TY  - JOUR
TI  - Scaling Rectified Flow Transformers for High-Resolution Image Synthesis
AU  - Esser, P.
AU  - Stability AI research team
PY  - 2024
DA  - 2024/03//
JO  - arXiv
AB  - Published in March 2024, this paper introduces the multimodal diffusion transformer (MMDiT) architecture and rectified flow training methodology that underpin Stable Diffusion 3. The authors subsequently founded Black Forest Labs and applied the same approach to the FLUX model family, making this the conceptual lineage anchor for the image generation architectures currently taught across image-generation curricula. The paper demonstrates predictable scaling behaviour across a large parameter range, a finding with direct implications for understanding the capabilities and limits of the models students use.
KW  - generative-ai
KW  - image-generation
KW  - production-practice
UR  - https://arxiv.org/abs/2403.03206
LA  - en
ER  -