Datacte: Proteus v0.3

datacte/proteus-v0.3

Access Proteus v0.3 from Datacte using the Puter.js AI API.

Add to your app

Model Card

Proteus v0.3 is a Stable Diffusion XL fine-tune published on Hugging Face by dataautogpt3 (the same creator behind the Replicate handle datacte), continuing the same OpenDalle v1.1-derived Proteus line as v0.2.

It carries over v0.2's training set of about 220,000 GPT-V captioned, copyright-free stock images and 10,000 DPO-optimized image pairs, then adds roughly 200,000 additional anime images refined by a further 15,000 aesthetically selected images. The model card reports this improved lighting effects significantly, without degrading the existing photorealistic and stylistic range or causing catastrophic forgetting.

It keeps the facial detail and skin texture gains from v0.2 while extending anime and stylized output further.

It fits use cases that need stronger anime and stylized generation alongside photorealism, such as pipelines mixing multiple art styles.

Cost Per Image $0.001

per generation

Configuration second

resolution

Release Date N/A

Add Proteus v0.3 to your app

Use Proteus v0.3 in your app with the Puter.js AI API, no API keys or setup required.

// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';

puter.ai.txt2img("A serene mountain landscape at sunset", {
    model: "datacte/proteus-v0.3"
}).then(image => {
    document.body.appendChild(image);
});

<html>
<body>
    <script src="https://js.puter.com/v2/"></script>
    <script>
        puter.ai.txt2img("A serene mountain landscape at sunset", {
            model: "datacte/proteus-v0.3"
        }).then(image => {
            document.body.appendChild(image);
        });
    </script>
</body>
</html>

More AI Models From Datacte

Find other Datacte models →

Image

Proteus v0.2

Proteus v0.2 is a Stable Diffusion XL fine-tune published on Hugging Face by dataautogpt3 (the same creator behind the Replicate handle datacte), built as an enhancement over OpenDalle v1.1. It was trained on around 220,000 GPT-V captioned, copyright-free stock images (with some anime included), plus 10,000 curated AI-generated image pairs run through Direct Preference Optimization. Several LoRA models were trained separately and merged into the base network at targeted layers. Compared to Proteus v0.1, v0.2 improves prompt understanding, which the model card describes as surpassing Midjourney 6, and renders facial detail and skin texture more realistically. It keeps proficiency across surrealism, anime, and cartoon styles alongside photorealism. It suits developers who want one model spanning anime, cartoon, and photorealistic output without switching checkpoints.

Frequently Asked Questions

How do I use Proteus v0.3?

You can access Proteus v0.3 by Datacte through Puter.js AI API. Include the library in your web app or Node.js project and start making calls with just a few lines of JavaScript — no backend and no configuration required.

Is the Proteus v0.3 API free for developers?

Proteus v0.3 is free to integrate using the Puter.js AI API. With the User-Pays Model, you can add AI to your app for $0, since users cover their own AI usage through their Puter account.

What is the pricing for Proteus v0.3?

Proteus v0.3 costs $0.001 per image.

	Price
Per image	$0.001

Does it work with React / Vue / Vanilla JS / Node / etc.?

Yes — the Proteus v0.3 API works with any JavaScript framework, Node.js, or plain HTML through Puter.js. Just include the library and start building. See the documentation for more details.

Add Proteus v0.3 to your app for free

Developers can integrate Proteus v0.3 for free using the Puter.js AI API.
With the User-Pays Model, each user covers their own AI usage instead of the developer.

Get started How pricing works