Patrick EsserPatrick Esser
Black Forest Labs
Black Forest Labs 联合创始人 · Stable Diffusion 创造者Co-founder of Black Forest Labs · Stable Diffusion creator
visiondeep-learning
德国 AI 研究者，在慕尼黑大学（LMU）跟随 Bjorn Ommer 研究生成式图像建模。他是《Taming Transformers for High-Resolution Image Synthesis》（VQGAN）的第一作者，也是成为 Stable Diffusion 基础的潜在扩散模型论文的共同作者。在 Stability AI 主导 Stable Diffusion 3，提出多模态扩散 Transformer（MM-DiT）架构。2024 年与 Robin Rombach 共同创办 Black Forest Labs，发布了被广泛采用的 FLUX.1 家族。
German AI researcher who studied generative image modeling at LMU Munich under Bjorn Ommer. He was the lead author of 'Taming Transformers for High-Resolution Image Synthesis' (VQGAN) and a co-author of the latent diffusion model paper that became the basis of Stable Diffusion. At Stability AI he led Stable Diffusion 3,introducing the multimodal diffusion transformer (MM-DiT) architecture. In 2024 he co-founded Black Forest Labs with Robin Rombach to build frontier image and video generative models,releasing the widely adopted FLUX.1 family.
在关系图谱中查看 Patrick Esser →View Patrick Esser in the graph →
时间线Timeline
- 2021 Taming Transformers (VQGAN)
- 2024 Stable Diffusion 3 (MM-DiT)