PeopleofSuperintelligence

Researcher

Dustin Podell

Dustin Podell is a generative AI researcher whose work spans latent diffusion, rectified flow and multimodal image generation. He moved from technical work in visual effects, media and software into self-directed machine-learning research, then led SDXL at Stability AI. His rectified-flow paper received ICML's 2024 Best Paper recognition; he co-founded Black Forest Labs, contributed to FLUX.1 and led the 2025 Kontext project. As of October 2026, he researches multimodal systems at Black Forest Labs and has coauthored Self-Flow, a 2026 paper on learning representations through flow matching.

Badges

Timeline

  1. 2015–2021

    Technical work in VFX

    From 2015 to 2021, he works across VFX, media production and software.

  2. 2021–2022

    Self-directed machine learning

    He pivots into self-directed machine-learning research in 2021 and teaches himself deep learning and generative modeling from scratch.

  3. 2022–2024

    Applied Model Lead at Stability AI

    From 2022 to 2024, he works at Stability AI and rises from ML engineer to Applied Model Lead, leading SDXL. The 2024 ICLR paper presents SDXL as a latent diffusion model for text-to-image synthesis.

  4. 2024

    An ICML Best Paper

    He coauthors the 2024 ICML paper “Scaling Rectified Flow Transformers for High-Resolution Image Synthesis,” which improves noise sampling for rectified-flow training and introduces a transformer-based architecture for high-resolution text-to-image synthesis. ICML lists the paper in its 2024 Best Paper group.

  5. 2024

    Co-founding Black Forest Labs

    He co-founds Black Forest Labs in 2024 and works there as a research scientist.

  6. 2024

    FLUX.1 core contributor

    He becomes a core contributor to FLUX.1 in 2024, a 12-billion-parameter multimodal diffusion transformer built with rectified flow matching.

  7. 2025

    Leading the Kontext project

    He leads the Kontext project in 2025, designing in-context image editing on a 12-billion-parameter FLUX transformer. His coauthored paper presents FLUX.1 Kontext as a flow-matching model that unifies image generation and editing.

  8. As of October 2026

    Multimodal research at BFL

    At Black Forest Labs, he works on representation learning and multimodal architectures spanning image, video, audio and text. In 2026, he coauthors Self-Flow, a self-supervised flow-matching framework for multimodal training.

Career

  1. Since 2024Black Forest LabsCo-founder, Research Scientist
  2. 2022–2024Stability AIML Engineer, then Applied Model Lead

From the biography.

  1. 11% of AI doctorate holders from 2010 to 2016 founded or led a company or lab by 10 years after graduationIncludes Black Forest Labs. We estimate how often AI doctorate holders founded or led a company or lab by 10 years after graduation, how waiting times compare between founders and top jobs, and which universities trained the most.
  2. Universities (31%) and startups and other companies (25%) employ the largest shares of 2020–2026 entrantsIncludes Black Forest Labs. Among 819 people whose first recorded role started in 2020–2026 and who have a known current organization, 60% work in commercial sectors (25% at startups and other companies, 23% at frontier labs and 13% at big tech, with 9 in two), and 31% work at universities, compared with 66% for earlier entrants.
  3. Google had the most people shaping AI every year from 2014 to 2025Our estimates of which organizations employed the most people shaping AI each year from 1955 to 2025, tracing the shift from university labs to companies.
  4. The United States employs an estimated 48% of people shaping AIWe estimate where the people shaping AI work today, how universities, companies and research institutes split across countries, and how country shares have changed since the 1960s.

Colleagues

People with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Dustin Podell yet. Send us a free-licensed photo.

  1. About — Dustin Podell dustinpodell.com. Checked 21 October 2026.
  2. SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis proceedings.iclr.cc. Checked 21 October 2026.
  3. ICML 2024 Awards icml.cc. Checked 21 October 2026.
  4. Scaling Rectified Flow Transformers for High-Resolution Image Synthesis proceedings.mlr.press. Checked 21 October 2026.
  5. FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space arxiv.org. Checked 21 October 2026.
  6. Self-Supervised Flow Matching for Scalable Multi-Modal Synthesis proceedings.mlr.press. Checked 21 October 2026.