| What it does | Transform text descriptions into high-quality professional videos using advanced AI
| Turn any web image into an editable AI prompt, then recreate the style with your own photo
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| Not given
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | Hobby $7.92/month (200 Credits/month), Basic $15.92/month (500 Credits/month), Pro $39.92/month (2000 Credits/month), Lite $5.99 one-time (50 Credits). 1 credit generates 1 AI artwork.
| Free: 3 welcome credits, no account needed. Starter: $4.99 for 120 credits. Creator: $9.99 for 300 credits. Studio: $19.99 for 700 credits. One-time purchases in USD, never expire.
|
|---|
| Key features | - Advanced 30-billion parameter AI model for detailed video generation
- Generate videos up to 204 frames long
- Video-VAE deep compression technology for faster processing
- High-quality visual output with DiT and 3D Full Attention mechanism
- Bilingual text input support for English and Chinese
- Customizable video length and style settings
- No ads and no watermark on generated videos
- Priority generation queue for faster processing
| - Analyze web images to generate structured photographic recipes with subject, lighting, setting, framing, lens, palette and grain
- Edit prompts with treatment options, avoidance lists, and word-by-word customization before generating
- Create reusable person cards from 1-5 everyday photos that preserve face and identity
- Generate coordinated 2×2 photo sets with four different poses in matching style
- Local inspiration library with no sign-in required to collect and organize images
- Works on regular HTTP and HTTPS web pages including moodboards, portfolios, shops, social feeds and stock photo sites
- Copy prompts in detailed, short or tag formats to use in Midjourney, Stable Diffusion, Flux, ChatGPT and other text-to-image tools
- Region select to capture backgrounds, video frames and canvas art beyond standard images
- Upscale generated images after selection
|
|---|
| What makes it different | - Supports up to 204 frames, enabling longer and more complete video narratives
- Bilingual AI understanding for both English and Chinese creators
- Continuous optimization through human feedback-based preference learning
- No watermarks and no ads on any subscription tier
| - Structured photographic recipe format with editable components instead of plain image captions
- Face and identity preservation when applying reference styles to user's own photos through person cards
- Local-first privacy design with no uploads until user explicitly clicks a button
- Works directly on any website via Chrome extension without leaving your current page
- One-time credit purchases with no subscription and credits that never expire
|
|---|
| 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) | 6 ▼ −1 (down) since last check | Not checked yet ● no change since last check |
|---|
| Trust Flow (Majestic) | 2 | 0 |
|---|
| Citation Flow (Majestic) | 10 | 4 |
|---|
| Referring domains (Majestic) | 13 | 1 |
|---|
Step Video T2V
LookRecipe