Item logo image for diffusion-ui — live page mirror

diffusion-ui — live page mirror

Item media 6 (screenshot) for diffusion-ui — live page mirror
Item video thumbnail
Item media 2 (screenshot) for diffusion-ui — live page mirror
Item media 3 (screenshot) for diffusion-ui — live page mirror
Item media 4 (screenshot) for diffusion-ui — live page mirror
Item media 5 (screenshot) for diffusion-ui — live page mirror
Item media 6 (screenshot) for diffusion-ui — live page mirror
Item video thumbnail
Item video thumbnail
Item media 2 (screenshot) for diffusion-ui — live page mirror
Item media 3 (screenshot) for diffusion-ui — live page mirror
Item media 4 (screenshot) for diffusion-ui — live page mirror
Item media 5 (screenshot) for diffusion-ui — live page mirror
Item media 6 (screenshot) for diffusion-ui — live page mirror

Overview

A real-time AI-diffused mirror of your tab in a side panel, plus bundled Draw/3D/page playgrounds. Bring your own fal key.

This is an experimental Chrome extension that mirrors your active browser tab in real time and restyles the page from a prompt, using live image diffusion. It grabs your active tab a couple of times a second, runs each frame through a realtime img2img model, and shows the result in a side panel next to the real page. Scroll or type on the page and the mirror keeps repainting it as Claymation, Lego, Van Gogh, Manga, a wooly Wool/Felt world, or any of 35+ other prompts you can pick or write yourself. It's a bit laggy and expensive to run, so it's not meant for production. But it's a fun way to experiment with image diffusion models, and a glimpse of where this kind of thing might go. Expect roughly 2 frames a second. How it works It runs on the FLUX.2 [klein] model on fal.ai. - Capture: it screenshots your active tab with Chrome's tabs.captureVisibleTab, about twice a second. - Diffuse: each frame goes to fal's realtime img2img model (via @fal-ai/client) with your prompt. - Render: the result streams into a side panel next to the page, following whatever tab you're on. Everything runs client-side with your own fal API key. There's no backend of mine in the loop. Each frame goes straight from your browser to your fal account. Getting started 1. Make a fal account at https://fal.ai and add credits (generation is pay-as-you-go). 2. Create an API key at https://fal.ai/dashboard/keys. 3. Open the side panel, paste your key, pick a style, and watch your tab repaint. Also bundled A few self-contained playgrounds for poking at the same engine without capturing any tabs: a drawing pad, a small walkable 3D scene, and some mock pages. They diffuse only their own page. Follow fal's terms of service and privacy policy.

Details

  • Version
    0.1.0
  • Updated
    June 26, 2026
  • Size
    4.6MiB
  • Languages
    English (United States)
  • Developer
    Email
    ccraig.dev@gmail.com
  • Non-trader
    This developer has not identified itself as a trader. For consumers in the European Union, please note that consumer rights do not apply to contracts between you and this developer.

Privacy

Manage extensions and learn how they're being used in your organization

diffusion-ui — live page mirror has disclosed the following information regarding the collection and usage of your data. More detailed information can be found in the developer's privacy policy.

diffusion-ui — live page mirror handles the following:

Website content

This developer declares that your data is

  • Not being sold to third parties, outside of the approved use cases
  • Not being used or transferred for purposes that are unrelated to the item's core functionality
  • Not being used or transferred to determine creditworthiness or for lending purposes

Related

MirrorTab

4.8

Mirror any DOM interactions from a source tab to a target tab in real time.

Flowblock: Notion Diagrams & Flowcharts

0.0

Add Excalidraw and draw.io diagrams to Notion pages. Import Notion AI Mermaid flowcharts in one click. Native Notion blocks.

Vibe Check

0.0

Real-time design feedback and vibe checks for your web apps using AI.

Prompt Optimizer

0.0

Refine AI prompts in-page or in a popup. Gemini, OpenAI, or local Ollama. Templates, secure keys, side-by-side preview.

Runi - AI 网页助手:自动填表、网页自动化、总结翻译

0.0

侧边栏 AI 助手:一句话自动填表、点击和操作网页、总结翻译当前页面,做过的任务可保存后一键重放。支持 DeepSeek、OpenAI、Claude 等模型。

ClipShot

0.0

Right-click to copy a full-page screenshot straight to your clipboard — paste it into any AI chat.

ReproLens

0.0

Capture bugs with a click or a full-page scan, then export straight to your team's issue tracker. Local-first. No AI, no tracking.

Sephir — Browser-native AI agent

0.0

A real AI agent in every browser tab. Reads, clicks, fills, compares — powered by your ChatGPT Plus or your own API keys.

Deep Dream Generator - Ai Image

0.0

Generate stunning AI images effortlessly with Deep Dream Generator. Simply type a keyword and create unique visuals.

Overlay Image Tool

4.0

Overlay your design draft on any page to compare with the actual UI.

Summate: AI Page Summarizer

0.0

Instant AI summaries of any page. Free on-device AI — no account or API key. Works offline; use your own key for top models.

Picsi.Ai Face Swapper

3.7

Swap faces directly from your browser with InsightFace AI precision. Right-click any image and swap instantly!

MirrorTab

4.8

Mirror any DOM interactions from a source tab to a target tab in real time.

Flowblock: Notion Diagrams & Flowcharts

0.0

Add Excalidraw and draw.io diagrams to Notion pages. Import Notion AI Mermaid flowcharts in one click. Native Notion blocks.

Vibe Check

0.0

Real-time design feedback and vibe checks for your web apps using AI.

Prompt Optimizer

0.0

Refine AI prompts in-page or in a popup. Gemini, OpenAI, or local Ollama. Templates, secure keys, side-by-side preview.

Runi - AI 网页助手:自动填表、网页自动化、总结翻译

0.0

侧边栏 AI 助手:一句话自动填表、点击和操作网页、总结翻译当前页面,做过的任务可保存后一键重放。支持 DeepSeek、OpenAI、Claude 等模型。

ClipShot

0.0

Right-click to copy a full-page screenshot straight to your clipboard — paste it into any AI chat.

ReproLens

0.0

Capture bugs with a click or a full-page scan, then export straight to your team's issue tracker. Local-first. No AI, no tracking.

Sephir — Browser-native AI agent

0.0

A real AI agent in every browser tab. Reads, clicks, fills, compares — powered by your ChatGPT Plus or your own API keys.

Google apps