Update files

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+public/banner.png filter=lfs diff=lfs merge=lfs -text
+public/logo.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -9,7 +9,9 @@ license: apache-2.0
 models:
   - onnx-community/Janus-1.3B-ONNX
 short_description: In-browser unified multimodal understanding and generation.
-thumbnail: https://huggingface.co/spaces/webml-community/janus-webgpu/resolve/main/banner.png
+thumbnail: https://huggingface.co/spaces/webml-community/janus-webgpu/resolve/main/public/banner.png
+app_build_command: npm run build
+app_file: dist/index.html
 ---
 
 # Janus 1.3B WebGPU

assets/index-Cy-lD5Cm.css

@@ -1 +0,0 @@
-@scope (.markdown){pre{margin:.5rem 0;white-space:break-spaces}code{padding:.2em .4em;border-radius:4px;font-family:Consolas,Monaco,Andale Mono,Ubuntu Mono,monospace;font-size:.9em}pre,code{background-color:#f2f2f2}@media (prefers-color-scheme: dark){pre,code{background-color:#333}}pre:has(code){padding:1rem .5rem}pre>code{padding:0}h1,h2,h3,h4,h5,h6{font-weight:600;line-height:1.2}h1{font-size:2em;margin:1rem 0}h2{font-size:1.5em;margin:.83rem 0}h3{font-size:1.25em;margin:.67rem 0}h4{font-size:1em;margin:.5rem 0}h5{font-size:.875em;margin:.33rem 0}h6{font-size:.75em;margin:.25rem 0}h1,h2,h3,h4,h5,h6:first-child{margin-top:0}ul{list-style-type:disc;margin-left:1.5rem}ol{list-style-type:decimal;margin-left:1.5rem}li{margin:.25rem 0}p:not(:first-child){margin-top:.75rem}p:not(:last-child){margin-bottom:.75rem}}*,:before,:after{box-sizing:border-box;border-width:0;border-style:solid;border-color:#e5e7eb}:before,:after{--tw-content: ""}html,:host{line-height:1.5;-webkit-text-size-adjust:100%;-moz-tab-size:4;-o-tab-size:4;tab-size:4;font-family:ui-sans-serif,system-ui,sans-serif,"Apple Color Emoji","Segoe UI Emoji",Segoe UI Symbol,"Noto Color Emoji";font-feature-settings:normal;font-variation-settings:normal;-webkit-tap-highlight-color:transparent}body{margin:0;line-height:inherit}hr{height:0;color:inherit;border-top-width:1px}abbr:where([title]){-webkit-text-decoration:underline dotted;text-decoration:underline dotted}h1,h2,h3,h4,h5,h6{font-size:inherit;font-weight:inherit}a{color:inherit;text-decoration:inherit}b,strong{font-weight:bolder}code,kbd,samp,pre{font-family:ui-monospace,SFMono-Regular,Menlo,Monaco,Consolas,Liberation Mono,Courier New,monospace;font-feature-settings:normal;font-variation-settings:normal;font-size:1em}small{font-size:80%}sub,sup{font-size:75%;line-height:0;position:relative;vertical-align:baseline}sub{bottom:-.25em}sup{top:-.5em}table{text-indent:0;border-color:inherit;border-collapse:collapse}button,input,optgroup,select,textarea{font-family:inherit;font-feature-settings:inherit;font-variation-settings:inherit;font-size:100%;font-weight:inherit;line-height:inherit;letter-spacing:inherit;color:inherit;margin:0;padding:0}button,select{text-transform:none}button,input:where([type=button]),input:where([type=reset]),input:where([type=submit]){-webkit-appearance:button;background-color:transparent;background-image:none}:-moz-focusring{outline:auto}:-moz-ui-invalid{box-shadow:none}progress{vertical-align:baseline}::-webkit-inner-spin-button,::-webkit-outer-spin-button{height:auto}[type=search]{-webkit-appearance:textfield;outline-offset:-2px}::-webkit-search-decoration{-webkit-appearance:none}::-webkit-file-upload-button{-webkit-appearance:button;font:inherit}summary{display:list-item}blockquote,dl,dd,h1,h2,h3,h4,h5,h6,hr,figure,p,pre{margin:0}fieldset{margin:0;padding:0}legend{padding:0}ol,ul,menu{list-style:none;margin:0;padding:0}dialog{padding:0}textarea{resize:vertical}input::-moz-placeholder,textarea::-moz-placeholder{opacity:1;color:#9ca3af}input::placeholder,textarea::placeholder{opacity:1;color:#9ca3af}button,[role=button]{cursor:pointer}:disabled{cursor:default}img,svg,video,canvas,audio,iframe,embed,object{display:block;vertical-align:middle}img,video{max-width:100%;height:auto}[hidden]{display:none}*,:before,:after{--tw-border-spacing-x: 0;--tw-border-spacing-y: 0;--tw-translate-x: 0;--tw-translate-y: 0;--tw-rotate: 0;--tw-skew-x: 0;--tw-skew-y: 0;--tw-scale-x: 1;--tw-scale-y: 1;--tw-pan-x: ;--tw-pan-y: ;--tw-pinch-zoom: ;--tw-scroll-snap-strictness: proximity;--tw-gradient-from-position: ;--tw-gradient-via-position: ;--tw-gradient-to-position: ;--tw-ordinal: ;--tw-slashed-zero: ;--tw-numeric-figure: ;--tw-numeric-spacing: ;--tw-numeric-fraction: ;--tw-ring-inset: ;--tw-ring-offset-width: 0px;--tw-ring-offset-color: #fff;--tw-ring-color: rgb(59 130 246 / .5);--tw-ring-offset-shadow: 0 0 #0000;--tw-ring-shadow: 0 0 #0000;--tw-shadow: 0 0 #0000;--tw-shadow-colored: 0 0 #0000;--tw-blur: ;--tw-brightness: ;--tw-contrast: ;--tw-grayscale: ;--tw-hue-rotate: ;--tw-invert: ;--tw-saturate: ;--tw-sepia: ;--tw-drop-shadow: ;--tw-backdrop-blur: ;--tw-backdrop-brightness: ;--tw-backdrop-contrast: ;--tw-backdrop-grayscale: ;--tw-backdrop-hue-rotate: ;--tw-backdrop-invert: ;--tw-backdrop-opacity: ;--tw-backdrop-saturate: ;--tw-backdrop-sepia: ;--tw-contain-size: ;--tw-contain-layout: ;--tw-contain-paint: ;--tw-contain-style: }::backdrop{--tw-border-spacing-x: 0;--tw-border-spacing-y: 0;--tw-translate-x: 0;--tw-translate-y: 0;--tw-rotate: 0;--tw-skew-x: 0;--tw-skew-y: 0;--tw-scale-x: 1;--tw-scale-y: 1;--tw-pan-x: ;--tw-pan-y: ;--tw-pinch-zoom: ;--tw-scroll-snap-strictness: proximity;--tw-gradient-from-position: ;--tw-gradient-via-position: ;--tw-gradient-to-position: ;--tw-ordinal: ;--tw-slashed-zero: ;--tw-numeric-figure: ;--tw-numeric-spacing: ;--tw-numeric-fraction: ;--tw-ring-inset: ;--tw-ring-offset-width: 0px;--tw-ring-offset-color: #fff;--tw-ring-color: rgb(59 130 246 / .5);--tw-ring-offset-shadow: 0 0 #0000;--tw-ring-shadow: 0 0 #0000;--tw-shadow: 0 0 #0000;--tw-shadow-colored: 0 0 #0000;--tw-blur: ;--tw-brightness: ;--tw-contrast: ;--tw-grayscale: ;--tw-hue-rotate: ;--tw-invert: ;--tw-saturate: ;--tw-sepia: ;--tw-drop-shadow: ;--tw-backdrop-blur: ;--tw-backdrop-brightness: ;--tw-backdrop-contrast: ;--tw-backdrop-grayscale: ;--tw-backdrop-hue-rotate: ;--tw-backdrop-invert: ;--tw-backdrop-opacity: ;--tw-backdrop-saturate: ;--tw-backdrop-sepia: ;--tw-contain-size: ;--tw-contain-layout: ;--tw-contain-paint: ;--tw-contain-style: }.pointer-events-none{pointer-events:none}.static{position:static}.fixed{position:fixed}.absolute{position:absolute}.relative{position:relative}.bottom-0{bottom:0}.bottom-3{bottom:.75rem}.left-1\.5{left:.375rem}.right-0{right:0}.right-3{right:.75rem}.top-0{top:0}.z-10{z-index:10}.m-1{margin:.25rem}.mx-auto{margin-left:auto;margin-right:auto}.my-3{margin-top:.75rem;margin-bottom:.75rem}.mb-0\.5{margin-bottom:.125rem}.mb-1{margin-bottom:.25rem}.mb-2{margin-bottom:.5rem}.mb-3{margin-bottom:.75rem}.mb-4{margin-bottom:1rem}.mr-1{margin-right:.25rem}.mt-2{margin-top:.5rem}.mt-auto{margin-top:auto}.block{display:block}.flex{display:flex}.hidden{display:none}.h-2\.5{height:.625rem}.h-20{height:5rem}.h-6{height:1.5rem}.h-8{height:2rem}.h-full{height:100%}.h-screen{height:100vh}.max-h-64{max-height:16rem}.max-h-\[200px\]{max-height:200px}.min-h-20{min-height:5rem}.min-h-6{min-height:1.5rem}.w-2\.5{width:.625rem}.w-20{width:5rem}.w-6{width:1.5rem}.w-8{width:2rem}.w-\[384px\]{width:384px}.w-\[600px\]{width:600px}.w-full{width:100%}.w-screen{width:100vw}.min-w-20{min-width:5rem}.min-w-6{min-width:1.5rem}.max-w-\[350px\]{max-width:350px}.max-w-\[452px\]{max-width:452px}.max-w-\[500px\]{max-width:500px}.max-w-\[600px\]{max-width:600px}.max-w-\[80\%\]{max-width:80%}.max-w-\[960px\]{max-width:960px}.max-w-full{max-width:100%}.flex-1{flex:1 