InfoVis: Unified Slide Image Generation and Editing

Jiahao Wang; Xiyan Jiang; Chenyuan Wu; Haoqiang Zhang; Xin Luo; Yueze Wang; Defu Lian; Bo Zhang

cs.CVOct 12, 2026

InfoVis: Unified Slide Image Generation and Editing

Authors: Jiahao Wang, Xiyan Jiang, Chenyuan Wu, Haoqiang Zhang, Xin Luo, Yueze Wang, Defu Lian, Bo Zhang,

Organizations: Institute of Automation, Chinese Academy of Sciences · Beijing Academy of Artificial Intelligence · Zhejiang University · University of Science and Technology of China

Abstract

Generating and editing presentation slides requires models to combine accurate text rendering, instruction following, visual grounding, aesthetic design, and precise editing within one canvas. Existing work covers only subsets of these capabilities and lacks large-scale slide-native supervision and diagnostic evaluation. We formulate four slide-centric tasks and build a scalable data engine with over 13M continual-pretraining records and 1.9M supervised fine-tuning records. We also introduce VisSlideBench, a benchmark of 1,527 manually screened instances that covers all four tasks with task-specific, multidimensional evaluation. Its automatic rankings agree with blinded, dimension-wise human rankings. Using these resources, we train InfoVis, a unified 9B slide generation and editing model. On VisSlideBench, InfoVis leads every evaluated open-source model on all eleven metrics and scores 7.94 overall against 7.99 for Nano-Banana-2. Starting from FLUX.2-klein-base-9B, slide-specific post-training adds 1.6 points overall, with the largest generation gains in content faithfulness; the remaining gap to proprietary models is smallest in content faithfulness and largest in aesthetic quality. Built on InfoVis, our document-to-slide workflow achieves the second-highest Aesthetics score on the external SlidesGen-Bench. We will release the model, code, data, and benchmark.

Figures & tables

Figure 1: Overview of our slide tasks, InfoVis, and VisSlideBench. InfoVis is trained through three stages on four generation and editing tasks, and VisSlideBench evaluates each task along task-specific dimensions. Bar values are the dimension means of Tables 12 – 15 .

Figure 2: Slide data engine. (A) Continual pretraining: real decks are filtered, parsed into text and localized visual assets, and annotated with short requests, detailed descriptions, and style_json ; the same target slide yields text-to-slide, template-conditioned, and multi-image records, and executed PPTX edits yield source–instruction–target triplets. (B) Supervised fine-tuning: Nano-Banana-2 synthesizes targets from LLM concepts, SlideShare content, and paper-derived slide specifications; multi-image records reuse assets extracted from synthesized targets; editing records combine selected CPT triplets with model-generated theme switching and image replacement.

Type	Model	T2I			Template			Multi-image			Edit		Overall
Type	Model	CF	IF	AQ	CF	IF	AQ	CF	IF	AQ	SC	PQ	Overall
Proprietary	GPT-Image-2	8.52	8.57	7.71	8.19	8.51	7.62	8.93	8.44	7.61	9.80	8.04	8.36
	Nano-Banana-2	8.38	8.17	7.33	7.59	7.95	7.08	8.60	7.93	7.14	9.70	8.03	7.99
	Qwen-Image-2	7.18	6.89	6.38	8.23	6.29	5.74	6.97	6.25	5.55	4.96	6.47	6.45
Open-source	Qwen-Image	6.50	6.34	5.17	–	–	–	–	–	–	–	–	–
	Z-Image-Turbo	6.66	6.84	5.79	–	–	–	–	–	–	–	–	–

Table 1: Main results on VisSlideBench. T2I, Template, and Multi-image report Content Faithfulness (CF), Instruction Following (IF), and Aesthetic Quality (AQ); Edit reports Semantic Consistency (SC) and Presentation Quality (PQ). Overall averages the eleven metrics; bold marks the best in each group.

