MultimodalBlack Forest Labs
Black Forest Labs releases FLUX.3 Image Klein open weights
AIMade by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made
Black Forest Labs released the open weights of FLUX.3 Image Klein — one model handles making a picture from text, editing with several reference pictures, and layout control that places regions by writing coordinates into the prompt
Why it matters
It shipped two versions, a 16-step distilled one and a 50-step base one, together with FP8 and NVFP4 quantized weights and a DreamBooth LoRA training script. Only a speed figure was given — the distilled version makes a 1024×1024 picture in about 2 seconds on a single H100 — and no quality scores
Source — Primary sources first; secondary reports are labelled “Press”
Officialhuggingface.cohttps://huggingface.co/blog/flux-3Added in Week 43, 2026 · See that week
On the map — ⑦ Multimodal line
- Previous stopGoogle DeepMind
- This recordBlack Forest Labs releases FLUX.3 Image Klein open weights
- Next stopworld model Genie 4