← Back to all news
arXiv Machine Learning

Abra: Scaling Diffusion Image Training

The paper introduces Abra, a family of flow‑matching transformers used to systematically study scaling laws for text‑to‑image diffusion models across three orders of magnitude in compute. It finds that diffusion models scale predictably like language models but need far more data, with compute optimality occurring at roughly 200 image tokens per parameter—ten times the optimal ratio for large language models. The study also shows that diffusion models are robust to overtraining, that more data is preferable to larger models, and that scaling predictability extends to generative quality, optimal CFG settings, representation quality, and training curve shapes.

Related stories

arXiv AI
Sep 4

LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes

LLaDA-Image is a unified framework that couples a 6B Diffusion Transformer (DiT) trained from scratch with a frozen vision‑language module based on the LLaDA2.0‑Mini diffusion language model. The approach first builds a strong visual generative prior through image‑only pre‑training and mid‑training, then fine‑tunes with a 220M‑sample generation pipeline that includes 98 real images. The resulting model produces highly photorealistic images that accurately follow fine‑grained editing instructions, and a distilled version, LLaDA‑Image‑Turbo, enables fast inference in 2–4 sampling steps. On Qwen‑Image‑Bench, LLaDA‑Image sets new state‑of‑the‑art scores for open‑source models in both English and Chinese tracks, and the authors release weights, code, and detailed recipes to support further research.

By Chuyan Chen, Haoxing Chen, Kun Chen, Zhenglin Cheng, Long Cui, Ruishan Fang, Zhangxuan Gu, Zhicheng Huang, Zhenzhong Lan, Yuanting Lei, Haoquan Li, Jianguo Li, Rongchuan Li, Sidu Li, Tao Lin, Deyuan Liu, Jiacheng Liu, Lin Liu, Yuxuan Lou, Zhisheng Lu, Yuxin Ma, Shuheng Shen, Peng Sun, Chaoyang Wang, Hongjun Wang, Xiaomei Wang, Yongxin Wang, Chengzhang Wu, Hongru Wu, Jun Xie
llmsdiffusionmultimodalbenchmarks
More like this →
arXiv AI
Sep 16

Efficient Text-to-Image Generation: An Adaptive Step Schedule Controller for Diffusion Models

The paper introduces an adaptive step schedule controller for text‑to‑image diffusion models, allowing the number of denoising steps to vary based on the complexity of the input prompt. By mixing step schedules of different sizes and monitoring error discrepancies at each timestep, the method switches schedules to maintain image quality while reducing inference time. Experiments on COCO and DiffusionDB demonstrate that this approach achieves faster generation without sacrificing visual fidelity.

By Kuluhan Binici, Cihan Acar, Shivam Aggarwal, Siying Liu, Tulika Mitra
diffusion
More like this →
arXiv AI
Jun 29

ELF: Embedded Language Flows

arXiv:2605. 10938v2 Announce Type: replace-cross Abstract: Diffusion and flow-based models have become the de facto approaches for generating continuous data, e.

By Keya Hu, Linlu Qiu, Yiyang Lu, Hanhong Zhao, Tianhong Li, Yoon Kim, Jacob Andreas, Kaiming He
llmsragdiffusion
More like this →