Table 4

Stage	Model	T2I			Template			Multi-image			Edit		Overall
Stage	Model	CF	IF	AQ	CF	IF	AQ	CF	IF	AQ	SC	PQ	Overall
Base	FLUX.2-klein-base-9B	6.29	7.11	5.19	6.44	7.24	5.40	6.57	6.99	5.32	5.98	6.72	6.30
CPT	Stage-1 CPT: T2I only	8.00	7.32	6.05	5.93	7.03	4.57	6.16	6.23	4.89	1.60	4.78	5.69
CPT	Stage-2 CPT: four-task mixture	8.15	7.42	6.22	8.04	7.77	6.33	8.38	7.54	6.29	7.87	7.13	7.38
Task SFT	Shared SFT	8.28	7.80	6.83	8.25	7.87	6.81	8.50	7.82	6.82	8.44	7.60	7.73
	Shared SFT + T2I SFT	8.28	7.72	6.84	8.12	7.81	6.72	8.24	7.90	6.94	7.92	7.43	7.63

Table 4: Training-stage ablation; metric groups and Overall follow Table 1 . Bold marks the best in each column.

Figure 3: Test-time scaling and prompt categories on the T2I split. (a) Best-of-

K

selection for

K\in\{1,2,4,8\}

: IF dimensions, AQ dimensions, and aggregates. (b) Mean of per-slide CF, IF, and AQ over all 317 cases by prompt category. Vertical ranges differ across panels.

Appendix figures & tables24 assets

Supplementary material from the paper’s appendix.

Appendix

Operation	Construction	SFT records
Text modification	PPTX execution	$\approx$ 10K
Block addition	Reversed block removal	$\approx$ 10K
Block removal	PPTX execution	$\approx$ 10K
Background update	PPTX execution	$\approx$ 10K
Color change	PPTX execution	$\approx$ 10K
Font change	PPTX execution	$\approx$ 10K

Appendix

Table 5: Editing operations and SFT records. The seven executable operations also contribute to CPT. Theme switching and image replacement are used only for SFT.

Training branch	CPT records	SFT records
Text-to-slide	$\approx$ 5.16M	$\approx$ 890K
Template-conditioned	$\approx$ 3.92M	$\approx$ 300K
Multi-image grounded	$\approx$ 2.25M	$\approx$ 580K
Slide editing	$\approx$ 2.12M	$\approx$ 140K
Total	$>13M$	$\approx$ 1.9M

Appendix

Table 6: Training records by branch. Counts are rounded. Multiple records can share a target slide or differ only in their instruction or visual condition.

Figure 4: Training record distributions by task and by CPT/SFT pool. Generation branches are further divided by source and domain, and the editing branch by operation. IC denotes multi-image grounded generation; Ref denotes template-conditioned generation. Counts are rounded.

Feature	SlidesBench Ge et al. ( 2025 )	PPTBench Huang et al. ( 2025 )	BizGenEval Li et al. ( 2026 )	PresentBench Chen et al. ( 2026 )	SlidesGen- Bench Yang et al. ( 2026 )	VisSlideBench (ours)
General Properties
Size	585	4,439 mixed	400 total (80 slides)	238	189	1,527
Single-slide evaluation	$\checkmark$	$\checkmark$	$\checkmark$	$\times$	$\times$	$\checkmark$
Image-centric systems included	$\checkmark$	$\times$	$\checkmark$	$\checkmark$	$\checkmark$	$\checkmark$
Task Coverage
Text-to-single-slide	$\checkmark$	$\checkmark$	$\checkmark$	$\times$	$\times$	$\checkmark$

Appendix

Table 7: Comparison of representative slide-creation benchmarks. A checkmark indicates explicit coverage in the task or evaluation protocol; a cross indicates that the feature is not covered. Size reports evaluation cases, with mixed tasks and slide subsets identified.

Figure 5: VisSlideBench curation and evaluation. Left: task coverage and manual screening for generation and held-out editing data. Right: representative multi-image generation and editing cases illustrate the evaluation criteria with recorded scores and concise scoring explanations. CF describes the scoring procedure; editing PQ explanations summarize the four AQ dimensions. MLLM judges assess visual criteria, while OCR-based text matching evaluates text fidelity.

Task	Visual input	Real	Synthetic	Total
Text-to-slide	None	167	150	317
Template-conditioned	One reference slide	147	150	297
Multi-image grounded	One to four assets	179	150	329
Total		493	450	943

Appendix

Table 8: Composition of VisSlideBench-Gen. Counts refer to evaluation cases. The three prompt formats occur within each task.

