Tao Lin, Chaoyang Wang, Lin Liu, Jun Xie, Zhenzhong Lan, Hongjun Wang, Jiacheng Liu, Haoxing Chen, Zhangxuan Gu, Jianguo Li, Zhenglin Cheng, Yongxin Wang, and 18 more
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We introduce LLaDA-Image, a unified framework that pairs a 6B Diffusion Transformer (DiT) trained from scratch with a frozen vision-language understanding module built on the LLaDA2.0-Mini diffusion language model backbone. Instead of relying heavily on paired image-text data from the beginning, we first build a strong visual generative prior through image-only pre-training and mid-training. The generation pipeline comprises 220M samples, 98 of which are real images. For efficient and scalable optimization, we use parameter-free RMSNorm throughout the DiT together with the Muon optimizer. The resulting unified model produces highly photorealistic images while accurately following fine-grained editing instructions. We further distill LLaDA-Image into LLaDA-Image-Turbo, enabling fast inference in 2-4 sampling steps. On Qwen-Image-Bench, LLaDA-Image achieves overall scores of 53.53 and 53.38 on the English and Chinese tracks, respectively, setting a new state-of-the-art among open-source models on both tracks. To support further research on capable and efficient generative models, we release our model weights, training code, and detailed recipes.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2609.03796")
get_code_for_paper("2609.03796")
have("2609.03796")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2609.03796.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2609.03796)
Connect an agent — have() is free.