The Open Weights
LatestModelsLeaderboardsCompanies
Subscribe
The Open Weights

The daily record of open-source AI. New model releases, leaderboards, and what's coming next — written for people who ship.

Refreshed every 12 hours

Discover

  • Latest releases
  • New today
  • Trending models

Browse

  • All models
  • Companies
  • Categories
  • Leaderboards

About

  • About
  • Editorial policy
  • Hardware estimates
  • RSS feed
  • llms.txt
  • Newsletter

© 2026 The Open Weights. An independent publication.

PrivacyTermsSMSAggregated by Claude · curated by humans.
LatestBriaai3.0
BriaaiImage Editing

Bria releases RMBG-3.0 for background removal

The latest iteration of Bria's open background-removal model targets cleaner cutouts and finer alpha matting for image editing workflows.

Nov 10, 2026
NotableOther
RMBG-3.0

Bria has published RMBG-3.0, the newest version of its background-removal model, on Hugging Face. The model is built for isolating foreground subjects from images and producing alpha mattes — the soft transparency masks that make cutouts look natural around hair, edges, and semi-transparent regions.

Background removal is one of the most common tasks in practical image editing, from e-commerce product photography to design tooling and content pipelines. A dedicated model that outputs quality alpha mattes can slot directly into those workflows, reducing the manual masking work that otherwise falls to designers.

Licensing and access

RMBG-3.0 is distributed under a custom license rather than a standard permissive one, so teams planning commercial use should review Bria's terms on the model page before integrating it. Bria has historically paired its models with commercial licensing options aimed at enterprise users.

  • Primary task: background removal and alpha matting
  • Modality: image editing
  • Availability: Hugging Face model repository
  • License: custom (review before commercial use)

Why it matters: Reliable, openly available matting models remain relatively scarce compared with general image generators, and an updated RMBG release gives developers another well-maintained option for a workflow that shows up almost everywhere images are processed at scale.

Sources

  • briaai/RMBG-3.0

    Hugging Face

    Visit
OlderMeta AI debuts Muse Ember, a compact open modelMeta AI · Text / LLM · last weekNewerHaru-4B Brings Full-Duplex Speech to Six LanguagesHigurashi Ai · Any-to-Any · last week

Get the model

Hugging Face

Specs

Size16.3 GB
PrecisionBF16
ArchitectureBriaFibo2Pipeline
LicenseOTHER
Downloads152
Likes169

Can you run it?

Runs on a laptop — about 9.1 GB at FP8.

  • BF16 (as published)

    24 GB GPU (RTX 3090 / 4090) · 32 GB Mac

    17.3 GB
  • FP8

    12 GB GPU (RTX 3060 / 4070) · 16 GB Mac

    9.1 GB
Your machine
  • Covers the published checkpoint; text encoders and VAE loaded alongside may add a few GB (many runtimes offload them to CPU).

Based on Hugging Face weights metadata. Assumes an 8K context and ~1 GB runtime overhead; actual needs vary. How we estimate


Modalities

Image Editing

The Weekly Weights

Every open release that mattered, one email a week.

0 comments

No comments yet. Be the first to weigh in.

More from Briaai

All Briaai releases →
Fibo 2.0-dev
Briaai/Text → ImageRuns on a laptop

Bria's Fibo 2.0 Brings Structured Prompts to Open Image AI

The new text-to-image and editing model leans on structured prompts and multi-reference inputs for more controllable generation.

Oct 18, 2026

More in Image Editing

All Image Editing →
MiniMax H3 Image
MiniMax/Text → Image

MiniMax Releases H3 Image, Its Open Text-to-Image Model

The Chinese AI lab enters the open image-generation space with a single model that both creates and edits pictures from text.

Nov 3, 2026
FLUX.3 Image Klein
Black Forest Labs/Text → Image

Black Forest Labs ships FLUX.3 Image Klein for ComfyUI

The lab's latest open image model arrives packaged for ComfyUI with both generation and editing built in.

Oct 14, 2026
FLUX.3 Image Klein
Black Forest Labs/Text → ImageRuns on a laptop

Black Forest Labs ships FLUX.3 Image Klein

The latest open image model from the FLUX team handles both text-to-image generation and editing, and arrives ready to run in Diffusers.

Oct 13, 2026