1 0%}@keyframes pulse{50%{opacity:.5}}.animate-pulse{animation:pulse 2s cubic-bezier(.4,0,.6,1) infinite}.cursor-not-allowed{cursor:not-allowed}.cursor-pointer{cursor:pointer}.select-none{-webkit-user-select:none;-moz-user-select:none;user-select:none}.resize-none{resize:none}.flex-col{flex-direction:column}.items-start{align-items:flex-start}.items-center{align-items:center}.justify-end{justify-content:flex-end}.justify-center{justify-content:center}.gap-1{gap:.25rem}.space-x-4>:not([hidden])~:not([hidden]){--tw-space-x-reverse: 0;margin-right:calc(1rem * var(--tw-space-x-reverse));margin-left:calc(1rem * calc(1 - var(--tw-space-x-reverse)))}.space-y-4>:not([hidden])~:not([hidden]){--tw-space-y-reverse: 0;margin-top:calc(1rem * calc(1 - var(--tw-space-y-reverse)));margin-bottom:calc(1rem * var(--tw-space-y-reverse))}.overflow-auto{overflow:auto}.overflow-hidden{overflow:hidden}.overflow-y-auto{overflow-y:auto}.whitespace-nowrap{white-space:nowrap}.rounded-full{border-radius:9999px}.rounded-lg{border-radius:.5rem}.rounded-md{border-radius:.375rem}.border{border-width:1px}.border-none{border-style:none}.bg-black{--tw-bg-opacity: 1;background-color:rgb(0 0 0 / var(--tw-bg-opacity))}.bg-blue-400{--tw-bg-opacity: 1;background-color:rgb(96 165 250 / var(--tw-bg-opacity))}.bg-blue-500{--tw-bg-opacity: 1;background-color:rgb(59 130 246 / var(--tw-bg-opacity))}.bg-gray-100{--tw-bg-opacity: 1;background-color:rgb(243 244 246 / var(--tw-bg-opacity))}.bg-gray-200{--tw-bg-opacity: 1;background-color:rgb(229 231 235 / var(--tw-bg-opacity))}.bg-gray-600{--tw-bg-opacity: 1;background-color:rgb(75 85 99 / var(--tw-bg-opacity))}.bg-gray-800{--tw-bg-opacity: 1;background-color:rgb(31 41 55 / var(--tw-bg-opacity))}.bg-transparent{background-color:transparent}.bg-white{--tw-bg-opacity: 1;background-color:rgb(255 255 255 / var(--tw-bg-opacity))}.bg-opacity-\[92\%\]{--tw-bg-opacity: 92%}.fill-gray-200{fill:#e5e7eb}.object-cover{-o-object-fit:cover;object-fit:cover}.p-1{padding:.25rem}.p-2{padding:.5rem}.p-4{padding:1rem}.p-6{padding:1.5rem}.px-1{padding-left:.25rem;padding-right:.25rem}.px-4{padding-left:1rem;padding-right:1rem}.py-2{padding-top:.5rem;padding-bottom:.5rem}.py-4{padding-top:1rem;padding-bottom:1rem}.pl-11{padding-left:2.75rem}.pr-12{padding-right:3rem}.text-left{text-align:left}.text-center{text-align:center}.font-mono{font-family:ui-monospace,SFMono-Regular,Menlo,Monaco,Consolas,Liberation Mono,Courier New,monospace}.text-2xl{font-size:1.5rem;line-height:2rem}.text-5xl{font-size:3rem;line-height:1}.text-sm{font-size:.875rem;line-height:1.25rem}.text-xl{font-size:1.25rem;line-height:1.75rem}.text-xs{font-size:.75rem;line-height:1rem}.font-bold{font-weight:700}.font-medium{font-weight:500}.font-semibold{font-weight:600}.text-black{--tw-text-opacity: 1;color:rgb(0 0 0 / var(--tw-text-opacity))}.text-gray-400{--tw-text-opacity: 1;color:rgb(156 163 175 / var(--tw-text-opacity))}.text-gray-50{--tw-text-opacity: 1;color:rgb(249 250 251 / var(--tw-text-opacity))}.text-gray-500{--tw-text-opacity: 1;color:rgb(107 114 128 / var(--tw-text-opacity))}.text-gray-800{--tw-text-opacity: 1;color:rgb(31 41 55 / var(--tw-text-opacity))}.text-red-500{--tw-text-opacity: 1;color:rgb(239 68 68 / var(--tw-text-opacity))}.text-white{--tw-text-opacity: 1;color:rgb(255 255 255 / var(--tw-text-opacity))}.underline{text-decoration-line:underline}.placeholder-gray-500::-moz-placeholder{--tw-placeholder-opacity: 1;color:rgb(107 114 128 / var(--tw-placeholder-opacity))}.placeholder-gray-500::placeholder{--tw-placeholder-opacity: 1;color:rgb(107 114 128 / var(--tw-placeholder-opacity))}.outline-none{outline:2px solid transparent;outline-offset:2px}.filter{filter:var(--tw-blur) var(--tw-brightness) var(--tw-contrast) var(--tw-grayscale) var(--tw-hue-rotate) var(--tw-invert) var(--tw-saturate) var(--tw-sepia) var(--tw-drop-shadow)}.scrollbar-thin::-webkit-scrollbar{width:.5rem}.scrollbar-thin::-webkit-scrollbar-track{border-radius:9999px;--tw-bg-opacity: 1;background-color:rgb(243 244 246 / var(--tw-bg-opacity))}@media (prefers-color-scheme: dark){.scrollbar-thin::-webkit-scrollbar-track{--tw-bg-opacity: 1;background-color:rgb(55 65 81 / var(--tw-bg-opacity))}}.scrollbar-thin::-webkit-scrollbar-thumb{border-radius:9999px;--tw-bg-opacity: 1;background-color:rgb(209 213 219 / var(--tw-bg-opacity))}@media (prefers-color-scheme: dark){.scrollbar-thin::-webkit-scrollbar-thumb{--tw-bg-opacity: 1;background-color:rgb(75 85 99 / var(--tw-bg-opacity))}}.scrollbar-thin::-webkit-scrollbar-thumb:hover{--tw-bg-opacity: 1;background-color:rgb(107 114 128 / var(--tw-bg-opacity))}.animation-delay-200{animation-delay:.2s}.animation-delay-400{animation-delay:.4s}.overflow-wrap-anywhere{overflow-wrap:anywhere}.hover\:bg-blue-500:hover{--tw-bg-opacity: 1;background-color:rgb(59 130 246 / var(--tw-bg-opacity))}.disabled\:cursor-not-allowed:disabled{cursor:not-allowed}.disabled\:bg-blue-100:disabled{--tw-bg-opacity: 1;background-color:rgb(219 234 254 / var(--tw-bg-opacity))}.disabled\:text-gray-400:disabled{--tw-text-opacity: 1;color:rgb(156 163 175 / var(--tw-text-opacity))}.disabled\:placeholder-gray-200:disabled::-moz-placeholder{--tw-placeholder-opacity: 1;color:rgb(229 231 235 / var(--tw-placeholder-opacity))}.disabled\:placeholder-gray-200:disabled::placeholder{--tw-placeholder-opacity: 1;color:rgb(229 231 235 / var(--tw-placeholder-opacity))}@media (prefers-color-scheme: dark){.dark\:border-gray-600{--tw-border-opacity: 1;border-color:rgb(75 85 99 / var(--tw-border-opacity))}.dark\:bg-gray-100{--tw-bg-opacity: 1;background-color:rgb(243 244 246 / var(--tw-bg-opacity))}.dark\:bg-gray-300{--tw-bg-opacity: 1;background-color:rgb(209 213 219 / var(--tw-bg-opacity))}.dark\:bg-gray-600{--tw-bg-opacity: 1;background-color:rgb(75 85 99 / var(--tw-bg-opacity))}.dark\:bg-gray-700{--tw-bg-opacity: 1;background-color:rgb(55 65 81 / var(--tw-bg-opacity))}.dark\:bg-gray-900{--tw-bg-opacity: 1;background-color:rgb(17 24 39 / var(--tw-bg-opacity))}.dark\:fill-gray-400{fill:#9ca3af}.dark\:text-black{--tw-text-opacity: 1;color:rgb(0 0 0 / var(--tw-text-opacity))}.dark\:text-gray-100{--tw-text-opacity: 1;color:rgb(243 244 246 / var(--tw-text-opacity))}.dark\:text-gray-200{--tw-text-opacity: 1;color:rgb(229 231 235 / var(--tw-text-opacity))}.dark\:text-gray-300{--tw-text-opacity: 1;color:rgb(209 213 219 / var(--tw-text-opacity))}.dark\:text-gray-500{--tw-text-opacity: 1;color:rgb(107 114 128 / var(--tw-text-opacity))}.dark\:text-gray-800{--tw-text-opacity: 1;color:rgb(31 41 55 / var(--tw-text-opacity))}.dark\:text-white{--tw-text-opacity: 1;color:rgb(255 255 255 / var(--tw-text-opacity))}.dark\:placeholder-gray-300::-moz-placeholder{--tw-placeholder-opacity: 1;color:rgb(209 213 219 / var(--tw-placeholder-opacity))}.dark\:placeholder-gray-300::placeholder{--tw-placeholder-opacity: 1;color:rgb(209 213 219 / var(--tw-placeholder-opacity))}.dark\:disabled\:placeholder-gray-500:disabled::-moz-placeholder{--tw-placeholder-opacity: 1;color:rgb(107 114 128 / var(--tw-placeholder-opacity))}.dark\:disabled\:placeholder-gray-500:disabled::placeholder{--tw-placeholder-opacity: 1;color:rgb(107 114 128 / var(--tw-placeholder-opacity))}}

