| What it does | Open-source video generation models and world simulators
| Motion transfer and object swap video generator
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | US
| Not given
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | Free plan: $0/month with 250 lifetime credits. Lite plan: 1,200 credits per month. Standard plan: 5,000 credits per month. Mochi video generation costs 100 credits; replay video costs 50 credits.
| Free: 18 starting credits plus up to 60 weekly check-in credits. Starter: $8.3/month or $100.0/year (2,400 credits/year). Pro: $30.0/month or $360.0/year (21,600 credits/year), 40% off. Business: $49.9/month or $599.0/year (48,000 credits/year), 50% off.
|
|---|
| Key features | - Text-to-video generation from written descriptions
- Local execution and customization via open-source repository
- ComfyUI integration for tailored experience
- Interactive playground for testing capabilities
- Commercial usage rights on paid plans
- MP4 video format with H.264 encoding
- Videos up to 5.4 seconds at 30fps
- Video download for 30 days after generation
- Watermark removal on paid plans
- High queue priority for paid users
| - Motion transfer to recast performances with new people or pets
- Object swap to feature different products, vehicles, or props in scenes
- Community presets with ready-made setups and reference clips
- Support for multiple reference images and video uploads
- Multiple AI models: Seedance, Kling, and Wan
- Resolution options up to 4K for images and HD for videos
- Custom prompt support for more control over generations
- Video history and watermark-free downloads with paid plans
- Motion templates with dance, sports, and gesture options
- Shared credit system across image and video generation
|
|---|
| What makes it different | - Apache 2.0 licensed open-source model for individual and commercial use
- World simulator technology for embodied AI breakthroughs
- Team with 55,000+ citations across foundational AI research
- Run locally without vendor lock-in
- State-of-the-art open text-to-video model
| - Video reference approach that lets you show action instead of describing every movement
- Single credit system unified across all image and video models
- Community presets that combine clip, reference images, and instructions in one setup
- Support for object swap effects on reflections, labels, edges, and surrounding details
- Flexible model selection with different capabilities for motion control and photo orientation
|
|---|
| Free plan | Not given
| Not given
|
|---|
| Open source | Not given
| Not given
|
|---|
| Platforms | Not given
| Not given
|
|---|
| Public API | Not given
| Not given
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 65 ▲ +1 (up) since last check | 31 ▼ −1 (down) since last check |
|---|
| Trust Flow (Majestic) | 33 | 4 |
|---|
| Citation Flow (Majestic) | 42 | 29 |
|---|
| Referring domains (Majestic) | 3405 | 57 |
|---|
Genjutsu AI