real-time-pix2pix-turbo / static /controlnet.html
radames's picture
all static one folder
8b069db
raw
history blame
22.7 kB
<!doctype html>
<html>
<head>
<meta charset="UTF-8">
<title>Real-Time Latent Consistency Model ControlNet</title>
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<script
src="https://cdnjs.cloudflare.com/ajax/libs/iframe-resizer/4.3.1/iframeResizer.contentWindow.min.js"></script>
<script src="https://cdn.jsdelivr.net/npm/piexifjs@1.0.6/piexif.min.js"></script>
<script src="https://cdn.tailwindcss.com"></script>
<style type="text/tailwindcss">
.button {
@apply bg-gray-700 hover:bg-gray-800 text-white font-normal p-2 rounded disabled:bg-gray-300 dark:disabled:bg-gray-700 disabled:cursor-not-allowed dark:disabled:text-black
}
</style>
<script type="module">
const getValue = (id) => {
const el = document.querySelector(`${id}`)
if (el.type === "checkbox")
return el.checked;
return el.value;
}
const startBtn = document.querySelector("#start");
const stopBtn = document.querySelector("#stop");
const videoEl = document.querySelector("#webcam");
const imageEl = document.querySelector("#player");
const queueSizeEl = document.querySelector("#queue_size");
const errorEl = document.querySelector("#error");
const snapBtn = document.querySelector("#snap");
const webcamsEl = document.querySelector("#webcams");
function LCMLive(webcamVideo, liveImage) {
let websocket;
async function start() {
return new Promise((resolve, reject) => {
const websocketURL = `${window.location.protocol === "https:" ? "wss" : "ws"
}:${window.location.host}/ws`;
const socket = new WebSocket(websocketURL);
socket.onopen = () => {
console.log("Connected to websocket");
};
socket.onclose = () => {
console.log("Disconnected from websocket");
stop();
resolve({ "status": "disconnected" });
};
socket.onerror = (err) => {
console.error(err);
reject(err);
};
socket.onmessage = (event) => {
const data = JSON.parse(event.data);
switch (data.status) {
case "success":
break;
case "start":
const userId = data.userId;
initVideoStream(userId);
break;
case "timeout":
stop();
resolve({ "status": "timeout" });
case "error":
stop();
reject(data.message);
}
};
websocket = socket;
})
}
function switchCamera() {
const constraints = {
audio: false,
video: { width: 1024, height: 1024, deviceId: mediaDevices[webcamsEl.value].deviceId }
};
navigator.mediaDevices
.getUserMedia(constraints)
.then((mediaStream) => {
webcamVideo.removeEventListener("timeupdate", videoTimeUpdateHandler);
webcamVideo.srcObject = mediaStream;
webcamVideo.onloadedmetadata = () => {
webcamVideo.play();
webcamVideo.addEventListener("timeupdate", videoTimeUpdateHandler);
};
})
.catch((err) => {
console.error(`${err.name}: ${err.message}`);
});
}
async function videoTimeUpdateHandler() {
const dimension = getValue("input[name=dimension]:checked");
const [WIDTH, HEIGHT] = JSON.parse(dimension);
const canvas = new OffscreenCanvas(WIDTH, HEIGHT);
const videoW = webcamVideo.videoWidth;
const videoH = webcamVideo.videoHeight;
const aspectRatio = WIDTH / HEIGHT;
const ctx = canvas.getContext("2d");
ctx.drawImage(webcamVideo, videoW / 2 - videoH * aspectRatio / 2, 0, videoH * aspectRatio, videoH, 0, 0, WIDTH, HEIGHT)
const blob = await canvas.convertToBlob({ type: "image/jpeg", quality: 1 });
websocket.send(blob);
websocket.send(JSON.stringify({
"seed": getValue("#seed"),
"prompt": getValue("#prompt"),
"guidance_scale": getValue("#guidance-scale"),
"strength": getValue("#strength"),
"steps": getValue("#steps"),
"lcm_steps": getValue("#lcm_steps"),
"width": WIDTH,
"height": HEIGHT,
"controlnet_scale": getValue("#controlnet_scale"),
"controlnet_start": getValue("#controlnet_start"),
"controlnet_end": getValue("#controlnet_end"),
"canny_low_threshold": getValue("#canny_low_threshold"),
"canny_high_threshold": getValue("#canny_high_threshold"),
"debug_canny": getValue("#debug_canny")
}));
}
let mediaDevices = [];
async function initVideoStream(userId) {
liveImage.src = `/stream/${userId}`;
await navigator.mediaDevices.enumerateDevices()
.then(devices => {
const cameras = devices.filter(device => device.kind === 'videoinput');
mediaDevices = cameras;
webcamsEl.innerHTML = "";
cameras.forEach((camera, index) => {
const option = document.createElement("option");