eslint.config.js

@@ -0,0 +1,38 @@
+import js from "@eslint/js";
+import globals from "globals";
+import react from "eslint-plugin-react";
+import reactHooks from "eslint-plugin-react-hooks";
+import reactRefresh from "eslint-plugin-react-refresh";
+
+export default [
+  { ignores: ["dist"] },
+  {
+    files: ["**/*.{js,jsx}"],
+    languageOptions: {
+      ecmaVersion: 2020,
+      globals: globals.browser,
+      parserOptions: {
+        ecmaVersion: "latest",
+        ecmaFeatures: { jsx: true },
+        sourceType: "module",
+      },
+    },
+    settings: { react: { version: "18.3" } },
+    plugins: {
+      react,
+      "react-hooks": reactHooks,
+      "react-refresh": reactRefresh,
+    },
+    rules: {
+      ...js.configs.recommended.rules,
+      ...react.configs.recommended.rules,
+      ...react.configs["jsx-runtime"].rules,
+      ...reactHooks.configs.recommended.rules,
+      "react/jsx-no-target-blank": "off",
+      "react-refresh/only-export-components": [
+        "warn",
+        { allowConstantExport: true },
+      ],
+    },
+  },
+];

index.html

@@ -5,8 +5,6 @@
     <link rel="icon" type="image/png" href="/logo.png" />
     <meta name="viewport" content="width=device-width, initial-scale=1.0" />
     <title>Janus WebGPU</title>
-    <script type="module" crossorigin src="/assets/index-FQf4wfd9.js"></script>
-    <link rel="stylesheet" crossorigin href="/assets/index-Cy-lD5Cm.css">
   </head>
 
