AI Model Catalogue

Z-Image Turbo is a super fast text-to-image model of 6B parameters developed by Tongyi-MAI.

FLUX LoRA trained on portraits by Thomas Lawrence, the leading British portraitist of the Regency era. Fluid brushwork, romantic lighting, aristocratic ease.

Segment floorplan images into walls, doors, windows, and kitchen zones using a deep learning model, then extract structured contours and center lines as JSON for downstream applications.

A 17 billion parameter model with 16 experts

Feed-forward neural network that directly infers all key 3D attributes of a scene.

DA3Metric-Large metric depth estimation (Apache 2.0). Returns 16-bit PNG depth map with metric metadata.

This is a version of GPT-OSS-120B that is optimised by Pruna AI.

Create realistic talking avatar videos from text with HeyGen's Avatar IV engine

Use trained LoRAs from the https://replicate.com/prunaai/p-image-trainer. Find or contribute LoRAs here https://huggingface.co/collections/PrunaAI/p-image-loras

FLUX LoRA trained on paintings by Jean-Marc Nattier. Ladies of the court depicted as goddesses, flowing blue drapery, soft pastel tones, Rococo elegance.

FLUX LoRA trained on portrait photographs by Nadar. Intimate psychologically revealing studio portraits, soft directional natural light, minimal props.

Highest-quality text-to-speech with <200ms latency, emotion control, and 15-language support

Model Card: Moreiraj Overview Moreiraj is a high-performance AI model fine-tuned for generating realistic and artistic visual content. Built on advanced transformer architecture, this model specializes in character-consistent generation and style

Create your own Realistic Voice Cloning (RVC v2) dataset using a YouTube link

Seedream 5.0 lite: image generation with built-in reasoning, example-based editing, and deep domain knowledge

Google's most intelligent model, with improved reasoning and a new medium thinking level

Generate detailed SVG vector graphics from text prompts. Recraft V4 Pro's design taste with more geometric detail and finer paths — clean layers, editable output, and scalable to any size.

OpenAI's most capable frontier model for complex professional work, coding, and multi-step reasoning.

Updated Qwen3 model for instruction following

Bria Expand expands images beyond their borders in high quality. Resizing the image by generating new pixels to expand to the desired aspect ratio. Trained exclusively on licensed data for safe and risk-free commercial use

DeepSeek-V3-0324 is the leading non-reasoning model, a milestone for open source

Nova Anime XL (Illustrious) v14.0

FLUX LoRA trained on paintings by Édouard Manet. Loose spontaneous brushwork, flat areas of tone, modern Parisian subjects.

League of Legends splash art generator

FLUX LoRA trained on portraits by François Clouet. Precise detailed rendering of rich costume and jewels, flat even lighting, Valois court style.

FLUX LoRA trained on Fayum mummy portraits. Striking directness, dark engaging eyes, gilded details, luminous encaustic wax technique.

90's Photographs in the style of Bjorks promo material

Remove backgrounds with real alpha transparency using Nano Banana 2. Triangulation matting produces clean edges, proper semi-transparency, and accurate colors — superior to traditional background removal. Optionally specify what to isolate.

Ideal for rapid ideation and mobile workflows. Perfect for creators who need instant feedback, real-time previews, or high-throughput content.

High-fidelity video generation with portrait support, audio-to-video, retake, and extend. Text, image, and audio-driven creation up to 4K at 50 FPS.

FLUX LoRA trained on dramatic painted sky imagery — stormy heavens, golden hour light, baroque clouds.

Nova Anime XL (Illustrious) v17.0

Nano Banana 2 with alpha transparency. Generates images with real RGBA transparency using triangulation matting — clean edges, proper semi-transparency, and accurate colors. Powered by Google Gemini 3.1 Flash Image.

Feed-forward neural network that directly infers all key 3D attributes of a scene.