option.value = index;
option.innerText = camera.label;
webcamsEl.appendChild(option);
option.selected = index === 0;
});
webcamsEl.addEventListener("change", switchCamera);
})
.catch(err => {
console.error(err);
});
const constraints = {
audio: false,
video: { width: 1024, height: 1024, deviceId: mediaDevices[0].deviceId }
};
navigator.mediaDevices
.getUserMedia(constraints)
.then((mediaStream) => {
webcamVideo.srcObject = mediaStream;
webcamVideo.onloadedmetadata = () => {
webcamVideo.play();
webcamVideo.addEventListener("timeupdate", videoTimeUpdateHandler);
};
})
.catch((err) => {
console.error(`${err.name}: ${err.message}`);
});
}
async function stop() {
websocket.close();
navigator.mediaDevices.getUserMedia({ video: true }).then((mediaStream) => {
mediaStream.getTracks().forEach((track) => track.stop());
});
webcamVideo.removeEventListener("timeupdate", videoTimeUpdateHandler);
webcamsEl.removeEventListener("change", switchCamera);
webcamVideo.srcObject = null;
}
return {
start,
stop
}
}
function toggleMessage(type) {
errorEl.hidden = false;
errorEl.scrollIntoView();
switch (type) {
case "error":
errorEl.innerText = "To many users are using the same GPU, please try again later.";
errorEl.classList.toggle("bg-red-300", "text-red-900");
break;
case "success":
errorEl.innerText = "Your session has ended, please start a new one.";
errorEl.classList.toggle("bg-green-300", "text-green-900");
break;
}
setTimeout(() => {
errorEl.hidden = true;
}, 2000);
}
function snapImage() {
try {
const zeroth = {};
const exif = {};
const gps = {};
zeroth[piexif.ImageIFD.Make] = "LCM Image-to-Image ControNet";
zeroth[piexif.ImageIFD.ImageDescription] = `prompt: ${getValue("#prompt")} | seed: ${getValue("#seed")} | guidance_scale: ${getValue("#guidance-scale")} | strength: ${getValue("#strength")} | controlnet_start: ${getValue("#controlnet_start")} | controlnet_end: ${getValue("#controlnet_end")} | lcm_steps: ${getValue("#lcm_steps")} | steps: ${getValue("#steps")}`;
zeroth[piexif.ImageIFD.Software] = "https://github.com/radames/Real-Time-Latent-Consistency-Model";
exif[piexif.ExifIFD.DateTimeOriginal] = new Date().toISOString();
const exifObj = { "0th": zeroth, "Exif": exif, "GPS": gps };
const exifBytes = piexif.dump(exifObj);
const canvas = document.createElement("canvas");
canvas.width = imageEl.naturalWidth;
canvas.height = imageEl.naturalHeight;
const ctx = canvas.getContext("2d");
ctx.drawImage(imageEl, 0, 0);
const dataURL = canvas.toDataURL("image/jpeg");
const withExif = piexif.insert(exifBytes, dataURL);
const a = document.createElement("a");
a.href = withExif;
a.download = `lcm_txt_2_img${Date.now()}.png`;
a.click();
} catch (err) {
console.log(err);
}
}
const lcmLive = LCMLive(videoEl, imageEl);
startBtn.addEventListener("click", async () => {
try {
startBtn.disabled = true;
snapBtn.disabled = false;
const res = await lcmLive.start();
startBtn.disabled = false;
if (res.status === "timeout")
toggleMessage("success")
} catch (err) {
console.log(err);
toggleMessage("error")
startBtn.disabled = false;
}
});
stopBtn.addEventListener("click", () => {
lcmLive.stop();
});
window.addEventListener("beforeunload", () => {
lcmLive.stop();
});
snapBtn.addEventListener("click", snapImage);
setInterval(() =>
fetch("/queue_size")
.then((res) => res.json())
.then((data) => {
queueSizeEl.innerText = data.queue_size;
})
.catch((err) => {
console.log(err);
})
, 5000);
</script>
</head>
<body class="text-black dark:bg-gray-900 dark:text-white">
<div class="fixed right-2 top-2 p-4 font-bold text-sm rounded-lg max-w-xs text-center" id="error">
</div>
<main class="container mx-auto px-4 py-4 max-w-4xl flex flex-col gap-4">
<article class="text-center max-w-xl mx-auto">
<h1 class="text-3xl font-bold">Real-Time Latent Consistency Model</h1>
<h2 class="text-2xl font-bold mb-4">ControlNet</h2>
<p class="text-sm">
This demo showcases
<a href="https://huggingface.co/SimianLuo/LCM_Dreamshaper_v7" target="_blank"
class="text-blue-500 underline hover:no-underline">LCM</a> Image to Image pipeline
using
<a href="https://github.com/huggingface/diffusers/tree/main/examples/community#latent-consistency-pipeline"
target="_blank" class="text-blue-500 underline hover:no-underline">Diffusers</a> with a MJPEG
stream server.
