AI Model Catalogue

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

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

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

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

Turn a text prompt into a complete, polished video with AI-generated script, avatar presenter, voiceover, visuals, and editing.

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

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

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

Private instance of stable-diffusion

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.

HeartMuLa: A Family of Open Sourced Music Foundation Models

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

Remove any object from video - fast.

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.

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

Arise V2

Generate videos guided by reference images using xAI's Grok Imagine Video model

Temporary publish target for bgogo deployment validation.

Extend videos with xAI's Grok Imagine Video model. Provide a source video and describe what happens next.

🔥 SeedVR2: one-step video & image restoration with 7B and Adjustable Resolution

Alpha-only video matting for 5-10 second white-background videos using BackgroundMattingV2 MobileNetV2 TorchScript.

Image to separate stems from a song, using demucs and spleeter

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.

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

This is a version of Qwen 3.5 27B optimised by Pruna AI.

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

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

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.