| What it does | Text-to-image and image-to-image AI generator with accurate multilingual typography and world-knowledge reasoning
| Studio-quality demo videos made from your real product by AI
|
|---|
| Stage | Not given
| MVP
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| US
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | Free: 10 credits on signup. Hobby: $19/month (800 credits/month, personal use). Creator: $49/month (2,000 credits/month, commercial use, character lock & region prompting). Studio: $99/month (4,000 credits/month, team seats). One-time top-up available.
| The skill is free. The app is in early access with one free hosted video to start; pricing to be announced.
|
|---|
| Key features | - 99%+ text rendering in English, Chinese, Japanese, Arabic without retouching
- World-knowledge reasoning for accurate contextual details
- Native 2K, 16:9 & 9:16 output up to 4096×4096
- Sub-3 second single-pass generation
- Character lock consistency across batches
- Region-based editing with natural language prompts
- Image-to-image style transfer and reference editing
- Export as PNG, transparent PNG, or PDF
- Unified canvas for text-to-image and image-to-image workflows
- Draft, Standard, and HD quality tiers
| - Creates videos from real product screens without stock footage
- Four video types: launch, explainer, spotlight and ad
- Multiple formats from one project: landscape, vertical and 15 or 30 second cuts
- AI writes story with hook, problem and resolution
- Checks every frame before showing the video
- Edit by commenting directly on the video
- Generates thumbnails in every platform size
- Only changed scenes are rebuilt when UI updates
- Works with Claude Code, Codex, Gemini CLI, Figma and ElevenLabs
- Free voices included with ElevenLabs integration
|
|---|
| What makes it different | - Production-ready assets in one prompt without designer retouching needed
- Accurate multilingual text rendering across Latin, CJK, Arabic, and Cyrillic scripts
- World-knowledge reasoning model that understands context before drawing
- Native 2K output and sub-3 second generation speed
- Unified canvas replacing separate diffusion, ControlNet, and inpainting tools
| - Free and open source with no per-video cost
- Runs on your computer using your own Claude plan
- Every format generated from one project automatically
- Smart rebuilding when product changes
- Professional voice and music mixing included
|
|---|
| 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) | 13 ● no change since last check | 10 ▼ −1 (down) since last check |
| Trust Flow (Majestic) | 6 | 0 |
| Citation Flow (Majestic) | 21 | 15 |
| Referring domains (Majestic) | 38 | 6 |