Black Forest Labs releases 5.6B open-weights FLUX 3 Image Klein that tops larger models
lmoroney · x · 2026-10-16
Black Forest Labs released FLUX 3 Image Klein, a 5.6B-parameter open-weights image model that runs on consumer GPUs under the FLUX Kommunity License.
- All-in-one: one checkpoint handles text-to-image, instruction-based editing, and multi-reference generation with up to 10 reference images, keeping FLUX 3 Image features like native 4K generation, pixel-perfect editing, and bounding-box placement/edit control.
- Multimodal training: combines image (spatial detail), video (motion/physics), and audio (events/interactions) signals for more grounded outputs.
- Benchmarks: ranks first among open-weights models in text-to-image, multi-reference generation, and image editing, also beating closed models Ideogram V4.5 and FLUX.2 [pro]; vs 9B FLUX.2 [klein] it has 38% fewer parameters while gaining 91 Elo in text-to-image and 70 in editing.
- Shipments: base model for fine-tuning, a step-distilled low-latency variant, and FP8/INT8/NVFP4 builds built with NVIDIA support.
More from Models
- PhoneLLM Mini (30B) and Max (120B) target sub-100ms voice AI latency on Workers AI — ritakozlov · 2026-10-16
- Yacine on LLMs: "I'm sick of how stupid these language models are. Accelerate!" — yacineMTB · 2026-10-16
- Gemini 4 Argon rolls out in Antigravity for paid AI Pro users with a separate weekly quota — GeminiApp · 2026-10-16
- GPT-4o API dies January 14 as OpenAI refuses to release weights, pushing users to Qwen — mimi10v3 · 2026-10-16
- Opus 5.5 value may end the habit of using the top model for everything — adonis_singh · 2026-10-16
- Musk says Grok Bot is growing faster than anything he's seen, with no free tier — elonmusk · 2026-10-16