| What it does | Text to image in about two seconds with eight-step distilled model
| 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 | Free credits available; paid annual plans with 50% launch discount: Basic $9.9/month (800 credits/month, 9600 credits/year), Professional $19.9/month (2000 credits/month, 24000 credits/year), Enterprise $44.9/month (6000 credits/month, 72000 credits/year). Monthly plans also available. Per-render co
| 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 | - Eight-step sampling produces 1024px drafts in roughly two seconds
- Text to image and image to image workflows in one workspace
- Support for LoRA attachments with no extra render cost
- Resolution from small exploratory sizes up to 2K
- Open weights published under custom licence permitting commercial use
- Photographic base behaviour from 12B model trained from scratch
- LoRAs behave as bipolar sliders for intensity control mid-series
- Browser-based workspace with no GPU or local install required
- Same 12B backbone as standard Krea 2 via trajectory distillation
- Unlimited exports in PNG, JPG and WebP formats
| - 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 | - Two-second generation speed enables iteration-heavy workflows instead of single-frame rendering
- Open weights allow running the same model locally without vendor lock-in
- Trajectory distillation preserves detail of full 12B model at eight-step speed
| - 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) | 15 ▼ −1 (down) since last check | Not checked yet ● no change since last check |
|---|
| Trust Flow (Majestic) | 20 | 0 |
|---|
| Citation Flow (Majestic) | 10 | 4 |
|---|
| Referring domains (Majestic) | 63 | 1 |
|---|
Krea 2 Turbo
LookRecipe