Research map / Image generation / Text-to-image diffusion
SIMPLEPOSTER: A SIMPLE BASELINE FOR PRODUCT POSTER GENERATION
Benlei Cui, Fangao Zeng, Weitao Jiang, Yuwen Zhai, Haiwen Hong, Longtao Huang, Hui Xue, Wenxiang Shang, Pipei Huang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add character position encoding (ablation) | SimplePoster · SimplePoster benchmark | Sen.ACC: 24.94% -> 71.33% | Improved |
| add character position encoding (ablation) | SimplePoster · SimplePoster benchmark | NED: 0.5484 -> 0.8062 | Improved |
| add character position encoding (ablation) | FLUX.1-dev LoRA · multilingual multi-line | Sen. Acc: 0.0461 -> 0.2571 | Improved |
| add character position encoding (ablation) | FLUX.1-dev LoRA · multilingual single-line | NED: 0.6326 -> 0.6765 | Improved |
| add ControlNet with frozen backbone | FLUX-Fill · subject extension rate | subject extension rate: 41% -> 23.6% | Improved |
| LoRA tuning instead of ControlNet (ablation) | FLUX-Fill · subject extension rate | subject extension rate: 23.6% -> 2.8% | Improved |
| full-parameter tuning instead of LoRA (ablation) | FLUX-Fill · subject extension rate | subject extension rate: 2.8% -> 0.6% | Improved |
| train 3K images for 300 epochs instead of 3 epochs (ablation) | FLUX-Fill full tuning · subject extension rate | subject extension rate: 17.3% -> 3.6% | Improved |
| train 3K images for 10 epochs instead of 3 epochs (ablation) | FLUX-Fill full tuning · subject extension rate | subject extension rate: 17.3% -> 9.3% | Improved |
| scale data from 3K to 300K images (ablation) | FLUX-Fill full tuning · subject extension rate | subject extension rate: 3.6% -> 0.6% | Improved |
| SimplePoster vs PosterMaker subject preservation | SimplePoster · SimplePoster benchmark | subject preservation rate: 85.3% -> 98.7% | Improved |
| SimplePoster vs Gemini2.5Flash prompt following | SimplePoster · SimplePoster benchmark | prompt following: 3.82 -> 3.55 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- PosterMaker — PosterMaker: Towards High-Quality Product Poster Generation with Accurate Text Rendering (CVPR 2025) · better on 6 of 6 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- PosterMaker: Towards High-Quality Product Poster Generation with Accurate Text Rendering (CVPR 2025 · similarity 0.88)
- GlyphDraw2: Automatic Generation of Complex Glyph Posters with Diffusion Models and Large Language Models (AAAI 2025 · similarity 0.87)
- POSTA: A Go-to Framework for Customized Artistic Poster Generation (CVPR 2025 · similarity 0.86)
- Paper2Poster: Towards Multimodal Poster Automation from Scientific Papers (NeurIPS 2025 · similarity 0.86)
- DesignDiffusion: High-Quality Text-to-Design Image Generation with Diffusion Models (CVPR 2025 · similarity 0.86)
- Large-Scale Text-to-Image Model with Inpainting is a Zero-Shot Subject-Driven Image Generator (CVPR 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