   <body>
@@ -29,5 +27,6 @@
       id="MathJax-script"
       src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js"
     ></script>
+    <script type="module" src="/src/main.jsx"></script>
   </body>
 </html>

package.json

@@ -0,0 +1,34 @@
+{
+  "name": "smollm-webgpu",
+  "private": true,
+  "version": "0.0.0",
+  "type": "module",
+  "scripts": {
+    "dev": "vite",
+    "build": "vite build",
+    "lint": "eslint .",
+    "preview": "vite preview"
+  },
+  "dependencies": {
+    "@huggingface/transformers": "3.7.1",
+    "dompurify": "^3.1.2",
+    "marked": "^12.0.2",
+    "react": "^18.3.1",
+    "react-dom": "^18.3.1"
+  },
+  "devDependencies": {
+    "@eslint/js": "^9.9.0",
+    "@types/react": "^18.3.3",
+    "@types/react-dom": "^18.3.0",
+    "@vitejs/plugin-react": "^4.3.1",
+    "autoprefixer": "^10.4.20",
+    "eslint": "^9.9.0",
+    "eslint-plugin-react": "^7.35.0",
+    "eslint-plugin-react-hooks": "^5.1.0-rc.0",
+    "eslint-plugin-react-refresh": "^0.4.9",
+    "globals": "^15.9.0",
+    "postcss": "^8.4.41",
+    "tailwindcss": "^3.4.10",
+    "vite": "^6.2.0"
+  }
+}

postcss.config.js

@@ -0,0 +1,6 @@
+export default {
+  plugins: {
+    tailwindcss: {},
+    autoprefixer: {},
+  },
+};