</p>
<p class="text-sm">
There are <span id="queue_size" class="font-bold">0</span> user(s) sharing the same GPU, affecting
real-time performance. Maximum queue size is 4. <a
href="https://huggingface.co/spaces/radames/Real-Time-Latent-Consistency-Model?duplicate=true"
target="_blank" class="text-blue-500 underline hover:no-underline">Duplicate</a> and run it on your
own GPU.
</p>
</article>
<div>
<h2 class="font-medium">Prompt</h2>
<p class="text-sm text-gray-500">
Change the prompt to generate different images, accepts <a
href="https://github.com/damian0815/compel/blob/main/doc/syntax.md" target="_blank"
class="text-blue-500 underline hover:no-underline">Compel</a> syntax.
</p>
<div class="flex text-normal px-1 py-1 border border-gray-700 rounded-md items-center">
<textarea type="text" id="prompt" class="font-light w-full px-3 py-2 mx-1 outline-none dark:text-black"
title="Prompt, this is an example, feel free to modify"
placeholder="Add your prompt here...">Portrait of The Terminator with , glare pose, detailed, intricate, full of colour, cinematic lighting, trending on artstation, 8k, hyperrealistic, focused, extreme details, unreal engine 5, cinematic, masterpiece</textarea>
</div>
</div>
<div class="">
<details>
<summary class="font-medium cursor-pointer">Advanced Options</summary>
<div class="grid grid-cols-3 sm:grid-cols-6 items-center gap-3 py-3">
<label for="webcams" class="text-sm font-medium">Camera Options: </label>
<select id="webcams" class="text-sm border-2 border-gray-500 rounded-md font-light dark:text-black">
</select>
<div></div>
<label class="text-sm font-medium " for="steps">Inference Steps
</label>
<input type="range" id="steps" name="steps" min="1" max="20" value="4"
oninput="this.nextElementSibling.value = Number(this.value)">
<output class="text-xs w-[50px] text-center font-light px-1 py-1 border border-gray-700 rounded-md">
4</output>
<!-- -->
<label class="text-sm font-medium" for="lcm_steps">LCM Inference Steps
</label>
<input type="range" id="lcm_steps" name="lcm_steps" min="2" max="60" value="50"
oninput="this.nextElementSibling.value = Number(this.value)">
<output class="text-xs w-[50px] text-center font-light px-1 py-1 border border-gray-700 rounded-md">
50</output>
<!-- -->
<label class="text-sm font-medium" for="guidance-scale">Guidance Scale
</label>
<input type="range" id="guidance-scale" name="guidance-scale" min="0" max="30" step="0.001"
value="8.0" oninput="this.nextElementSibling.value = Number(this.value).toFixed(2)">
<output class="text-xs w-[50px] text-center font-light px-1 py-1 border border-gray-700 rounded-md">
8.0</output>
<!-- -->
<label class="text-sm font-medium" for="strength">Strength</label>
<input type="range" id="strength" name="strength" min="0.1" max="1" step="0.001" value="0.50"
oninput="this.nextElementSibling.value = Number(this.value).toFixed(2)">
<output class="text-xs w-[50px] text-center font-light px-1 py-1 border border-gray-700 rounded-md">
0.5</output>
<!-- -->
<label class="text-sm font-medium" for="controlnet_scale">ControlNet Condition Scale</label>
<input type="range" id="controlnet_scale" name="controlnet_scale" min="0.0" max="1" step="0.001"
value="0.80" oninput="this.nextElementSibling.value = Number(this.value).toFixed(2)">
<output class="text-xs w-[50px] text-center font-light px-1 py-1 border border-gray-700 rounded-md">
0.8</output>
<!-- -->
<label class="text-sm font-medium" for="controlnet_start">ControlNet Guidance Start</label>
<input type="range" id="controlnet_start" name="controlnet_start" min="0.0" max="1.0" step="0.001"
