AI Model Catalogue

Generate 30-second music clips from text prompts or images with Lyria 3, Google's music generation model

Ultralytics YOLOE-L Real-Time Seeing Anything model with 26.2M parameters. Achieves 52.6 mAP50-95 on COCO dataset. Optimized for real-time inference with 6.2 ms speed on T4 GPU..

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

Fast video generation with text-to-video, image-to-video, and start-end-to-video modes. Up to 16 seconds at 1080p with synchronized audio.

The fastest diffusion language model with up to ~1000+ tps

Generate videos from images, with support for first-and-last-frame control, clip continuation, and audio synchronization using Alibaba's Wan 2.7 model

Kling 2.5 Turbo Pro: Unlock pro-level text-to-video and image-to-video creation with smooth motion, cinematic depth, and remarkable prompt adherence.

A unified foundation model for prompt-based segmentation in images and videos

Fast video generation with built-in draft mode for rapid creative iteration. Text-to-video, image-to-video, and audio-to-video in a single endpoint.

Generate and edit high-quality images with Alibaba's Wan 2.7 Pro with 4K output, thinking mode, text-to-image, multi-image editing, and image set generation

Seedream 4.5: Upgraded Bytedance image model with stronger spatial understanding and world knowledge

Metric3D v2 (TPAMI 2024): Monocular metric depth and surface normals from a single image. Predicts real-world depth in meters. Works indoor and outdoor.

Arise V2

A visual style focused on modern enterprise architecture—reflective blue glass skyscrapers captured from upward perspectives, emphasizing symmetry, scale, and a clean, premium corporate aesthetic.

When combining short AI videos encoded with different tools, codecs, and frame rates, this process standardizes them to ensure they are merged safely so that the final combined video remains intact.

This chatbot is designed to answer medical-related questions and has been fine-tuned on a large dataset. It is built on the Qwen 2.5 3B Instruct base model.

Professional inpainting and outpainting model with state-of-the-art performance. Edit or extend images with natural, seamless results.

This is a version of the MoE Gemma 4 26B optimised by Pruna AI.

Remove any object from video - fast.

Generate full-length songs with vocals, lyrics, and rich instrumentation from a text prompt

ByteDance's multimodal video generation model with native audio, multimodal reference inputs, and intelligent duration control.

Open-source Phi-3-mini-4k-instruct model from microsoft — available for download and self-hosting on Hugging Face.

Inspired by 90s streetwear, graffiti culture, and macabre aesthetics

Ultralytics YOLO11n object detection model with 2.6M parameters. Achieves 39.5 mAP50-95 on COCO dataset. Optimized for real-time inference with 1.55 ms speed on T4 GPU..

Generate videos from reference images or clips while preserving subject identity using Alibaba's Wan 2.7 reference-to-video model

Edit videos with natural language instructions using Alibaba's Wan 2.7 VideoEdit model

Reimagine any song in a different style — change voice, instruments, genre, and arrangement while keeping the original melody

Change the aspect ratio of any photo using AI (not cropping)

A sub 1 second 0.01$ multi-image editing model built for production use cases. For image generation, check out p-image here: https://replicate.com/prunaai/p-image