src/App.jsx

@@ -0,0 +1,512 @@
+import { useEffect, useState, useRef } from "react";
+
+import Chat from "./components/Chat";
+import ArrowRightIcon from "./components/icons/ArrowRightIcon";
+import StopIcon from "./components/icons/StopIcon";
+import Progress from "./components/Progress";
+import ImageIcon from "./components/icons/ImageIcon";
+import ImagePreview from "./components/ImagePreview";
+
+const IS_WEBGPU_AVAILABLE = !!navigator.gpu;
+const STICKY_SCROLL_THRESHOLD = 120;
+const EXAMPLES = [
+  {
+    display: "Generate an image of a cute baby fox.",
+    prompt:
+      "/imagine A cute and adorable baby fox with big brown eyes, autumn leaves in the background enchanting, immortal, fluffy, shiny mane, Petals, fairyism, unreal engine 5 and Octane Render, highly detailed, photorealistic, cinematic, natural colors.",
+  },
+  {
+    prompt: "Convert the formula into latex code.",
+    image:
+      "https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/quadratic_formula.png",
+  },
+  {
+    prompt: "What is the difference between AI and ML?",
+  },
+  {
+    prompt: "Write python code to compute the nth fibonacci number.",
+  },
+];
+
+function App() {
+  // Create a reference to the worker object.
+  const worker = useRef(null);
+
+  const textareaRef = useRef(null);
+  const chatContainerRef = useRef(null);
+  const imageUploadRef = useRef(null);
+
+  // Model loading and progress
+  const [status, setStatus] = useState(null);
+  const [error, setError] = useState(null);
+  const [loadingMessage, setLoadingMessage] = useState("");
+  const [progressItems, setProgressItems] = useState([]);
+  const [isRunning, setIsRunning] = useState(false);
+
+  // Inputs and outputs
+  const [input, setInput] = useState("");
+  const [image, setImage] = useState(null);
+  const [messages, setMessages] = useState([]);
+  const [tps, setTps] = useState(null);
+  const [numTokens, setNumTokens] = useState(null);
+  const [imageProgress, setImageProgress] = useState(null);
+  const [imageGenerationTime, setImageGenerationTime] = useState(null);
+
+  function onEnter(message, img) {
+    setMessages((prev) => [
+      ...prev,
+      { role: "user", content: message, image: img ?? image },
+    ]);
+    setTps(null);
+    setIsRunning(true);
+    setInput("");
+    setImage(null);
+    setNumTokens(null);
+    setImageProgress(null);
+    setImageGenerationTime(null);
+  }
+
+  function onInterrupt() {
+    // NOTE: We do not set isRunning to false here because the worker
+    // will send a 'complete' message when it is done.
+    worker.current.postMessage({ type: "interrupt" });
+  }
+
+  function resizeInput() {
+    if (!textareaRef.current) return;
+
+    const target = textareaRef.current;
+    target.style.height = "auto";
+    const newHeight = Math.min(Math.max(target.scrollHeight, 24), 200);
+    target.style.height = `${newHeight}px`;
+  }
+
+  useEffect(() => {
+    resizeInput();
+  }, [input]);
+
+  // We use the `useEffect` hook to setup the worker as soon as the `App` component is mounted.
+  useEffect(() => {
+    // Create the worker if it does not yet exist.
+    if (!worker.current) {
+      worker.current = new Worker(new URL("./worker.js", import.meta.url), {
+        type: "module",
+      });
+      worker.current.postMessage({ type: "check" }); // Do a feature check
+    }
+
+    // Create a callback function for messages from the worker thread.
+    const onMessageReceived = (e) => {
+      switch (e.data.status) {
+        // WebGPU feature checking
+        case "success":
+          setStatus("idle");
+          break;
+        case "error":
+          setError(e.data.data);
+          break;
+
+        case "loading":
+          // Model file start load: add a new progress item to the list.
+          setStatus("loading");
+          setLoadingMessage(e.data.data);
+          break;
+
+        case "initiate":
+          setProgressItems((prev) => [...prev, e.data]);
+          break;
+
+        case "progress":
+          // Model file progress: update one of the progress items.
+          setProgressItems((prev) =>
+            prev.map((item) => {
+              if (item.file === e.data.file) {
+                return { ...item, ...e.data };
+              }
+              return item;
+            }),
+          );
+          break;
+
+        case "done":
+          // Model file loaded: remove the progress item from the list.
+          setProgressItems((prev) =>
+            prev.filter((item) => item.file !== e.data.file),
+          );
+          break;
+
+        case "ready":
+          // Pipeline ready: the worker is ready to accept messages.
+          setStatus("ready");
+          break;
+
+        case "start":
+          {
+            // Start generation
+            setMessages((prev) => [
+              ...prev,
+              { role: "assistant", content: "" },
+            ]);
+          }
+          break;
+
+        case "text-update":
+          // Generation update: update the output text.
+          // Parse messages
+          const { output, tps, numTokens } = e.data;
+          setTps(tps);
+          setNumTokens(numTokens);
+          setMessages((prev) => {
+            const cloned = [...prev];
+            const last = cloned.at(-1);
+            cloned[cloned.length - 1] = {
+              ...last,
+              content: last.content + output,
+            };
+            return cloned;
+          });
+          break;
+
+        case "image-update":
+          const { blob, progress, time } = e.data;
+
+          if (blob) {
+            // Add image to the last message
+            const url = URL.createObjectURL(blob);
+            setMessages((prev) => {
+              const cloned = [...prev];
+              const last = cloned.at(-1);
+              cloned[cloned.length - 1] = {
+                ...last,
+                image: url,
+              };
+              return cloned;
+            });
+          } else {
+            setImageProgress(progress);
+            setImageGenerationTime(time);
+          }
+          break;
+
+        case "complete":
+          // Generation complete: re-enable the "Generate" button
+          setIsRunning(false);
+          break;
+      }
+    };
+
+    const onErrorReceived = (e) => {
+      console.error("Worker error:", e);
+    };
+
+    // Attach the callback function as an event listener.
+    worker.current.addEventListener("message", onMessageReceived);
+    worker.current.addEventListener("error", onErrorReceived);
+
+    // Define a cleanup function for when the component is unmounted.
+    return () => {
+      worker.current.removeEventListener("message", onMessageReceived);
+      worker.current.removeEventListener("error", onErrorReceived);
+    };
+  }, []);
+
+  // Send the messages to the worker thread whenever the `messages` state changes.
+  useEffect(() => {
+    if (messages.filter((x) => x.role === "user").length === 0) {
+      // No user messages yet: do nothing.
+      return;
+    }
+    if (messages.at(-1).role === "assistant") {
+      // Do not update if the last message is from the assistant
+      return;
+    }
+    setTps(null);
+    worker.current.postMessage({ type: "generate", data: messages });
+  }, [messages, isRunning]);
+
+  useEffect(() => {
+    if (!chatContainerRef.current || !isRunning) return;
+    const element = chatContainerRef.current;
+    if (
+      element.scrollHeight - element.scrollTop - element.clientHeight <
+      STICKY_SCROLL_THRESHOLD
+    ) {
+      element.scrollTop = element.scrollHeight;
+    }
+  }, [messages, isRunning]);
+
+  return IS_WEBGPU_AVAILABLE ? (
+    <div className="flex flex-col h-screen mx-auto items justify-end text-gray-800 dark:text-gray-200 bg-white dark:bg-gray-900">
+      {(status === null || status === "idle") && messages.length === 0 && (
+        <div className="h-full overflow-auto scrollbar-thin flex justify-center items-center flex-col relative">
+          <div className="flex flex-col items-center mb-1 max-w-[350px] text-center">
+            <img
+              src="logo.png"
+              width="80%"
+              height="auto"
+              className="block"
+            ></img>
+            <h1 className="text-5xl font-bold mb-1">Janus WebGPU</h1>
+            <h2 className="font-semibold">
+              A novel autoregressive framework for unified multimodal
+              understanding and generation.
+            </h2>
+          </div>
+
+          <div className="flex flex-col items-center px-4">
+            <p className="max-w-[452px] mb-4">
+              <br />
+              You are about to load{" "}
+              <a
+                href="https://huggingface.co/onnx-community/Janus-1.3B-ONNX"
+                target="_blank"
+                rel="noreferrer"
+                className="font-medium underline"
+              >
+                Janus-1.3B
+              </a>
+              , a multimodal vision-language model that is optimized for
+              inference on the web. Everything runs 100% locally in your browser
+              with{" "}
+              <a
+                href="https://huggingface.co/docs/transformers.js"
+                target="_blank"
+                rel="noreferrer"
+                className="underline"
+              >
+                🤗&nbsp;Transformers.js
+              </a>{" "}
+              and ONNX Runtime Web, meaning no data is sent to a server. Once
+              the model has loaded, it can even be used offline. The source code
+              for the demo can be found on{" "}
+              <a
+                href="https://github.com/huggingface/transformers.js-examples/tree/main/janus-webgpu"
+                target="_blank"
+                rel="noreferrer"
+                className="font-medium underline"
+              >
+                GitHub
+              </a>
+              .
+            </p>
+
+            {error && (
+              <div className="text-red-500 text-center mb-2">
+                <p className="mb-1">
+                  Unable to load model due to the following error:
+                </p>
+                <p className="text-sm">{error}</p>
+              </div>
+            )}
+
+            {!error && (
+              <button
+                className="border px-4 py-2 rounded-lg bg-blue-400 text-white hover:bg-blue-500 disabled:bg-blue-100 disabled:cursor-not-allowed select-none"
+                onClick={() => {
+                  worker.current.postMessage({ type: "load" });
+                  setStatus("loading");
+                }}
+                disabled={status === null || status === "loading"}
+              >
+                {status === null ? "Running feature checks..." : "Load model"}
+              </button>
+            )}
+          </div>
+        </div>
+      )}
+      {status === "loading" && (
+        <>
+          <div className="w-full max-w-[500px] text-left mx-auto p-4 bottom-0 mt-auto">
+            <p className="text-center mb-1">{loadingMessage}</p>
+            {progressItems.map(({ file, progress, total }, i) => (
+              <Progress
+                key={i}
+                text={file}
+                percentage={progress}
+                total={total}
+              />
+            ))}
+          </div>
+        </>
+      )}
+
+      {status === "ready" && (
+        <div
+          ref={chatContainerRef}
+          className="overflow-y-auto scrollbar-thin w-full flex flex-col items-center h-full"
+        >
+          <Chat messages={messages} />
+          {messages.length === 0 && !image && (
+            <div className="flex flex-col center">
+              {EXAMPLES.map(({ display, prompt, image }, i) => (
+                <div
+                  key={i}
+                  className="max-w-[600px] m-1 border dark:border-gray-600 rounded-md p-2 bg-gray-100 dark:bg-gray-700 cursor-pointer"
+                  onClick={() => onEnter(prompt, image)}
+                >
+                  {display ?? prompt}
+                </div>
+              ))}
+            </div>
+          )}
+
+          <p className="text-center text-sm min-h-6 text-gray-500 dark:text-gray-300">
+            {messages.length > 0 && (
+              <>
+                {tps ? (
+                  <>
+                    {!isRunning && (
+                      <span>
+                        Generated {numTokens} tokens in{" "}
+                        {(numTokens / tps).toFixed(2)} seconds&nbsp;&#40;
+                      </span>
+                    )}
+                    <span className="font-medium font-mono text-center mr-1 text-black dark:text-white">
+                      {tps.toFixed(2)}
+                    </span>
+                    <span className="text-gray-500 dark:text-gray-300">
+                      tokens/second
+                    </span>
+                    {!isRunning && <span className="mr-1">&#41;.</span>}
+                  </>
+                ) : (
+                  imageProgress && (
+                    <>
+                      {isRunning ? (
+                        <>
+                          <span>Generating image...</span>&nbsp;&#40;
+                          <span className="font-medium font-mono text-center text-black dark:text-white">
+                            {(imageProgress * 100).toFixed(2)}%
+                          </span>
+                          <span className="mr-1">&#41;</span>
+                        </>
+                      ) : (
+                        <span>
+                          Generated image in{" "}
+                          {(imageGenerationTime / 1000).toFixed(2)}{" "}
+                          seconds.&nbsp;
+                        </span>
+                      )}
+                    </>
+                  )
+                )}
+
+                {!isRunning && (
+                  <span
+                    className="underline cursor-pointer"
+                    onClick={() => setMessages([])}
+                  >
+                    Reset
+                  </span>
+                )}
+              </>
+            )}
+          </p>
+        </div>
+      )}
+
+      <div className="mt-2 border dark:bg-gray-700 rounded-lg w-[600px] max-w-[80%] max-h-[200px] mx-auto relative mb-3 flex">
+        <label
+          htmlFor="file-upload"
+          className={
+            status === "ready"
+              ? "cursor-pointer"
+              : "cursor-not-allowed pointer-events-none"
+          }
+        >
+          <ImageIcon
+            className={`h-8 w-8 p-1 rounded-md ${status === "ready" ? "text-gray-800 dark:text-gray-100" : "text-gray-400 dark:text-gray-500"} absolute bottom-3 left-1.5`}
+          ></ImageIcon>
+          <input
+            ref={imageUploadRef}
+            id="file-upload"
+            type="file"
+            accept="image/*"
+            className="hidden"
+            onInput={(e) => {
+              const file = e.target.files[0];
+              if (!file) {
+                return;
+              }
+
+              const reader = new FileReader();
+
+              // Set up a callback when the file is loaded
+              reader.onload = (e2) => {
+                setImage(e2.target.result);
+                e.target.value = "";
+              };
+
+              reader.readAsDataURL(file);
+            }}
+          ></input>
+        </label>
+        <div className="w-full flex flex-col">
+          {image && (
+            <ImagePreview
+              onRemove={() => {
+                setImage(null);
+              }}
+              src={image}
+              className="w-20 h-20 min-w-20 min-h-20 relative p-2"
+            />
+          )}
+
+          <textarea
+            ref={textareaRef}
+            className="scrollbar-thin w-full pl-11 pr-12 dark:bg-gray-700 py-4 rounded-lg bg-transparent border-none outline-none text-gray-800 disabled:text-gray-400 dark:text-gray-100 placeholder-gray-500 disabled:placeholder-gray-200 dark:placeholder-gray-300 dark:disabled:placeholder-gray-500 resize-none disabled:cursor-not-allowed"
+            placeholder="Type message or use '/imagine <prompt>' to generate an image."
+            type="text"
+            rows={1}
+            value={input}
+            disabled={status !== "ready"}
+            title={
+              status === "ready" ? "Model is ready" : "Model not loaded yet"
+            }
+            onKeyDown={(e) => {
+              if (
+                input.length > 0 &&
+                !isRunning &&
+                e.key === "Enter" &&
+                !e.shiftKey
+              ) {
+                e.preventDefault(); // Prevent default behavior of Enter key
+                onEnter(input, image);
+              }
+            }}
+            onInput={(e) => setInput(e.target.value)}
+          />
+        </div>
+        {isRunning ? (
+          <div className="cursor-pointer" onClick={onInterrupt}>
+            <StopIcon className="h-8 w-8 p-1 rounded-md text-gray-800 dark:text-gray-100 absolute right-3 bottom-3" />
+          </div>
+        ) : input.length > 0 ? (
+          <div className="cursor-pointer" onClick={() => onEnter(input)}>
+            <ArrowRightIcon
+              className={`h-8 w-8 p-1 bg-gray-800 dark:bg-gray-100 text-white dark:text-black rounded-md absolute right-3 bottom-3`}
+            />
+          </div>
+        ) : (
+          <div>
+            <ArrowRightIcon
+              className={`h-8 w-8 p-1 bg-gray-200 dark:bg-gray-600 text-gray-50 dark:text-gray-800 rounded-md absolute right-3 bottom-3`}
+            />
+          </div>
+        )}
+      </div>
+
+      <p className="text-xs text-gray-400 text-center mb-3">
+        Disclaimer: Generated content may be inaccurate or false.
+      </p>
+    </div>
+  ) : (
+    <div className="fixed w-screen h-screen bg-black z-10 bg-opacity-[92%] text-white text-2xl font-semibold flex justify-center items-center text-center">
+      WebGPU is not supported
+      <br />
+      by this browser :&#40;
+    </div>
+  );
+}
+
+export default App;

