite of weighted, independently-sourced signals (no user reviews, no vendor payment).

| Signal | Score | Weight | Contribution | Evidence present |
|---|--:|--:|--:|:--:|
| capabilities | 28.9 | 0.07844444444444446 | 2.3 | ✓ |
| repo_stars | 77.6 | 0.026 | 2 | ✓ |
| integrations | 0 | 0.07033333333333334 | 0 | - |
| dependent_projects | 0 | 0.063 | 0 | - |
| dev_activity | 0 | 0.094 | 0 | ✓ |
| release_cadence | 0 | 0.052 | 0 | - |
| security_posture | 0 | 0.073 | 0 | - |
| package_downloads | 0 | 0.136 | 0 | - |
| security_score | 0 | 0.042 | 0 | - |
| community_qa_activity | 0 | 0.063 | 0 | - |

## Pricing

_As of 2026-08-31, [verify at source](https://github.com/pricing). Independently observed._

Open source · Free tier

## About

An open source video generation model supporting text-to-video, image-to-video, and video continuation modes with optimizations for efficient inference.

_Independently observed._

## Platform & deployment
- **Deployment:** Cloud / SaaS, Self-hosted

## Capabilities

_The capabilities that matter for AI Video Generation. "-" = undocumented, not absent._

| Capability | Supported |
|---|:--:|
| **Capabilities** | |
| Architecture model | Foundational model research |
| Generation focus | - |
| Text to video and image to video keyframing | ✓ |
| Photorealistic lip sync and human micro expressions | - |
| Custom digital twin avatar training from webcam | - |
| Automatic translated dubbing retaining original voice | - |
| Temporal consistency for multi shot narrative continuity | - |
| Camera motion control panning tilting and zoom | - |
| Video to video style transfer and rotoscoping | - |
| Watermarking and deepfake generation safety filters | - |
| SOC2 type ii | - |
| ISO 27001 | - |
| Pricing model | - |

## Release history

| Version | Date | Type |
|---|---|---|
| [v1.0](https://github.com/zai-org/CogVideo/releases/tag/v1.0) | 2024-11-08 | stable |

## Facts

Every value below carries its source and our confidence. Facts are re-crawled on a freshness schedule.

### activity

| Attribute | Value | Source | Retrieved | Confidence |
|---|---|---|---|---|
| activity.commits_last_30d | 0 | [link](https://github.com/THUDM/CogVideo/pulse) | 2026-08-31 | 65% (medium) |

### adoption

| Attribute | Value | Source | Retrieved | Confidence |
|---|---|---|---|---|
| adoption.github_stars | 12,988 | [link](https://github.com/THUDM/CogVideo) | 2026-08-31 | 90% (high) |

### language

| Attribute | Value | Source | Retrieved | Confidence |
|---|---|---|---|---|
| language.primary | Python | [link](https://github.com/THUDM/CogVideo) | 2026-08-31 | 90% (high) |

### license

| Attribute | Value | Source | Retrieved | Confidence |
|---|---|---|---|---|
| license.spdx | Apache-2.0 | [link](https://github.com/THUDM/CogVideo) | 2026-08-31 | 95% (high) |

### pricing

| Attribute | Value | Source | Retrieved | Confidence |
|---|---|---|---|---|
| pricing.model | open_source | [link](https://github.com/pricing) | 2026-08-31 | 60% (medium) |
| pricing.free_tier | yes | [link](https://github.com/pricing) | 2026-08-31 | 60% (medium) |
| pricing.price_level | free | [link](https://github.com/pricing) | 2026-08-31 | 60% (medium) |

### security

| Attribute | Value | Source | Retrieved | Confidence |
|---|---|---|---|---|
| security.trust_center | https://github.com/security | [link](https://github.com/pricing) | 2026-08-31 | 60% (medium) |

---
*Source: Vioscale (https://www.vioscale.ai/software/cogvideox). Independent, evidence-based software intelligence. Cite the canonical URI.*