Bria
Commercial safe AI visuals for enterprise scale production
Bria builds visual foundation models trained on ethically sourced and legally verified datasets, providing clarity and safety for commercial usage. The platform empowers brands and agencies to generate large volumes of product imagery and campaign assets without licensing uncertainty. Through Runware, Bria becomes a scalable and compliant provider for visual generation inside professional production pipelines.
Models by Bria
Bria FIBO Edit is an image editing model that applies text instructions and optional masks to modify existing images. It supports targeted alterations, generative fill, outpainting, and compositional edits while preserving original image attributes such as lighting and structure, enabling professional-grade inpainting and background modification workflows.
Api Only
Bria Video Eraser is a video editing model that removes objects from existing video using point-based selection, text instructions, or uploaded masks. It is designed to maintain temporal consistency across frames, prevent flickering and drift, and preserve the original audio track while modifying only the targeted visual regions.
Bria FIBO is a JSON native text to image model for precise visual generation. It converts short prompts or reference images into structured JSON schemas, then renders reproducible images. It supports iterative refinement, strict control over attributes, and enterprise safe licensed data.
Bria Video Increase Resolution upscales visual assets by 2x or 4x while preserving detail and transparency. Ideal for product footage and design workflows that need clean high resolution results without manual rework or artifacts.
Bria Image Increase Resolution is a specialized upscaling model for production workflows. It increases image resolution by 2x or 4x while preserving fine detail and transparency. Use it to upscale illustrations, product shots or UI assets without artifacts.
Bria Video Background Removal detects moving subjects in video and removes complex backgrounds in real time. It outputs clean alpha channels for precise keying. Ideal for virtual production, live streaming, post production pipelines, and automated video workflows.
Bria 3.2 is a compact text to image model built on fully licensed data. It delivers strong prompt alignment, high aesthetic quality, and reliable short text rendering. Ideal for enterprise workflows that need compliant image generation with predictable behavior and easy integration.
Bria Image Replace Background replaces image backgrounds from text prompts or reference images. It preserves the main subject with high fidelity. Ideal for automated product visuals, creative workflows, and bulk content pipelines.
Bria FIBO Lite is a lightweight, efficient text-to-image model designed for rapid image generation with structured prompt control and minimal inference steps. It uses a two-stage distillation approach to deliver high-quality visuals in fewer steps while preserving prompt adherence and visual coherence.
Bria RMBG v2.0 removes complex backgrounds and produces clean alpha mattes for product photos and portraits. It supports varied subjects and lighting. Ideal for ecommerce pipelines and design tools that need fast accurate subject isolation at scale.