AI Model Catalogue

Updated Qwen3 model for instruction following

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

A 17 billion parameter model with 16 experts

A 17 billion parameter model with 128 experts

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

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

A sub 1 second text-to-image model built for production use cases.

Latest hybrid thinking model from Deepseek

Google's state of the art image generation and editing model 🍌🍌

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

Delivers high visual fidelity with fast turnaround. Great for daily content creation, marketing teams, and iterative creative workflows.

I don't have reliable information about a specific AI model called "painting" by serayai to provide you with an accurate description. I'd recommend checking the model's official documentation or repository for an authoritative description.

I don't have access to specific information about a model called "vintage" by benmorton74-hash in my training data, so I cannot provide an accurate and factual description of its capabilities and intended users.

I don't have any information about an AI model called "windows-trees" by tarasotherstuff-arch in my training data, so I cannot provide a factually accurate description of what it does or who should use it.

I don't have reliable information about a specific AI model called "moon_tvey" by esadorleans in my training data, so I cannot write a factually accurate description of it. To provide you with an accurate sentence, I would need verified information about this model's capabilities and intended users.

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

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.

I don't have reliable information about a specific AI model called "studioisatwo" by hebhar in my training data. I cannot provide a factual description without verified information about this model's capabilities and intended users. I'd recommend checking the model's official documentation or repository for an accurate description.

ERNIE-Image is an open text-to-image generation model developed by the ERNIE-Image team at Baidu

Lo-fi hip-hop music generation with ACE-Step 1.5 + LoRA

This model generates minimalist logo marks and brand symbols, making it ideal for designers, startups, and businesses seeking quick visual identity concepts without extensive design experience.

Generate videos with audio from text prompts using Alibaba's Wan 2.7 model. 1080p, up to 15 seconds, with audio synchronization.

New and improved version of Veo 3, with higher-fidelity video, context-aware audio, reference image and last frame support

This model specializes in generating vintage poster artwork with retro aesthetic styles, making it ideal for designers, artists, and content creators seeking to produce nostalgic visual designs for print, digital media, or creative projects.

The smartest diffusion language model up to ~800+ tps

FireRed-Image-Edit 1.1 is a general-purpose image editing model that delivers high-fidelity and consistent editing across a wide range of scenarios.

I don't have reliable information about a specific AI model called "zozu" by fultonyard in my training data. I cannot provide a factually accurate description without verifying details about this model's capabilities and intended users.

This is a version of the MoE Qwen 3.5 35B optimised by Pruna AI.

Ultra-fast, cost-efficient text-to-speech with ~120ms latency and 15-language support

Get embeddings for image using siglip-large-patch16-384

High-quality image generation and editing with support for eight reference images

Temporary publish target for bgogo deployment validation.