Operation	Cases
Text modification	50
Block addition	74
Block removal	49
Background update	52
Color change	49
Font change	49

Appendix

Table 9: Composition of VisSlideBench-Edit.

Figure 6: Distribution of VisSlideBench examples across tasks, sources, domains, and editing operations.

Task	Examples	Rankings	Pairs	$\tau_{b}$	$\rho$	Agree. (%)
Text-to-slide	36	71	548	0.729	0.798	91.24
Template-conditioned	37	74	502	0.613	0.676	87.25
Multi-image grounded	32	88	540	0.640	0.702	90.00
Editing	32	95	563	0.595	0.645	86.32
Overall	137	328	2,153	0.640	0.700	88.71

Appendix

Table 10: Agreement between human rankings and GPT-4.1 scores. Rankings counts valid example–dimension pairs, and Pairs counts model pairs that are untied in both rankings.

Run	Nodes	GPUs	Steps	Global batch
Stage 1: T2I CPT	6	48	13,500	384
Stage 2: four-task mixed CPT	10	80	16,500	640
T2I SFT	10	80	4,500	640
Template-conditioned SFT	10	80	1,500	640
Multi-image grounded SFT	12	96	2,500	768
Editing SFT	12	96	500	768

Appendix

Table 11: Training stages and resources. The shared checkpoint

\theta_{\mathrm{shared}}

is the step-1,500 checkpoint of the T2I SFT run.

Type	Model	CF	IF						AQ				Overall
Type	Model	Text	BG	Color	Typo	Layout	Mood	Block	Clarity	LayoutQ	StyleQ	Prof	Overall
Proprietary	GPT-Image-2	8.52	8.71	8.44	8.31	8.44	9.26	8.23	8.05	7.29	8.09	7.39	8.25
	Nano-Banana-2	8.38	8.39	8.13	7.81	7.97	8.93	7.81	7.72	6.97	7.66	6.97	7.89
	Qwen-Image-2	7.18	7.01	6.90	6.72	6.83	7.59	6.29	6.32	6.34	6.97	5.88	6.73
Open-source	Qwen-Image	6.50	7.09	6.70	5.85	6.04	7.04	5.34	4.84	5.38	5.92	4.55	5.93
	Z-Image-Turbo	6.66	7.72	7.16	6.51	6.45	7.49	5.68	5.25	6.18	6.73	4.99	6.44

Appendix

Table 12: Detailed text-to-slide results. CF reports Text Rendering. IF reports Background Compliance (BG), Color Palette Adherence (Color), Typography Compliance (Typo), Layout and Position Accuracy (Layout), Mood and Atmosphere Match (Mood), and Block-Level Style Fidelity (Block). AQ reports Clarity, Layout Quality (LayoutQ), Style Coherence (StyleQ), and Presentation Professionalism (Prof). Overall averages these eleven dimensions. Bold marks the best score within each model group. Higher is better.

Type	Model	CF	IF						AQ				Overall
Type	Model	Text	BG	Color	Typo	Layout	Mood	Block	Clarity	LayoutQ	StyleQ	Prof	Overall
Proprietary	GPT-Image-2	8.19	9.08	8.70	8.50	7.51	9.34	7.93	7.93	7.22	8.02	7.32	8.16
	Nano-Banana-2	7.59	8.85	8.26	7.97	6.74	8.90	6.96	7.38	6.73	7.47	6.74	7.60
	Qwen-Image-2	8.23	6.65	6.49	6.07	5.89	6.93	5.68	5.85	5.53	6.24	5.35	6.26
Open-source	Qwen-Image-Edit	3.10	7.25	7.02	6.51	4.46	6.63	3.98	5.19	5.49	6.11	4.83	5.51
	LongCat-Image-Edit	4.86	7.08	6.51	5.69	5.46	6.70	4.52	4.51	5.37	5.88	4.41	5.54

Appendix

Table 13: Detailed template-conditioned generation results. Dimensions follow Table 12 ; Overall averages the same eleven dimensions. Bold marks the best score within each model group. Higher is better.

