BRIA drops RMBG 3.0, a 4-step background remover that tops 234 hard-image benchmark
linoy_tsaban · x · 2026-11-17
BRIA AI released RMBG 3.0 on Hugging Face, the third generation of its background-removal models and the first built on a generative foundation: Fibo 2.0, fine-tuned and distilled to produce a clean soft alpha matte in just 4 steps (6 s per image), with diffusers and ComfyUI support.
- In a head-to-head benchmark on 234 hard full-resolution images against Photoroom, remove.bg (Canva), Ideogram, BiRefNet and RMBG-2.0, it averaged rank 1.51 and was best or tied-best on 185 images (79%).
- Pairwise preference: 55.1% vs Photoroom, 59.4% vs remove.bg, 60.9% vs RMBG-2.0, 65.6% vs Ideogram, 75.9% vs BiRefNet.
- Leads 7 of 12 hard categories and places top-2 in 10, including motion blur, multiple subjects, holes & mesh, shadows & reflections, hair & fur, transparent objects and reflective surfaces.
- Built for e-commerce: average rank 1.15 on 48 real store product shots (Photoroom 1.83, remove.bg 1.94), preserving product text, logos and badges.
- Trained exclusively on licensed data.
Related event: Bria Open-Sources RMBG 3.0 Background Removal Model(2 posts)→
More from Multimodal
- Chromostereopsis prompt trick makes flat AI images pop with fake depth — LudovicCreator · 2026-11-17
- CLAP2 Audio Segmentation Demo Built on Last Week's Model Release — wightmanr · 2026-11-17
- AI-Generated Robert Pattinson as James Bond Images Go Viral for Film-Grade Realism — egeberkina · 2026-11-17
- Higgsfield Launches Short Drama Studio: One Script, a Full Season — CurieuxExplorer · 2026-11-17
- AI acting tests with MiniMax H3: one character, six subtle emotions — Acrobatic-Example315 · 2026-11-17
- Cohere launches Compass Video Intelligence, tops video retrieval benchmarks at 0.69 nDCG@10 — cohere · 2026-11-17