Welcome
ThinkDiffusion/ ThinkDiffusionXL
API Sample: ThinkDiffusion/ThinkDiffusionXL
You don't have any projects yet. To be able to use our api service effectively, please sign in/up and create a project.
Get your api keyPrepare Authentication Signature
//Sign up Wiro dashboard and create project
export YOUR_API_KEY="{{useSelectedProjectAPIKey}}";
export YOUR_API_SECRET="XXXXXXXXX";
//unix time or any random integer value
export NONCE=$(date +%s);
//hmac-SHA256 (YOUR_API_SECRET+Nonce) with YOUR_API_KEY
export SIGNATURE="$(echo -n "${YOUR_API_SECRET}${NONCE}" | openssl dgst -sha256 -hmac "${YOUR_API_KEY}")";
Create a New Folder - Make HTTP Post Request
Create a New Folder - Response
Upload a File to the Folder - Make HTTP Post Request
Upload a File to the Folder - Response
Run Command - Make HTTP Post Request
curl -X POST "{{apiUrl}}/Run/{{toolSlugOwner}}/{{toolSlugProject}}" \
-H "Content-Type: {{contentType}}" \
-H "x-api-key: ${YOUR_API_KEY}" \
-H "x-nonce: ${NONCE}" \
-H "x-signature: ${SIGNATURE}" \
-d '{{toolParameters}}';
Run Command - Response
//response body
{
"errors": [],
"taskid": "2221",
"socketaccesstoken": "eDcCm5yyUfIvMFspTwww49OUfgXkQt",
"result": true
}
Get Task Detail - Make HTTP Post Request
curl -X POST "{{apiUrl}}/Task/Detail" \
-H "Content-Type: {{contentType}}" \
-H "x-api-key: ${YOUR_API_KEY}" \
-H "x-nonce: ${NONCE}" \
-H "x-signature: ${SIGNATURE}" \
-d '{
"tasktoken": 'eDcCm5yyUfIvMFspTwww49OUfgXkQt',
}';
Get Task Detail - Response
//response body
{
"total": "1",
"errors": [],
"tasklist": [
{
"id": "2221",
"uuid": "15bce51f-442f-4f44-a71d-13c6374a62bd",
"name": "",
"socketaccesstoken": "eDcCm5yyUfIvMFspTwww49OUfgXkQt",
"parameters": {
"inputImage": "https://api.wiro.ai/v1/File/mCmUXgZLG1FNjjjwmbtPFr2LVJA112/inputImage-6060136.png"
},
"debugoutput": "",
"debugerror": "",
"starttime": "1734513809",
"endtime": "1734513813",
"elapsedseconds": "6.0000",
"status": "task_postprocess_end",
"cps": "0.000585000000",
"totalcost": "0.003510000000",
"guestid": null,
"projectid": "699",
"modelid": "598",
"description": "",
"basemodelid": "0",
"runtype": "model",
"modelfolderid": "",
"modelfileid": "",
"callbackurl": "",
"marketplaceid": null,
"createtime": "1734513807",
"canceltime": "0",
"assigntime": "1734513807",
"accepttime": "1734513807",
"preprocessstarttime": "1734513807",
"preprocessendtime": "1734513807",
"postprocessstarttime": "1734513813",
"postprocessendtime": "1734513814",
"pexit": "0",
"categories": "["tool","image-to-image","quick-showcase","compare-landscape"]",
"outputs": [
{
"id": "6bc392c93856dfce3a7d1b4261e15af3",
"name": "0.png",
"contenttype": "image/png",
"parentid": "6c1833f39da71e6175bf292b18779baf",
"uuid": "15bce51f-442f-4f44-a71d-13c6374a62bd",
"size": "202472",
"addedtime": "1734513812",
"modifiedtime": "1734513812",
"accesskey": "dFKlMApaSgMeHKsJyaDeKrefcHahUK",
"foldercount": "0",
"filecount": "0",
"ispublic": 0,
"expiretime": null,
"url": "https://cdn1.wiro.ai/6a6af820-c5050aee-40bd7b83-a2e186c6-7f61f7da-3894e49c-fc0eeb66-9b500fe2/0.png"
}
],
"size": "202472"
}
],
"result": true
}
Get Task Process Information and Results with Socket Connection
<script type="text/javascript">
window.addEventListener('load',function() {
//Get socketAccessToken from task run response
var SocketAccessToken = 'eDcCm5yyUfIvMFspTwww49OUfgXkQt';
WebSocketConnect(SocketAccessToken);
});
//Connect socket with connection id and register task socket token
async function WebSocketConnect(accessTokenFromAPI) {
if ("WebSocket" in window) {
var ws = new WebSocket("wss://socket.wiro.ai/v1");
ws.onopen = function() {
//Register task socket token which has been obtained from task run API response
ws.send('{"type": "task_info", "tasktoken": "' + accessTokenFromAPI + '"}');
};
ws.onmessage = function (evt) {
var msg = evt.data;
try {
var debugHtml = document.getElementById('debug');
debugHtml.innerHTML = debugHtml.innerHTML + "\n" + msg;
var msgJSON = JSON.parse(msg);
console.log('msgJSON: ', msgJSON);
if(msgJSON.type != undefined)
{
console.log('msgJSON.target: ',msgJSON.target);
switch(msgJSON.type) {
case 'task_queue':
console.log('Your task has been waiting in the queue.');
break;
case 'task_accept':
