| What it does | Turn reference images and ideas into AI image prompts for any model
| AI video production studio with 21 studios and an autopilot editor
|
|---|
| Stage | Not given
| Startup
|
|---|
| Founded | Not given
| 2024
|
|---|
| Based in | Not given
| US
|
|---|
| Pricing model | Freemium
| Not given
|
|---|
| Pricing | Free: 10 credits/week (3 free prompts and 1 image/week without signup). Starter Monthly: $9.90/month (500 credits/month). Starter Yearly: $79.90/year (500 credits/month, save 33%). Pro Monthly: $19.90/month (1500 credits/month). Pro Yearly: $169.90/year (1500 credits/month, save 29%). Costs: 1 credi
| Free during launch: 2,000 credits per month, 10 GB storage, watermark-free exports. Paid plans starting from 5,000 credits per month and 25 GB storage are coming. Individual studios charge per output: AI Film from 250 credits per shot, Generate Video from 50 credits per minute, Dubbing from 50 credi
|
|---|
| Key features | - Multiple output formats: general prose, structured breakdown, graphic design analysis, JSON
- Target model optimization for Midjourney, Stable Diffusion, Flux, GPT Image, Nano Banana
- Image upload, paste, and URL linking in JPG, PNG, WEBP up to 10 MB
- Text to Prompt tool expands written ideas into complete image prompts
- AI Image Describer analyzes images in clear natural language
- AI Image Generator creates images from finished prompts with refinement
- Commercial license and no watermark on paid plans
- Free account creation via Google Sign-In with usage history tracking
| - 21 purpose-built AI studios for different video production tasks
- AI Film: generate multi-scene cinematic films from scripts with consistent characters
- Autopilot Editor: turn raw footage into finished edits with automatic cutting, framing, grading, captions and mixing
- Dubbing: translate and re-voice videos into 75+ languages keeping original speaker's voice
- Voice Clone: clone voice from 42-second sample and reuse for any script
- Doodle Explainer: generate hand-drawn whiteboard explainer videos
- AI Avatar Twins: create speaking avatars from a photo and voice sample
- No installation required: browser-based with renders running on servers
- Exports up to 4K without watermark on free plan
|
|---|
| What makes it different | - Model-aware syntax: tool automatically writes prompts in the format each AI model reads best instead of generic prose
- Editable starting points: all results are readable prompts users can adjust to preserve one quality while changing another
- Comprehensive toolkit: image-to-prompt, text-to-prompt, image description and generation in one workflow
- Privacy-first: uploaded images sent only for processing, never stored publicly or shown to other users
- Flexible credit system: one balance for all tools with no separate pools, 1 credit per prompt and 10 per image
| - All 21 studios accessible in one browser tab with a unified autopilot editor
- Editing and exporting never use credits; credits only for GPU-intensive generation
- Character consistency: AI Film maintains same protagonist across multi-scene films
- Renders continue running on servers when browser tab is closed
- Designed for low bandwidth and mid-range devices without performance sacrifice
|
|---|
| 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) | 25 ▲ +1 (up) since last check | Not checked yet ● no change since last check |
| Trust Flow (Majestic) | 5 | 0 |
| Citation Flow (Majestic) | 24 | 18 |
| Referring domains (Majestic) | 54 | 2 |