MangaFlow: An End-to-End Agentic Framework for Controllable Story to Manga Generation

• URL: http://arxiv.org/abs/2605.28173v1
• Date: Wed, 27 May 2026 08:54:12 GMT
• Title: MangaFlow: An End-to-End Agentic Framework for Controllable Story to Manga Generation
• Abstract summary: MangaFlow is a framework for controllable long-form manga generation.<n>It decomposes manga creation into planning, grounding, layout construction, reference-conditioned rendering, composition, and text placement.
• Score: 22.40264045909082
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: End-to-end manga generation is a structured visual storytelling task that requires story decomposition, recurring character and scene grounding, page layout design, panel rendering, page composition, and lettering. However, existing generative models often perform direct page synthesis, entangling these factors in a single visual output and limiting precise control over layout geometry, visual references, and cross-panel consistency. To address these limitations, we propose MangaFlow, an agentic framework for controllable long-form manga generation that decomposes manga creation into planning, grounding, layout construction, reference-conditioned rendering, composition, and text placement. By treating layout and visual references as explicit intermediate variables, MangaFlow enables both simple text-to-manga generation and more precise user-controlled manga creation. This design exposes layout, visual assets, and lettering as editable intermediate controls for refining panel geometry, references, and text placement. To support long-form consistency, MangaFlow introduces a story section memory that links section descriptions with corresponding character, scene, and object references for reuse across panels. We further present a meta-benchmark for evaluating layout controllability, visual consistency, and generation quality. Experiments show that MangaFlow improves layout adherence and cross-panel consistency over direct generation baselines while supporting flexible human control.

Related papers

• SpatialGuard: Harness-Guided Verifiable Spatial Reasoning for Text-to-Image Generation [47.693838969607704]
  Complex 3D spatial text to image generation requires models to convert natural language into stable visual geometry.<n>This paper presents SpatialGuard, a structured layout-guided framework for complex 3D spatial text-to-image generation.
  arXiv  Detail & Related papers  (2026-09-01T17:47:00Z)
• CreatiParser: Generative Image Parsing of Raster Graphic Designs into Editable Layers [48.779823303618734]
  We propose a hybrid generative framework for rendering graphic design parsing.<n>It decomposes a design image into editable text, background, and sticker layers.<n>Text regions are parsed using a vision-language model into a text design protocol.<n>Background sticker layers are generated using a multi-branch diffusion architecture.
  arXiv  Detail & Related papers  (2026-04-21T16:20:19Z)
• FlowScene: Style-Consistent Indoor Scene Generation with Multimodal Graph Rectified Flow [52.01563659850181]
  FlowScene is a graph-based scene generative model that collaboratively generates scene layouts, object shapes, and object textures.<n>At its core lies a tight-coupled rectified flow model that exchanges object information during generation, enabling collaborative reasoning across the graph.<n>Extensive experiments show that FlowScene outperforms both language-conditioned and graph-conditioned baselines in terms of generation realism, style consistency, and alignment with human preferences.
  arXiv  Detail & Related papers  (2026-03-20T03:15:42Z)
• CalliMaster: Mastering Page-level Chinese Calligraphy via Layout-guided Spatial Planning [37.872480365351485]
  Page-level calligraphy synthesis requires balancing glyph precision with layout composition.<n>We present textbfCalliMaster, a unified framework for controllable generation and editing.
  arXiv  Detail & Related papers  (2026-03-12T22:01:19Z)
• Manga Generation via Layout-controllable Diffusion [21.080054070512023]
  This paper presents the manga generation task and constructs the Manga109Story dataset for studying manga generation solely from plain text.<n>We propose MangaDiffusion to facilitate the intra-panel and inter-panel information interaction during the manga generation process.
  arXiv  Detail & Related papers  (2024-12-26T17:52:19Z)
• How Panel Layouts Define Manga: Insights from Visual Ablation Experiments [24.408092528259424]
  This paper aims to analyze the visual characteristics of manga works, with a particular focus on panel layout features.<n>As a research method, we used facing page images of manga as input to train a deep learning model for predicting manga titles.<n>Specifically, we conducted ablation studies by limiting page image information to panel frames to analyze the characteristics of panel layouts.
  arXiv  Detail & Related papers  (2024-12-26T09:53:37Z)
• DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation [32.24143157812589]
  textbfDiffSensei is a framework specifically designed for generating manga with dynamic multi-character control.<n>DiffSensei integrates a diffusion-based image generator with a multimodal large language model (MLLM) that acts as a text-compatible identity adapter.<n>Our approach employs masked cross-attention to seamlessly incorporate character features, enabling precise layout control without direct pixel transfer.
  arXiv  Detail & Related papers  (2024-12-10T15:24:12Z)
• The Manga Whisperer: Automatically Generating Transcriptions for Comics [55.544015596503726]
  We present a unified model, Magi, that is able to detect panels, text boxes and character boxes. We propose a novel approach that is able to sort the detected text boxes in their reading order and generate a dialogue transcript.
  arXiv  Detail & Related papers  (2024-01-18T18:59:09Z)
• Deep Geometrized Cartoon Line Inbetweening [98.35956631655357]
  Inbetweening involves generating intermediate frames between two black-and-white line drawings. Existing frame methods that rely on matching and warping whole images are unsuitable for line inbetweening. We propose AnimeInbet, which geometrizes geometric line drawings into endpoints and reframes the inbetweening task as a graph fusion problem. Our method can effectively capture the sparsity and unique structure of line drawings while preserving the details during inbetweening.
  arXiv  Detail & Related papers  (2023-09-28T17:50:05Z)
• PosterLayout: A New Benchmark and Approach for Content-aware Visual-Textual Presentation Layout [62.12447593298437]
  Content-aware visual-textual presentation layout aims at arranging spatial space on the given canvas for pre-defined elements. We propose design sequence formation (DSF) that reorganizes elements in layouts to imitate the design processes of human designers. A novel CNN-LSTM-based conditional generative adversarial network (GAN) is presented to generate proper layouts.
  arXiv  Detail & Related papers  (2023-03-28T12:48:36Z)
• MARVEL: Raster Manga Vectorization via Primitive-wise Deep Reinforcement Learning [29.14983719525674]
  Manga is a fashionable Japanese-style comic form that is composed of black-and-white strokes and is generally displayed as images on digital devices. We propose MARVEL, a primitive-wise approach for vectorizing mangas by Deep Reinforcement Learning (DRL) Unlike previous learning-based methods which predict vector parameters for an entire image, MARVEL introduces a new perspective that regards an entire manga as a collection of basic primitivestextemdash stroke lines.
  arXiv  Detail & Related papers  (2021-10-10T15:52:38Z)

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.