Released Flux 3, a multimodal model generating 20-second video with native audio.

ByteDance Seed releases SpectraReward, a training-free reward model for text-to-image generation.

Released iLLaDA, an 8B diffusion language model trained on 12T tokens.

ByteDance purchased tens of thousands of Iluvatar CoreX AI processors for cloud infrastructure

Building custom data-center CPUs for AI inference, targeting TikTok-scale agent workloads

ByteDance open-sources BAGEL 7B multimodal model under Apache 2.0 license

Released GenLIP, a generative pretraining framework for Vision Transformers.

Released FLUX.2 klein AI image generation model on Hugging Face