Type	Model	CF		IF						AQ				Overall
Type	Model	Text	MIC	BG	Color	Typo	Layout	Mood	Block	Clarity	LayoutQ	StyleQ	Prof	Overall
Proprietary	GPT-Image-2	8.38	9.47	8.74	8.29	8.26	8.20	9.16	8.00	7.83	7.24	8.06	7.30	8.24
	Nano-Banana-2	7.74	9.46	8.37	7.87	7.65	7.52	8.78	7.39	7.34	6.77	7.66	6.79	7.78
	Qwen-Image-2	7.25	6.69	6.42	6.31	6.23	5.97	6.81	5.75	5.50	5.44	6.18	5.07	6.14
Open-source	Qwen-Image-Edit	3.74	4.94	5.96	5.53	3.96	4.20	5.37	3.40	3.41	4.41	5.27	3.39	4.47
	LongCat-Image-Edit	4.58	5.91	5.97	5.79	4.60	4.59	5.76	3.91	4.07	4.67	5.43	3.88	4.93

Appendix

Table 14: Detailed multi-image grounded generation results. In addition to Text Rendering, CF includes Multi-image Consistency (MIC), which measures preservation and use of supplied assets. Other dimensions follow Table 12 . Overall averages all twelve dimensions. Bold marks the best score within each model group. Higher is better.

Type	Model	Text	Color	Font	Typo	Remove	Add	Image	Theme	BG	Overall
Proprietary	GPT-Image-2	9.03	8.83	8.52	8.64	8.42	8.98	9.44	8.77	8.74	8.88
	Nano-Banana-2	8.93	8.80	8.30	8.53	8.07	8.85	9.33	9.26	8.62	8.83
	Qwen-Image-2	5.82	5.67	3.84	4.54	2.80	6.15	6.43	7.75	5.79	5.66
Open-source	Qwen-Image-Edit	7.02	6.26	5.95	6.80	7.66	7.95	8.74	8.13	7.84	7.57
	LongCat-Image-Edit	5.52	6.58	4.06	5.22	7.23	6.66	7.95	7.41	6.94	6.63
	FLUX.2-dev	6.04	5.99	4.42	4.68	5.84	5.91	8.22	7.88	8.25	6.63

Appendix

Table 15: Results for all nine editing operations. Text, Typo, Image, Theme, and BG denote text modification, typography changes, image replacement, theme switching, and background updates. Each score is the geometric mean of Semantic Consistency (SC) and Presentation Quality (PQ); Overall uses overall SC and PQ. Bold marks the best score within each model group. Higher is better.

Type	Model	T2I		Template		Multi-image		Macro		$\|\Delta\|$
Type	Model	R	S	R	S	R	S	R	S	$\|\Delta\|$
Proprietary	GPT-Image-2	8.26	8.28	8.08	8.13	8.36	8.28	8.23	8.23	0.004
	Nano-Banana-2	8.00	7.92	7.37	7.70	7.95	7.81	7.77	7.81	0.039
	Qwen-Image-2	6.67	6.98	7.15	6.36	5.98	6.60	6.60	6.65	0.046
Open-source	FLUX.2-dev	6.25	6.41	6.41	6.17	6.15	6.46	6.27	6.35	0.076
	FLUX.2-klein-base-9B	6.15	6.25	6.53	6.20	6.15	6.47	6.28	6.31	0.029

Appendix

Table 16: Generation performance by benchmark source. R and S denote real and synthetic records. Each task score averages CF, IF, and AQ over the partition; Macro averages the three task scores.

|\Delta|

is the absolute Real–Synthetic macro gap. Bold marks the best score within each model group. Higher is better except for

|\Delta|

Model	Real (R)			Synthetic (S)
Model	CF	IF	AQ	CF	IF	AQ
Stage-2 CPT: four-task mixture	8.60	7.90	6.34	8.12	7.11	6.21
Shared SFT	8.64	8.05	6.68	8.34	7.53	6.97
Shared SFT + T2I SFT	8.50	8.12	6.84	7.92	7.65	7.05
Shared SFT + Template SFT	7.62	8.08	6.68	7.36	7.61	6.95
Shared SFT + Multi-image SFT	7.99	7.55	5.94	8.29	7.23	6.67

Appendix

Table 17: Multi-image grounded generation by benchmark source for the training-stage checkpoints. R: cases from real decks (179); S: synthetic cases (150). Each entry averages the per-case score over the cases with valid CF, IF, and AQ. Bold marks the best score in each column.

