Lucataco: OpenDalle V1.1
lucataco/open-dalle-v1.1
Access OpenDalle V1.1 from Lucataco using the Puter.js AI API.
Add to your appModel Card
OpenDalle V1.1 is a text-to-image model built on Stable Diffusion XL by dataautogpt3 (Alexander Izquierdo), using a proprietary merging and fine-tuning method rather than a single base checkpoint.
The model card describes its goal as prompt adherence and composition that sits between base SDXL and DALL-E 3, closer to DALL-E 3 quality while staying open enough to call through an API.
On Hugging Face it has drawn over 500 likes and is used in more than 100 community Spaces, one of the more widely adopted SDXL merges of its kind.
The original weights are released under a CC-BY-NC-ND-4.0 license, which restricts commercial redistribution of the checkpoint itself.
It suits illustration, concept art, and general creative image generation where prompt fidelity matters more than photorealism.
Cost Per Image $0.001
per generation
Configuration second
resolution
Release Date N/A
Add OpenDalle V1.1 to your app
Use OpenDalle V1.1 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: "lucataco/open-dalle-v1.1"
}).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: "lucataco/open-dalle-v1.1"
}).then(image => {
document.body.appendChild(image);
});
</script>
</body>
</html>
More AI Models From Lucataco
DreamShaper XL Turbo
DreamShaper XL Turbo is a text-to-image model by Lykon, a turbo-distilled version of DreamShaper rebuilt on Stable Diffusion XL rather than the SD 1.5 base used by the original DreamShaper. It uses SDXL-Turbo style distillation, so it reaches finished images in as few as 6 inference steps at a low guidance scale, compared to the 20-50 steps typical SDXL checkpoints need. Like its SD 1.5 predecessor, it aims for a painterly, non-CG look across photos, art, anime, and manga, rather than one narrow style. It's released under an OpenRAIL++ license and suits cases where fast turnaround matters, such as iterative concept art or high-throughput generation, without giving up the SDXL base's higher native resolution over SD 1.5.
ImageRealistic Vision V5.1
Realistic Vision V5.1 is a photorealistic Stable Diffusion 1.5 checkpoint by SG161222, published as SG161222/Realistic_Vision_V5.1_noVAE on Hugging Face. It's part of the long-running Realistic Vision series, one of the most downloaded photorealism checkpoints on Civitai, with entries in the series recording hundreds of thousands of downloads and well over a million combined views across versions. The model is tuned for lifelike skin texture, lighting, and detail, and is widely used for portraits and other human subjects, along with general photorealistic scenes. Because it's SD 1.5-based, it runs lighter and faster per step than SDXL-based checkpoints, though at SD 1.5's native resolution rather than SDXL's larger native output. It's a solid default for developers who want photorealistic portraits without calling a larger SDXL model.
ImageSSD-1B
SSD-1B is a distilled, smaller version of Stable Diffusion XL by Segmind, built by Yatharth Gupta and Vishnu Jaddipal using progressive knowledge distillation from several expert models, including SDXL, ZavyChromaXL, and JuggernautXL. At 1.3 billion parameters it's roughly 50% smaller than SDXL, and Segmind reports a 60% speedup in generation while aiming to keep close to SDXL's output quality. It was trained on datasets including Grit and Midjourney-sourced images and supports several output resolutions up to 1536x640. It's released under an Apache 2.0 license and works with common diffusion tooling such as Diffusers and ComfyUI. It suits cases where SDXL-level output is wanted but speed or resource use matters more than squeezing out the last bit of quality, such as high-volume or latency-sensitive image generation.
Frequently Asked Questions
You can access OpenDalle V1.1 by Lucataco 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.
OpenDalle V1.1 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.
| Price | |
|---|---|
| Per image | $0.001 |
Yes — the OpenDalle V1.1 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 OpenDalle V1.1 to your app for free
Developers can integrate OpenDalle V1.1 for free using the Puter.js AI API.
With the User-Pays Model, each user covers their own AI usage instead of the developer.