src/components/Chat.css

@@ -0,0 +1,109 @@
+@scope (.markdown) {
+  /* Code blocks */
+  pre {
+    margin: 0.5rem 0;
+    white-space: break-spaces;
+  }
+
+  code {
+    padding: 0.2em 0.4em;
+    border-radius: 4px;
+    font-family: Consolas, Monaco, "Andale Mono", "Ubuntu Mono", monospace;
+    font-size: 0.9em;
+  }
+
+  pre,
+  code {
+    background-color: #f2f2f2;
+  }
+
+  @media (prefers-color-scheme: dark) {
+    pre,
+    code {
+      background-color: #333;
+    }
+  }
+
+  pre:has(code) {
+    padding: 1rem 0.5rem;
+  }
+
+  pre > code {
+    padding: 0;
+  }
+
+  /* Headings */
+  h1,
+  h2,
+  h3,
+  h4,
+  h5,
+  h6 {
+    font-weight: 600;
+    line-height: 1.2;
+  }
+
+  h1 {
+    font-size: 2em;
+    margin: 1rem 0;
+  }
+
+  h2 {
+    font-size: 1.5em;
+    margin: 0.83rem 0;
+  }
+
+  h3 {
+    font-size: 1.25em;
+    margin: 0.67rem 0;
+  }
+
+  h4 {
+    font-size: 1em;
+    margin: 0.5rem 0;
+  }
+
+  h5 {
+    font-size: 0.875em;
+    margin: 0.33rem 0;
+  }
+
+  h6 {
+    font-size: 0.75em;
+    margin: 0.25rem 0;
+  }
+
+  h1,
+  h2,
+  h3,
+  h4,
+  h5,
+  h6:first-child {
+    margin-top: 0;
+  }
+
+  /* Unordered List */
+  ul {
+    list-style-type: disc;
+    margin-left: 1.5rem;
+  }
+
+  /* Ordered List */
+  ol {
+    list-style-type: decimal;
+    margin-left: 1.5rem;
+  }
+
+  /* List Items */
+  li {
+    margin: 0.25rem 0;
+  }
+
+  p:not(:first-child) {
+    margin-top: 0.75rem;
+  }
+
+  p:not(:last-child) {
+    margin-bottom: 0.75rem;
+  }
+}

src/components/Chat.jsx

@@ -0,0 +1,78 @@
+import { marked } from "marked";
+import DOMPurify from "dompurify";
+
+import BotIcon from "./icons/BotIcon";
+import UserIcon from "./icons/UserIcon";
+
+import "./Chat.css";
+import { useEffect } from "react";
+
+function render(text) {
+  return DOMPurify.sanitize(marked.parse(text));
+}
+
+export default function Chat({ messages }) {
+  const empty = messages.length === 0;
+
+  useEffect(() => {
+    window.MathJax.typeset();
+  }, [messages]);
+
+  return (
+    <div
+      className={`flex-1 p-6 max-w-[960px] w-full ${empty ? "flex flex-col items-center justify-end" : "space-y-4"}`}
+    >
+      {empty ? (
+        <div className="text-xl">Ready!</div>
+      ) : (
+        messages.map((msg, i) => (
+          <div key={`message-${i}`} className="flex items-start space-x-4">
+            {msg.role === "assistant" ? (
+              <>
+                <BotIcon className="h-6 w-6 min-h-6 min-w-6 my-3 text-gray-500 dark:text-gray-300" />
+                <div className="bg-gray-200 dark:bg-gray-700 rounded-lg p-4">
+                  <p className="min-h-6 text-gray-800 dark:text-gray-200 overflow-wrap-anywhere">
+                    {msg.image ? (
+                      <img
+                        src={msg.image}
+                        className="max-w-full w-[384px] rounded-md"
+                      />
+                    ) : msg.content.length > 0 ? (
+                      <span
+                        className="markdown"
+                        dangerouslySetInnerHTML={{
+                          __html: render(msg.content),
+                        }}
+                      />
+                    ) : (
+                      <span className="h-6 flex items-center gap-1">
+                        <span className="w-2.5 h-2.5 bg-gray-600 dark:bg-gray-300 rounded-full animate-pulse"></span>
+                        <span className="w-2.5 h-2.5 bg-gray-600 dark:bg-gray-300 rounded-full animate-pulse animation-delay-200"></span>
+                        <span className="w-2.5 h-2.5 bg-gray-600 dark:bg-gray-300 rounded-full animate-pulse animation-delay-400"></span>
+                      </span>
+                    )}
+                  </p>
+                </div>
+              </>
+            ) : (
+              <>
+                <UserIcon className="h-6 w-6 min-h-6 min-w-6 my-3 text-gray-500 dark:text-gray-300" />
+                <div className="bg-blue-500 text-white rounded-lg p-4">
+                  {msg.image && (
+                    <img
+                      src={msg.image}
+                      className="max-w-full max-h-64 rounded-md mb-3"
+                    />
+                  )}
+                  <p className="min-h-6 overflow-wrap-anywhere">
+                    {msg.content}
+                  </p>
+                </div>
+              </>
+            )}
+          </div>
+        ))
+      )}
+    </div>
+  );
+}

