AI Model Catalogue

Generate videos using xAI's Grok Imagine Video model

Recraft's latest image generation model at ~2048px resolution. Same design taste and prompt accuracy as V4, with higher resolution for print-ready and large-scale work.

FLUX LoRA trained on French First Empire paintings. Napoleonic state portraiture — generals in gleaming uniforms, imperial ceremonies, neoclassical grandeur.

Kling Video 3.0 Omni: Unified multimodal video generation with reference images, video editing, native audio, and multi-shot control

A reasoning model trained with reinforcement learning, on par with OpenAI o1

Creates Pokemon trainers

Grok 4 is xAI’s most advanced reasoning model. Excels at logical thinking and in-depth analysis. Ideal for insightful discussions and complex problem-solving.

Translate videos into over 150 languages

Google's fast image generation model with conversational editing, multi-image fusion, and character consistency

Compact Powerhouse for Vector Embeddings

FLUX LoRA trained on paintings by Diego Velázquez. Psychological penetration, muted silver-grey palettes, loose painterly surfaces, Spanish Baroque realism.

Designed to make images sharper and cleaner, Crisp Upscale increases overall quality, making visuals suitable for web use or print-ready materials.

FLUX LoRA trained on paintings by John Singer Sargent. Dazzling bravura brushwork, shimmering whites, vivid capturing of personality and social status.

A 17 billion parameter model with 128 experts

Serve QwenASR speech recognition and alignment.

A next-generation image generation and editing model from Alibaba's Qwen team. Supports text-to-image and image editing with strong text rendering, especially for Chinese.

The pro version of Qwen Image 2 from Alibaba's Qwen team. Enhanced text rendering, realism, and semantic adherence for high-quality image generation and editing.

Convert raster images to high-quality SVG format with precision and clean vector paths, perfect for logos, icons, and scalable graphics.

20b open-weight language model from OpenAI

FLUX LoRA trained on paintings by Titian. Luminous warm flesh tones, rich crimson and gold drapery, monumental Venetian Renaissance style.

Private instance of stable-diffusion

FLUX LoRA trained on portraits by Anthony van Dyck. Elegant elongated figures in satin and lace, subtly melancholic expressions, Baroque court style.

A feed-forward neural network that offers a novel approach to visual geometry reconstruction.

120b open-weight language model from OpenAI

FLUX LoRA trained on ancient Roman paintings — Pompeii frescoes, encaustic panel portraits. Earthy terracotta tones, flat modelling, direct frontal gazes.

HeartMuLa: A Family of Open Sourced Music Foundation Models

FLUX LoRA trained on paintings by J.-A.-D. Ingres. Porcelain-smooth surfaces, exquisitely elongated forms, precise linear contours, neoclassical mastery.

FLUX LoRA trained on paintings by Thomas Gainsborough. Feathery delicate brushwork, luminous silks, pastoral English backgrounds.

FLUX LoRA trained on ancient Mediterranean paintings — Greek vase paintings, Minoan frescoes, Egyptian tomb murals. Flat schematic figuration, bold outlines, ceremonial character.

Advanced 20B open-weight reasoning models to customize for any use case and run anywhere.

Granite-4.0-H-Small is a 32B parameter long-context instruct model finetuned from Granite-4.0-H-Small-Base using a combination of open source instruction datasets with permissive license and internally collected synthetic datasets.