PosterText: Towards Unified Visual Text Generation and Editing for E-commerce Poster

• URL: http://arxiv.org/abs/2608.16289v3
• Date: Thu, 20 Aug 2026 10:14:14 GMT
• Title: PosterText: Towards Unified Visual Text Generation and Editing for E-commerce Poster
• Abstract summary: Automated e-commerce poster design requires both high-quality poster generation and flexible editing of existing designs.<n>To enable unified generation and editing of e-commerce posters, we introduce Text Patch Generation and Editing.<n>We propose PosterText, a unified model trained with a four-stage curriculum, including text rendering pretraining, instruction-following training, reinforcement learning for preference alignment, and spatial guidance self-distillation.
• Score: 24.777892751309384
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Automated e-commerce poster design requires both high-quality poster generation and flexible editing of existing designs. However, most existing methods either target end-to-end poster generation or follow multi-stage design pipelines, with limited capability for flexible and precise editing of existing posters. To enable unified generation and editing of e-commerce posters, we introduce Text Patch Generation and Editing, a unified task formulation that treats text patches as atomic units and covers four operations: poster generation, patch addition, patch deletion, and patch modification, with optional reference-guided style control. Based on this, we propose PosterText, a unified model trained with a four-stage curriculum, including text rendering pretraining, instruction-following training, reinforcement learning for preference alignment, and spatial guidance self-distillation for execution refinement. We further construct a large-scale dataset with patch-level annotations and a comprehensive benchmark for evaluation. Extensive experiments demonstrate that PosterText achieves competitive performance against existing generation and editing approaches, validating the effectiveness of the proposed framework.

Related papers

• simpleposter: a simple baseline for product poster generation [17.46071085989295]
  We present SimplePoster, a simple yet effective inpainting-based framework that achieves faithful subject preservation and accurate, position-controllable text rendering without external controllers.<n> Experiments show that SimplePoster achieves a $98.7%$ subject preservation rate, compared to $55.2%$ for SeedEdit 3.0 and $85.3%$ for PosterMaker, while also improving text rendering accuracy.
  arXiv  Detail & Related papers  (2026-05-09T08:12:55Z)
• 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)
• WeEdit: A Dataset, Benchmark and Glyph-Guided Framework for Text-centric Image Editing [103.68419705566146]
  We present WeEdit, a systematic solution encompassing a scalable data construction pipeline, two benchmarks, and a tailored two-stage training strategy.<n>Specifically, we propose a novel HTML-based automatic editing pipeline, which generates 330K training pairs covering diverse editing operations and 15 languages.<n>On the algorithmic side, we employ glyph-guided supervised fine-tuning to inject explicit spatial and content priors, followed by a multi-objective reinforcement learning stage to align generation with instruction adherence, text clarity, and background preservation.
  arXiv  Detail & Related papers  (2026-03-12T06:25:09Z)
• InnoAds-Composer: Efficient Condition Composition for E-Commerce Poster Generation [27.024838488122104]
  We propose a single-stage framework that enables efficient tri-conditional control tokens over subject, glyph, and style.<n>InnoAds-Composer significantly outperforms existing product poster methods without obviously increasing inference latency.
  arXiv  Detail & Related papers  (2026-03-06T04:36:33Z)
• PosterVerse: A Full-Workflow Framework for Commercial-Grade Poster Generation with HTML-Based Scalable Typography [44.93712206658515]
  PosterVerse is a full-workflow, commercial-grade poster generation method.<n>PosterVerse replicates professional design through three key stages.<n>PosterDNA is a commercial-grade, HTML-based dataset.
  arXiv  Detail & Related papers  (2026-01-07T15:04:24Z)
• SkyReels-Text: Fine-grained Font-Controllable Text Editing for Poster Design [8.272505030643039]
  We present SkyReels-Text, a novel font-controllable framework for precise poster text editing.<n>Our method enables simultaneous editing of multiple text regions, each rendered in distinct styles.<n>SkyReels-Text achieves state-of-the-art performance in both text fidelity and visual realism.
  arXiv  Detail & Related papers  (2025-11-17T12:02:52Z)
• PosterMaker: Towards High-Quality Product Poster Generation with Accurate Text Rendering [50.76106125697899]
  Product posters, which integrate subject, scene, and text, are crucial promotional tools for attracting customers.<n>Main challenge lies in accurately rendering text, especially for complex writing systems like Chinese, which contains over 10,000 individual characters.<n>We develop TextRenderNet, which achieves a high text rendering accuracy of over 90%.<n>Based on TextRenderNet and SceneGenNet, we present PosterMaker, an end-to-end generation framework.
  arXiv  Detail & Related papers  (2025-04-09T07:13:08Z)
• POSTA: A Go-to Framework for Customized Artistic Poster Generation [87.16343612086959]
  POSTA is a modular framework for customized artistic poster generation.<n>Background Diffusion creates a themed background based on user input.<n>Design MLLM then generates layout and typography elements that align with and complement the background style.<n>ArtText Diffusion applies additional stylization to key text elements.
  arXiv  Detail & Related papers  (2025-03-19T05:22:38Z)
• Optimisation-Based Multi-Modal Semantic Image Editing [58.496064583110694]
  We propose an inference-time editing optimisation to accommodate multiple editing instruction types. By allowing to adjust the influence of each loss function, we build a flexible editing solution that can be adjusted to user preferences. We evaluate our method using text, pose and scribble edit conditions, and highlight our ability to achieve complex edits.
  arXiv  Detail & Related papers  (2023-11-28T15:31:11Z)
• Text Revision by On-the-Fly Representation Optimization [76.11035270753757]
  Current state-of-the-art methods formulate these tasks as sequence-to-sequence learning problems. We present an iterative in-place editing approach for text revision, which requires no parallel data. It achieves competitive and even better performance than state-of-the-art supervised methods on text simplification.
  arXiv  Detail & Related papers  (2022-04-15T07:38:08Z)

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.