src/components/ImagePreview.jsx

@@ -0,0 +1,24 @@
+import { useState } from "react";
+import CrossIcon from "./icons/CrossIcon";
+
+export default function ImagePreview({ src, onRemove, ...props }) {
+  const [hover, setHover] = useState(false);
+
+  return (
+    <div
+      {...props}
+      onMouseEnter={() => setHover(true)}
+      onMouseLeave={() => setHover(false)}
+    >
+      <CrossIcon
+        onClick={onRemove}
+        className={`absolute top-0 right-0 cursor-pointer dark:fill-gray-400 dark:text-gray-100 fill-gray-200 text-gray-800 ${hover ? "" : "hidden"}`}
+      />
+      <img
+        src={src}
+        alt="Upload preview"
+        className="w-full h-full object-cover rounded-md"
+      />
+    </div>
+  );
+}

src/components/Progress.jsx

@@ -0,0 +1,22 @@
+function formatBytes(size) {
+  const i = size == 0 ? 0 : Math.floor(Math.log(size) / Math.log(1024));
+  return (
+    +(size / Math.pow(1024, i)).toFixed(2) * 1 +
+    ["B", "kB", "MB", "GB", "TB"][i]
+  );
+}
+
+export default function Progress({ text, percentage, total }) {
+  percentage ??= 0;
+  return (
+    <div className="w-full bg-gray-100 dark:bg-gray-700 text-left rounded-lg overflow-hidden mb-0.5">
+      <div
+        className="bg-blue-400 whitespace-nowrap px-1 text-sm"
+        style={{ width: `${percentage}%` }}
+      >
+        {text} ({percentage.toFixed(2)}%
+        {isNaN(total) ? "" : ` of ${formatBytes(total)}`})
+      </div>
+    </div>
+  );
+}

src/components/icons/ArrowRightIcon.jsx

@@ -0,0 +1,19 @@
+export default function ArrowRightIcon(props) {
+  return (
+    <svg
+      {...props}
+      xmlns="http://www.w3.org/2000/svg"
+      width="24"
+      height="24"
+      viewBox="0 0 24 24"
+      fill="none"
+      stroke="currentColor"
+      strokeWidth="2"
+      strokeLinecap="round"
+      strokeLinejoin="round"
+    >
+      <path d="M5 12h14" />
+      <path d="m12 5 7 7-7 7" />
+    </svg>
+  );
+}

src/components/icons/BotIcon.jsx

@@ -0,0 +1,23 @@
+export default function BotIcon(props) {
+  return (
+    <svg
+      {...props}
+      xmlns="http://www.w3.org/2000/svg"
+      width="24"
+      height="24"
+      viewBox="0 0 24 24"
+      fill="none"
+      stroke="currentColor"
+      strokeWidth="2"
+      strokeLinecap="round"
+      strokeLinejoin="round"
+    >
+      <path d="M12 8V4H8" />
+      <rect width="16" height="12" x="4" y="8" rx="2" />
+      <path d="M2 14h2" />
+      <path d="M20 14h2" />
+      <path d="M15 13v2" />
+      <path d="M9 13v2" />
+    </svg>
+  );
+}

src/components/icons/CrossIcon.jsx

@@ -0,0 +1,18 @@
+export default function CrossIcon(props) {
+  return (
+    <svg
+      {...props}
+      xmlns="http://www.w3.org/2000/svg"
+      width="24"
+      height="24"
+      viewBox="0 0 24 24"
+      fill="none"
+      stroke="currentColor"
+      strokeWidth="2"
+      strokeLinecap="round"
+      strokeLinejoin="round"
+    >
+      <path d="m9.75 9.75 4.5 4.5m0-4.5-4.5 4.5M21 12a9 9 0 1 1-18 0 9 9 0 0 1 18 0Z" />
+    </svg>
+  );
+}

src/components/icons/ImageIcon.jsx

@@ -0,0 +1,18 @@
+export default function ImageIcon(props) {
+  return (
+    <svg
+      {...props}
+      xmlns="http://www.w3.org/2000/svg"
+      width="24"
+      height="24"
+      viewBox="0 0 24 24"
+      fill="none"
+      stroke="currentColor"
+      strokeWidth="2"
+      strokeLinecap="round"
+      strokeLinejoin="round"
+    >
+      <path d="m2.25 15.75 5.159-5.159a2.25 2.25 0 0 1 3.182 0l5.159 5.159m-1.5-1.5 1.409-1.409a2.25 2.25 0 0 1 3.182 0l2.909 2.909m-18 3.75h16.5a1.5 1.5 0 0 0 1.5-1.5V6a1.5 1.5 0 0 0-1.5-1.5H3.75A1.5 1.5 0 0 0 2.25 6v12a1.5 1.5 0 0 0 1.5 1.5Zm10.5-11.25h.008v.008h-.008V8.25Zm.375 0a.375.375 0 1 1-.75 0 .375.375 0 0 1 .75 0Z" />
+    </svg>
+  );
+}

src/components/icons/StopIcon.jsx

@@ -0,0 +1,22 @@
+export default function StopIcon(props) {
+  return (
+    <svg
+      {...props}
+      xmlns="http://www.w3.org/2000/svg"
+      width="24"
+      height="24"
+      viewBox="0 0 24 24"
+      fill="none"
+      stroke="currentColor"
+      strokeWidth="2"
+      strokeLinecap="round"
+      strokeLinejoin="round"
+    >
+      <path d="M21 12a9 9 0 1 1-18 0 9 9 0 0 1 18 0Z" />
+      <path
+        fill="currentColor"
+        d="M9 9.563C9 9.252 9.252 9 9.563 9h4.874c.311 0 .563.252.563.563v4.874c0 .311-.252.563-.563.563H9.564A.562.562 0 0 1 9 14.437V9.564Z"
+      />
+    </svg>
+  );
+}

src/components/icons/UserIcon.jsx

@@ -0,0 +1,19 @@
+export default function UserIcon(props) {
+  return (
+    <svg
+      {...props}
+      xmlns="http://www.w3.org/2000/svg"
+      width="24"
+      height="24"
+      viewBox="0 0 24 24"
+      fill="none"
+      stroke="currentColor"
+      strokeWidth="2"
+      strokeLinecap="round"
+      strokeLinejoin="round"
+    >
+      <path d="M19 21v-2a4 4 0 0 0-4-4H9a4 4 0 0 0-4 4v2" />
+      <circle cx="12" cy="7" r="4" />
+    </svg>
+  );
+}

src/index.css

@@ -0,0 +1,32 @@
+@tailwind base;
+@tailwind components;
+@tailwind utilities;
+
+@layer utilities {
+  .scrollbar-thin::-webkit-scrollbar {
+    @apply w-2;
+  }
+
+  .scrollbar-thin::-webkit-scrollbar-track {
+    @apply rounded-full bg-gray-100 dark:bg-gray-700;
+  }
+
+  .scrollbar-thin::-webkit-scrollbar-thumb {
+    @apply rounded-full bg-gray-300 dark:bg-gray-600;
+  }
+
+  .scrollbar-thin::-webkit-scrollbar-thumb:hover {
+    @apply bg-gray-500;
+  }
+
+  .animation-delay-200 {
+    animation-delay: 200ms;
+  }
+  .animation-delay-400 {
+    animation-delay: 400ms;
+  }
+
+  .overflow-wrap-anywhere {
+    overflow-wrap: anywhere;
+  }
+}

src/main.jsx

@@ -0,0 +1,10 @@
+import React from "react";
+import ReactDOM from "react-dom/client";
+import App from "./App.jsx";
+import "./index.css";
+
+ReactDOM.createRoot(document.getElementById("root")).render(
+  <React.StrictMode>
+    <App />
+  </React.StrictMode>,
+);

