Background
Blattmann was a PhD researcher with Robin Rombach in Björn Ommer's group at LMU Munich and a co-author on the Latent Diffusion / Stable Diffusion papers. He moved to Stability AI, worked on Stable Video Diffusion and SD3, and co-founded Black Forest Labs in 2024.
In Fortune's February 2026 profile he set out BFL's commercial logic: open-weight releases act as an adoption funnel, while production use by enterprises requires a paid commercial licence. He has said he wants BFL to become the standard for visual intelligence while staying structurally a small lab.
What they run now
Founding researcher across BFL's image and video stack, now inside FLUX 3's joint image/video/audio model. Publicly he owns the open-weights strategy: Schnell/Klein under permissive licences to drive adoption, Dev under non-commercial terms, Pro behind the API. On the a16z podcast he described using classical computer-vision techniques to filter the worst parts of video training data — a hint that BFL's video curation has historically been automated rather than human-judged.
What they buy
Inference. As a founder he approves rather than originates data spend, but his stated reliance on classical CV filters for video suggests an unmet need for human judgement on video quality — motion artifacts, temporal consistency, shot grammar — which is exactly what Luma's published Ray3 rubric covers and BFL's FLUX 3 post does not. Likely buyer of expert video preference pairs and video eval rubrics once FLUX 3 video exits 'preliminary'.
Career
- 2024 – presentCo-founder, Black Forest Labs
- 2022 – 2024Researcher (Stable Video Diffusion, SD3), Stability AI
- 2019 – 2022PhD researcher, LMU Munich (Ommer group) — Latent Diffusion co-author
- 2019–2022Ludwig Maximilian University of Munich, PhD-track research, computer vision
On the record
Frames open-weight releases as an adoption funnel that converts into paid enterprise licences. source
Says they used fairly classical computer-vision techniques to filter out the worst parts of video data. source
Wants BFL to become the standard for visual intelligence while keeping a small-lab structure. source