Code-as-reasoning framework generates precise image layouts through executable code and iterative refinement.
Recent advancements in Unified Multimodal Models (UMMs) have significantly advanced text-to-image (T2I) generation, particularly through the integration of Chain-of-Thought (CoT) reasoning. However, existing CoT-based T2I methods largely rely on abstract natural-language planning, which lacks the precision required for complex spatial layouts, structured visual elements, and dense textual content. In this work, we propose CoCo (Code-as-CoT), a code-driven reasoning framework that represents the reasoning process as executable code, enabling explicit and verifiable intermediate planning for image generation. Given a text prompt, CoCo first generates executable code that specifies the structural layout of the scene, which is then executed in a sandboxed environment to render a deterministic draft image. The model subsequently refines this draft through fine-grained image editing to produce the final high-fidelity result. To support this training paradigm, we construct CoCo-10K, a curated dataset containing structured draft-final image pairs designed to teach both structured draft construction and corrective visual refinement. Empirical evaluations on StructT2IBench, OneIG-Bench, and LongText-Bench show that CoCo achieves improvements of +68.83%, +54.8%, and +41.23% over direct generation, while also outperforming other generation methods empowered by CoT. These results demonstrate that executable code is an effective and reliable reasoning paradigm for precise, controllable, and structured text-to-image generation. The code is available at: https://github.com/micky-li-hd/CoCo
CoCo uses executable code as chain-of-thought reasoning to generate precise structural layouts before refining images into final results.
Code-driven planning is deterministic and verifiable, solving limitations of abstract natural language descriptions for structured image generation.
CoCo achieves 68.83% improvement on StructT2IBench by combining code execution, draft rendering, and targeted image refinement.
Existing models required specific training to reliably execute the code-to-image pipeline without errors or failures.
The approach's effectiveness on highly abstract or artistic prompts beyond structured visual domains remains unclear.
Shenghai Yuan, Yuanyang Yin +4
We introduce Helios, the first 14B video generation model that runs at 19.5 FPS on a single NVIDIA H100 GPU and supports minute-scale generation while matching the quality of a strong baseline. We mak...
Yiying Yang, Wei Cheng +6
OmniLottie is a versatile framework that generates high quality vector animations from multi-modal instructions. For flexible motion and visual content control, we focus on Lottie, a light weight JSON...
Zengbin Wang, Xuecai Hu +4
Text-to-image (T2I) models have achieved remarkable success in generating high-fidelity images, but they often fail in handling complex spatial relationships, e.g., spatial perception, reasoning, or i...
Grigorii Alekseenko, Aleksandr Gordeev +8
Instruction-based image editing is among the fastest developing areas in generative AI. Over the past year, the field has reached a new level, with dozens of open-source models released alongside high...
Hojung Jung, Rodrigo Hormazabal +6
Molecular generation with diffusion models has emerged as a promising direction for AI-driven drug discovery and materials science. While graph diffusion models have been widely adopted due to the dis...