src/worker.js

@@ -0,0 +1,271 @@
+import {
+  AutoProcessor,
+  MultiModalityCausalLM,
+  BaseStreamer,
+  TextStreamer,
+  InterruptableStoppingCriteria,
+} from "@huggingface/transformers";
+
+// Define constants
+const IMAGE_GENERATION_COMMAND_PREFIX = "/imagine ";
+const MAX_NEW_TEXT_TOKENS = 1024;
+
+/**
+ * Helper function to perform WebGPU feature detection
+ */
+let fp16_supported = false;
+async function check() {
+  try {
+    const adapter = await navigator.gpu.requestAdapter();
+    if (!adapter) {
+      throw new Error("WebGPU is not supported (no adapter found)");
+    }
+    fp16_supported = adapter.features.has("shader-f16");
+    self.postMessage({
+      status: "success",
+      data: fp16_supported,
+    });
+  } catch (e) {
+    self.postMessage({
+      status: "error",
+      data: e.toString(),
+    });
+  }
+}
+
+/**
+ * This class uses the Singleton pattern to enable lazy-loading of the pipeline
+ */
+class ImageGenerationPipeline {
+  static model_id = "onnx-community/Janus-1.3B-ONNX";
+
+  static async getInstance(progress_callback = null) {
+    this.processor ??= AutoProcessor.from_pretrained(this.model_id, {
+      progress_callback,
+    });
+
+    this.model ??= MultiModalityCausalLM.from_pretrained(this.model_id, {
+      dtype: fp16_supported
+        ? {
+            prepare_inputs_embeds: "q4",
+            language_model: "q4f16",
+            lm_head: "fp16",
+            gen_head: "fp16",
+            gen_img_embeds: "fp16",
+            image_decode: "fp32",
+          }
+        : {
+            prepare_inputs_embeds: "fp32",
+            language_model: "q4",
+            lm_head: "fp32",
+            gen_head: "fp32",
+            gen_img_embeds: "fp32",
+            image_decode: "fp32",
+          },
+      device: {
+        prepare_inputs_embeds: "wasm", // TODO use "webgpu" when bug is fixed
+        language_model: "webgpu",
+        lm_head: "webgpu",
+        gen_head: "webgpu",
+        gen_img_embeds: "webgpu",
+        image_decode: "webgpu",
+      },
+      progress_callback,
+    });
+
+    return Promise.all([this.processor, this.model]);
+  }
+}
+
+class ProgressStreamer extends BaseStreamer {
+  constructor(total, on_progress) {
+    super();
+    this.total = total;
+    this.on_progress = on_progress;
+
+    this.count = null;
+    this.start_time = null;
+  }
+
+  put(value) {
+    if (this.count === null) {
+      // Ignore the first batch of tokens (prompt)
+      this.count = 0;
+      this.start_time = performance.now();
+      return;
+    }
+
+    const progress = ++this.count / this.total;
+
+    this.on_progress({
+      count: this.count,
+      total: this.total,
+      progress,
+      time: performance.now() - this.start_time,
+    });
+  }
+
+  end() {
+    /* no nothing */
+  }
+}
+
+const stopping_criteria = new InterruptableStoppingCriteria();
+
+async function generate(messages) {
+  // For this demo, we only respond to the last message
+  const message = messages.at(-1);
+
+  // Tell the main thread we are starting
+  self.postMessage({ status: "start" });
+
+  // Load the pipeline
+  const [processor, model] = await ImageGenerationPipeline.getInstance();
+
+  // Determine if the user wants to generate an image or text
+  if (message.content.startsWith(IMAGE_GENERATION_COMMAND_PREFIX)) {
+    const text = message.content.replace(IMAGE_GENERATION_COMMAND_PREFIX, "");
+
+    const conversation = [
+      {
+        role: "User", // uses title case
+        content: text,
+      },
+    ];
+    const inputs = await processor(conversation, {
+      chat_template: "text_to_image",
+    });
+
+    const callback_function = (output) => {
+      self.postMessage({
+        status: "image-update",
+        ...output,
+      });
+    };
+
+    const num_image_tokens = processor.num_image_tokens;
+    const streamer = new ProgressStreamer(num_image_tokens, callback_function);
+
+    const outputs = await model.generate_images({
+      ...inputs,
+      min_new_tokens: num_image_tokens,
+      max_new_tokens: num_image_tokens,
+      do_sample: true,
+      streamer,
+    });
+
+    const blob = await outputs[0].toBlob();
+
+    // Send the output back to the main thread
+    self.postMessage({
+      status: "image-update",
+      blob,
+    });
+  } else {
+    const inputs = await processor(
+      message.image
+        ? [
+            {
+              role: "User",
+              content: "<image_placeholder>\n" + message.content,
+              images: [message.image],
+            },
+          ]
+        : [
+            {
+              role: "System",
+              content:
+                "You are a helpful assistant. Answer the user's questions in a concise manner.",
+            },
+            {
+              role: "User",
+              content: message.content,
+            },
+          ],
+    );
+
+    let startTime;
+    let numTokens = 0;
+    let tps;
+    const token_callback_function = () => {
+      startTime ??= performance.now();
+
+      if (numTokens++ > 0) {
+        tps = (numTokens / (performance.now() - startTime)) * 1000;
+      }
+    };
+    const callback_function = (output) => {
+      self.postMessage({
+        status: "text-update",
+        output,
+        tps,
+        numTokens,
+      });
+    };
+
+    const streamer = new TextStreamer(processor.tokenizer, {
+      skip_prompt: true,
+      skip_special_tokens: true,
+      callback_function,
+      token_callback_function,
+    });
+
+    // Generate response
+    const outputs = await model.generate({
+      ...inputs,
+      max_new_tokens: MAX_NEW_TEXT_TOKENS,
+      do_sample: false,
+      streamer,
+      stopping_criteria,
+    });
+  }
+
+  // Tell the main thread we are done
+  self.postMessage({
+    status: "complete",
+  });
+}
+
+async function load() {
+  self.postMessage({
+    status: "loading",
+    data: "Loading model...",
+  });
+
+  // Load the pipeline and save it for future use.
+  const [processor, model] = await ImageGenerationPipeline.getInstance((x) => {
+    // We also add a progress callback to the pipeline so that we can
+    // track model loading.
+    self.postMessage(x);
+  });
+
+  self.postMessage({ status: "ready" });
+}
+
+// Listen for messages from the main thread
+self.addEventListener("message", async (e) => {
+  const { type, data } = e.data;
+
+  switch (type) {
+    case "check":
+      check();
+      break;
+
+    case "load":
+      load();
+      break;
+
+    case "generate":
+      stopping_criteria.reset();
+      generate(data);
+      break;
+
+    case "interrupt":
+      stopping_criteria.interrupt();
+      break;
+
+    case "reset":
+      stopping_criteria.reset();
+      break;
+  }
+});

tailwind.config.js

@@ -0,0 +1,8 @@
+/** @type {import('tailwindcss').Config} */
+export default {
+  content: ["./index.html", "./src/**/*.{js,ts,jsx,tsx}"],
+  theme: {
+    extend: {},
+  },
+  plugins: [],
+};

vite.config.js

@@ -0,0 +1,7 @@
+import { defineConfig } from "vite";
+import react from "@vitejs/plugin-react";
+
+// https://vitejs.dev/config/
+export default defineConfig({
+  plugins: [react()],
+});