console.log('Your task has been accepted by the worker.');
break;
case 'task_preprocess_start':
console.log('Your task preprocess has been started.');
break;
case 'task_preprocess_end':
console.log('Your task preprocess has been ended.');
break;
case 'task_assign':
console.log('Your task has been assigned GPU and waiting in the queue.');
break;
case 'task_start':
console.log('Your task has been started.');
break;
case 'task_output':
console.log('Your task has been started and printing output log.');
console.log('Log: ', msgJSON.message);
break;
case 'task_error':
console.log('Your task has been started and printing error log.');
console.log('Log: ', msgJSON.message);
break;
case 'task_output_full':
console.log('Your task has been completed and printing full output log.');
break;
case 'task_error_full':
console.log('Your task has been completed and printing full error log.');
break;
case 'task_end':
console.log('Your task has been completed.');
break;
case 'task_postprocess_start':
console.log('Your task postprocess has been started.');
break;
case 'task_postprocess_end':
console.log('Your task postprocess has been completed.');
console.log('Outputs: ', msgJSON.message);
//output files will add ui
msgJSON.message.forEach(function(currentValue, index, arr){
console.log(currentValue);
var filesHtml = document.getElementById('files');
filesHtml.innerHTML = filesHtml.innerHTML + '<img src="' + currentValue.url + '" style="height:300px;">'
});
break;
}
}
} catch (e) {
console.log('e: ', e);
console.log('msg: ', msg);
}
};
ws.onclose = function() {
alert("Connection is closed...");
};
} else {
alert("WebSocket NOT supported by your Browser!");
}
}
</script>
Prepare UI Elements Inside Body Tag
<div id="files"></div>
<pre id="debug"></pre>
ThinkDiffusionXL (TDXL)
ThinkDiffusionXL is the result of our goal to build a go-to model capable of amazing photorealism that's also versatile enough to generate high-quality images across a variety of styles and subjects without needing to be a prompting genius.
You can find it preloaded on ThinkDiffusion.
Read more about the model, click here
Please leave a review if you're happy with it, this will encourage us to create more and improve on it.
The work
Data source: TDXL is trained on over 10,000 diverse images that span photorealism, digital art, anime, and more. The smallest resolution in our dataset is 1365x2048, but many images go up to resolutions as high as 4622x6753. In total, our dataset takes up 42GB.
Training: With 1.8 million steps, we’ve put in the work. For comparison, Juggernaut is at 600k steps and RealVisXL is at 348k steps
Hand-captioned images: Each image is carefully captioned by hand, enhancing the model's ability to generate accurate and high-quality results from minimal prompts.
NSFW capabilities: The model includes over 1,000 tastefully curated NSFW images.
Our thoughts
Detail and quality: Most XL models in the Realistic category suffer from poor detail, especially in the background and even in basic features like eyes, teeth, and skin. We believe TDXL outperforms in these areas due to its large, high-quality dataset. For comparison, Juggernaut has about half the image material, and RealVisXL has only 1,700 images. Ultimately, TDXL simply possesses much more "knowledge".
Less-Bias: We made sure to use an equal number of images for each style, gender, etc. Other models we tested over the past few months had some kind of bias, sometimes it was bias toward portrait shots, gender bias, certain ethnicities, etc. For instance, Juggernaut has a bias in the Close-Up area, and the Cinematic Light is quite dominant in that model. RealVisXL also has a bias towards Portrait shots. On the other hand, TDXL gives you what you want: Landscape, Midshot, Full Body, Close-Up, Portrait, Sideview, Backview, Action Shots, Cinematic...whatever you want without always being pushed in a certain direction due to a bias.
Versatile base: Because of its large balanced quality dataset, TDXL is versatile to serve as a base model for future trainings. You can create new finetunes in entirely different directions, add LoRAs to fill in missing concepts, or do additional trainings with more balanced quality data.
Tools
View All
