Black Forest Labs open-sources 5.6B FLUX 3 Image Klein, +91 Elo with 38% fewer params
dl_weekly · x · 2026-10-26
Black Forest Labs released FLUX 3 Image Klein, a 5.6B-parameter open-weights model for text-to-image, image editing, and multi-reference generation (up to 10 reference images).
- Shares core capabilities with full FLUX 3 Image: native 4K generation, pixel-perfect editing, bounding-box control over element placement and edit regions
- Trained on joint image, video and audio signals for more physically grounded outputs
- Ranks first internally in text-to-image, multi-reference generation and editing, beating larger open models (Qwen-Image 2.1 at 7B, Krea 2 at 12.9B) and closed models Ideogram V4.5 and FLUX.2 [pro]
- +91 Elo in text-to-image and +70 in editing vs FLUX.2 [klein] 9B, with 38% fewer parameters
- Ships as base + step-distilled variants with FP8/INT8/NVFP4 builds (NVIDIA-supported) under the FLUX Kommunity License; small size targets local deployment and on-device editing
More from Models
- Ruff creator Charlie Marsh: frontier models find infinite bugs in any software — charliermarsh · 2026-10-26
- Dev testing one skill across Opus 5.5 and Sol 6.1 finds instruction following 'all over the map' — lucasmeijer · 2026-10-26
- supermemory unveils learner-1, claiming continual learning for any model — julianweisser · 2026-10-26
- Anthropic says Opus 5.5 cuts cost per task by ~40% vs Opus 5 — taufiqintech · 2026-10-26
- AI search APIs ranked: top 12 within 7 points, yet prices differ nearly 7x — FinanceYF5 · 2026-10-26
- OpenAI Dots coming to EU/EEA and UK in a few weeks, slides confirm — testingcatalog · 2026-10-26