GenClaw: Code-Driven Agentic Image Generation

• URL: http://arxiv.org/abs/2605.30248v2
• Date: Fri, 29 May 2026 03:57:25 GMT
• Title: GenClaw: Code-Driven Agentic Image Generation
• Abstract summary: We propose GenClaw, a code-driven image generation paradigm that empowers the agent to create like a human artist.<n>Specifically, the agent first constructs the conceptual knowledge and context through search and reasoning.<n>It then utilizes code (e.g., SVG, HTML, ThreeJS) to render executable visual sketches.
• Score: 40.94073553092702
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Image generation models have evolved from text-conditioned pixel synthesis toward multimodal agents endowed with visual comprehension and tool invocation capabilities. Yet, existing agents remain at the mercy of underlying black-box image models. Their workflow is trapped in a repetitive cycle of prompt rewriting for generation refinement, leaving them with no mechanism to directly manipulate the canvas. In essence, the potential of LLMs to serve as a genuine "brush" for precise visual construction remains largely untapped. In this paper, we propose GenClaw, a code-driven agentic image generation paradigm that empowers the agent to create like a human artist: first conceptualizing, then sketching, and finally coloring. Specifically, the agent first constructs the conceptual knowledge and context through search and reasoning. It then utilizes code (e.g., SVG, HTML, ThreeJS) to render executable visual sketches. Finally, it employs an image generation model to supplement textures, materials, and photorealism. In this workflow, code serves as a controllable intermediate canvas bridging linguistic reasoning and pixel synthesis, seamlessly integrating programmatic logic with the visual expressiveness of generative models. By transforming image generation from a black-box paradigm into a staged process akin to authentic human creation, GenClaw offers a step toward for highly controllable and interpretable visual generation systems.

Related papers

• Editable Visual Design [32.993324966532235]
  We propose Editable Visual Design, a new paradigm driven by a Coding Agent.<n>We designate the creative brain'' for requirement comprehension, task planning, and aesthetic judgment.<n>Agent Design Replay faithfully reproduces the creative and reasoning trajectory akin to that of professional human designers.
  arXiv  Detail & Related papers  (2026-09-03T16:10:12Z)
• World Narrative Model for Highly Controllable Video Generation: A Paradigm Shift from Pixel Sampling to Physical World Orchestration [49.72473930573157]
  We introduce the World Narrative Model (WNM), a paradigm that decouples what to render -- the structured physical narrative -- from how to render.<n>WNM replaces end-to-end black-box sampling with orchestrated $4D$ pre-visualization for media generation.<n>Our human-AI platform supports automatic world generation and pre-visualization aligned with professional filmmaking pipelines.
  arXiv  Detail & Related papers  (2026-06-30T16:52:53Z)
• Unified Thinker: A General Reasoning Modular Core for Image Generation [57.665309753609144]
  We propose Unified Thinker, a task-agnostic reasoning architecture for general image generation.<n>Unified Thinker decouples a dedicated Thinker from the image Generator, enabling modular upgrades of reasoning without retraining the entire generative model.<n>Experiments on text-to-image generation and image editing show that Unified Thinker substantially improves image reasoning and generation quality.
  arXiv  Detail & Related papers  (2026-01-06T15:59:33Z)
• RealGen: Photorealistic Text-to-Image Generation via Detector-Guided Rewards [53.25632969696776]
  We propose RealGen, a text-to-image framework for photorealistic image generation.<n>Inspired by adversarial generation, RealGen introduces a "Detector Reward" mechanism, which quantifies artifacts and assesses realism.<n>Experiments demonstrate that RealGen significantly outperforms general models like GPT-Image-1 and Qwen-Image, as well as specialized photorealistic models like FLUX-Krea.
  arXiv  Detail & Related papers  (2025-11-29T12:52:26Z)
• Janus-Pro-R1: Advancing Collaborative Visual Comprehension and Generation via Reinforcement Learning [92.57052246970254]
  We propose to enable the collaborative co-evolution of visual comprehension and generation.<n>We introduce a two-stage training approach: supervised fine-tuning teaches the MLLM with the foundational ability to generate genuine CoT.<n>We unlock the Aha moment in visual generation, advancing MLLMs from text-to-image tasks to unified image generation.
  arXiv  Detail & Related papers  (2025-06-02T09:39:28Z)
• Iterative Flow Matching -- Path Correction and Gradual Refinement for Enhanced Generative Modeling [6.343872515377999]
  We explain and demonstrate why flow matching can generate hallucinations, and propose an iterative process to improve the generation process.<n>Our iterative process can be integrated into virtually $textitany$ generative modeling technique, thereby enhancing the performance and robustness of synthesis image systems.
  arXiv  Detail & Related papers  (2025-02-23T05:08:06Z)
• Alfie: Democratising RGBA Image Generation With No $$$ [33.334956022229846]
  We propose a fully-automated approach for obtaining RGBA illustrations by modifying the inference-time behavior of a pre-trained Diffusion Transformer model. We force the generation of entire subjects without sharp croppings, whose background is easily removed for seamless integration into design projects or artistic scenes.
  arXiv  Detail & Related papers  (2024-08-27T07:13:44Z)
• Interpreting Generative Adversarial Networks for Interactive Image Generation [36.539339220652046]
  This chapter will give a summary of recent works on interpreting deep generative models. We will see how the human-understandable concepts that emerge in the learned representation can be identified and used for interactive image generation and editing.
  arXiv  Detail & Related papers  (2021-08-10T19:42:20Z)
• Unsupervised Novel View Synthesis from a Single Image [47.37120753568042]
  Novel view synthesis from a single image aims at generating novel views from a single input image of an object. This work aims at relaxing this assumption enabling training of conditional generative model for novel view synthesis in a completely unsupervised manner.
  arXiv  Detail & Related papers  (2021-02-05T16:56:04Z)
• SMPLpix: Neural Avatars from 3D Human Models [56.85115800735619]
  We bridge the gap between classic rendering and the latest generative networks operating in pixel space. We train a network that directly converts a sparse set of 3D mesh vertices into photorealistic images. We show the advantage over conventional differentiables both in terms of the level of photorealism and rendering efficiency.
  arXiv  Detail & Related papers  (2020-08-16T10:22:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.