microsoft/AesCode 8B and 32B

https://preview.redd.it/r2ledkyuntuh1.png?width=1684&format=png&auto=webp&s=9ed4518b2d0f20f44835ebbfac605581da186a57 AesCode generates information-rich visual artifacts such as slides, posters, and dashboards as HTML/CSS. The output remains structured, editable, and verifiable, but the task poses a distinct challenge: code models cannot see how layout, hierarchy, and color come together on the canvas. Image generators offer the opposite strength. They compose visually compelling pages but often misrender text, numbers, and logical relationships. AesCode uses an image generated from the same prompt as an aesthetic reference while following the prompt for the required content. Reference input alone does not solve the problem. Off-the-shelf vision-language models may copy hallucinated content or ignore the reference layout. AesCode separates semantic requirements from visual cues through graph-structured supervision and decoupled cross-modal rewards. AesCode-32B starts from Qwen3-VL-32B-Instruct and is trained with cold-start SFT followed by GDPO across seven reward channels. It is the larger released checkpoint and leads the aggregate benchmark results. https://huggingface.co/microsoft/AesCode-32B https://huggingface.co/bartowski/AesCode-32B-GGUF https://huggingface.co/microsoft/AesCode-8B https://huggingface.co/bartowski/AesCode-8B-GGUF https://preview.redd.it/7s9j5oooxtuh1.png?width=734&format=png&auto=webp&s=f4c1c8dc912b5fe6f882387da7bb679eae4d767d