value="0.0" oninput="this.nextElementSibling.value = Number(this.value).toFixed(2)">
<output class="text-xs w-[50px] text-center font-light px-1 py-1 border border-gray-700 rounded-md">
0.0</output>
<!-- -->
<label class="text-sm font-medium" for="controlnet_end">ControlNet Guidance End</label>
<input type="range" id="controlnet_end" name="controlnet_end" min="0.0" max="1.0" step="0.001"
value="1.0" oninput="this.nextElementSibling.value = Number(this.value).toFixed(2)">
<output class="text-xs w-[50px] text-center font-light px-1 py-1 border border-gray-700 rounded-md">
1.0</output>
<!-- -->
<label class="text-sm font-medium" for="canny_low_threshold">Canny Low Threshold</label>
<input type="range" id="canny_low_threshold" name="canny_low_threshold" min="0.0" max="1.0"
step="0.001" value="0.1"
oninput="this.nextElementSibling.value = Number(this.value).toFixed(2)">
<output class="text-xs w-[50px] text-center font-light px-1 py-1 border border-gray-700 rounded-md">
0.1</output>
<!-- -->
<label class="text-sm font-medium" for="canny_high_threshold">Canny High Threshold</label>
<input type="range" id="canny_high_threshold" name="canny_high_threshold" min="0.0" max="1.0"
step="0.001" value="0.2"
oninput="this.nextElementSibling.value = Number(this.value).toFixed(2)">
<output class="text-xs w-[50px] text-center font-light px-1 py-1 border border-gray-700 rounded-md">
0.2</output>
<!-- -->
<label class="text-sm font-medium" for="seed">Seed</label>
<input type="number" id="seed" name="seed" value="299792458"
class="font-light border border-gray-700 text-right rounded-md p-2 dark:text-black">
<button
onclick="document.querySelector('#seed').value = Math.floor(Math.random() * Number.MAX_SAFE_INTEGER)"
class="button">
Rand
</button>
<!-- -->
<!-- -->
<label class="text-sm font-medium" for="dimension">Image Dimensions</label>
<div class="col-span-2 flex gap-2">
<div class="flex gap-1">
<input type="radio" id="dimension512" name="dimension" value="[512,512]" checked
class="cursor-pointer">
<label for="dimension512" class="text-sm cursor-pointer">512x512</label>
</div>
<div class="flex gap-1">
<input type="radio" id="dimension768" name="dimension" value="[768,768]"
lass="cursor-pointer">
<label for="dimension768" class="text-sm cursor-pointer">768x768</label>
</div>
</div>
<!-- -->
<!-- -->
<label class="text-sm font-medium" for="debug_canny">Debug Canny</label>
<div class="col-span-2 flex gap-2">
<input type="checkbox" id="debug_canny" name="debug_canny" class="cursor-pointer">
<label for="debug_canny" class="text-sm cursor-pointer"></label>
</div>
<div></div>
<!-- -->
</div>
</details>
</div>
<div class="flex gap-3">
<button id="start" class="button">
Start
</button>
<button id="stop" class="button">
Stop
</button>
<button id="snap" disabled class="button ml-auto">
Snapshot
</button>
</div>
<div class="relative rounded-lg border border-slate-300 overflow-hidden">
<img id="player" class="w-full aspect-square rounded-lg"
src="data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAQAAAC1HAwCAAAAC0lEQVR42mNkYAAAAAYAAjCB0C8AAAAASUVORK5CYII=">
<div class="absolute top-0 left-0 w-1/4 aspect-square">
<video id="webcam" class="w-full aspect-square relative z-10 object-cover" playsinline autoplay muted
loop></video>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 448" width="100"
class="w-full p-4 absolute top-0 opacity-20 z-0">
<path fill="currentColor"
d="M224 256a128 128 0 1 0 0-256 128 128 0 1 0 0 256zm-45.7 48A178.3 178.3 0 0 0 0 482.3 29.7 29.7 0 0 0 29.7 512h388.6a29.7 29.7 0 0 0 29.7-29.7c0-98.5-79.8-178.3-178.3-178.3h-91.4z" />
</svg>
</div>
</div>
</main>
</body>
</html>