Research map / Image generation / Text-to-image diffusion
InnoAds-Composer: Efficient Condition Composition for E-Commerce Poster Generation
Yuxin Qin, Ke Cao, Haowei Liu, Ao Ma, Fengheng Li, Honghe Zhu, Zheng Zhang, Run Ling, Wei Feng, Xuanhua He, Zhanjie Zhang, Zhen Guo and 4 more
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 Stage II token pruning and fine-tuning | InnoAds-Composer · Inference efficiency | Latency (s): 55.87 -> 47.32 | Improved |
| add Stage II token pruning and fine-tuning | InnoAds-Composer · InnoComposer-Bench | FID: 54.39 -> 55.24 | Hurt |
| add Stage II token pruning and fine-tuning | InnoAds-Composer · InnoComposer-Bench | Sen. Acc: 0.857 -> 0.847 | Hurt |
| add Stage II token pruning and fine-tuning | InnoAds-Composer · Inference efficiency | FLOPs (T): 165.56 -> 135.25 | Improved |
| add decoupled attention (vs native full attention) | InnoAds-Composer Stage I vs Flux-Kontext · Inference efficiency | Latency (s): 76.02 -> 55.87 | Improved |
| add Text Feature Enhancement Module (ablation) | InnoAds-Composer · InnoComposer-Bench | Sen. Acc: approximately 5% improvement | Improved |
| use importance-aware instead of random or uniform token pruning (ablation) | InnoAds-Composer Stage I · InnoComposer-Bench | NED, MSE, CLIP-I | Improved |
| prune glyph/subject/style tokens at 90/60/70 instead of 80/50/60 (ablation) | InnoAds-Composer Stage II · Stage II token pruning ratios | NED: 0.969 -> 0.582 | Hurt |
| prune glyph/subject/style tokens at 50/20/30 instead of 80/50/60 (ablation) | InnoAds-Composer Stage II · Stage II token pruning ratios | NED: 0.971 vs 0.969 | No clear effect |
| prune at 90/60/70 instead of 80/50/60 (ablation) | InnoAds-Composer Stage II · Stage II token pruning ratios | CLIP-I: 0.594 -> 0.451 | 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 2 of 2 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
- GlyphDraw2: Automatic Generation of Complex Glyph Posters with Diffusion Models and Large Language Models (AAAI 2025 · similarity 0.86)
- PosterMaker: Towards High-Quality Product Poster Generation with Accurate Text Rendering (CVPR 2025 · similarity 0.85)
- POSTA: A Go-to Framework for Customized Artistic Poster Generation (CVPR 2025 · similarity 0.84)
- P2P: Automated Paper-to-Poster Generation and Fine-Grained Benchmark (ICLR 2026 · similarity 0.83)
- DesignDiffusion: High-Quality Text-to-Design Image Generation with Diffusion Models (CVPR 2025 · similarity 0.83)
- BizGen: Advancing Article-level Visual Text Rendering for Infographics Generation (CVPR 2025 · similarity 0.83)
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.