Baseline	Window	Clipped (S/L/J)	Full prompts	$\Delta$ on full prompts	$\Delta$ in Table 1
Qwen-Image	1,024	0 / 0 / 93	224	$+0.56$ / $+0.96$ / $+1.22$	$+1.92$ / $+1.67$ / $+1.85$
Z-Image-Turbo	1,024	0 / 0 / 93	224	$+0.56$ / $+0.46$ / $+0.89$	$+1.76$ / $+1.17$ / $+1.23$
LongCat-Image	512	46 / 98 / 93	80	$+2.05$ / $+1.54$ / $+2.27$	$+3.73$ / $+2.54$ / $+2.77$
Qwen-Image-2	1,024	0 / 0 / 93	224	$-0.05$ / $+0.35$ / $-0.30$	$+1.24$ / $+1.12$ / $+0.64$

Appendix

Table 18: Baselines whose text window clips VisSlideBench prompts. Clipped counts are per category (115 short, 109 long, 93 StyleJSON).

\Delta

is InfoVis minus the baseline in CF/IF/AQ, on the prompts the baseline received in full and on the full T2I split of Table 1 .

Figure 7: Document-to-slide workflow with InfoVis. Content planning and design planning produce structured per-slide prompts. InfoVis generates candidates that an external verifier ranks. The selected first slide serves as a style reference for subsequent slides. Optional PowerPoint export reconstructs editable text while retaining visual assets as images. Candidate slides are schematic illustrations.

Figure 8: Showcases of InfoVis in text-to-slide image generation.

Figure 9: Showcases of InfoVis in template-conditioned slide image generation.

Figure 10: Showcases of InfoVis in multi-image grounded slide image generation.

Figure 11: Showcases of InfoVis in slide image editing.

Figure 12: Showcases of the document-to-slide workflow built on InfoVis.

Figure 13: Failure cases of InfoVis. (a)–(b) A supplied chart and the generated slide show errors in visual asset fidelity; the solid outline marks the reconstructed chart. (c)–(d) An original slide and its edited output show changes beyond the requested left-hand graphs. Dashed outlines mark the table region that should have been preserved. The editing instruction above the panels is abridged.

Generative AI Evaluation

Generative AI evaluation measures the quality, reliability, diversity, and real-world usefulness of generated outputs and AI-assisted workflows.

See all 309 papers

X+Slides: Benchmarking Audience-Conditioned Slide Generation
Jun 17, 2026Haodong Chen, Xuanhe Zhou, Wei Zhou +6Evidence-Grounded Generation Conditional Generation
Shanghai Jiao Tong University · Harbin Institute of Technology · SenseTime
PresentBench: A Fine-Grained Rubric-Based Benchmark for Slide Generation
Mar 7, 2026Xin-Sheng Chen, Jiayu Zhu, Pei-lin Li +3Benchmark Design Generative AI Evaluation
Tsinghua University
SLIDEFORGE: An LLM Agent for Controllable Editing of Slides as Structured Artifacts
Sep 2, 2026Haozhen Zheng, Fulin Wang, Tianhu Xiong +6LLM Agents
University of Illinois Urbana-Champaign · Meta

Jun 17, 2026J/K move · Enter open · S save

X+Slides: Benchmarking Audience-Conditioned Slide Generation

Haodong Chen, Xuanhe Zhou, Wei Zhou, Xinyue Shao+5

Shanghai Jiao Tong University · Harbin Institute of Technology · SenseTime

Evidence-Grounded Generation Conditional Generation Generative AI Evaluation

Open paper AskPDF arXiv

Automatically generating slide decks from source documents is an important application of large language models (LLMs). Existing benchmarks primarily assess slide completeness and technical depth, while overlooking the target audience as a critical real-world factor. For instance, specialists demand rigorous proofs, whereas decision-makers prioritize actionable conclusions. To bridge this gap, we introduce X+Slides, a benchmark specifically designed for audience-conditioned slide generation. Built on a diverse corpus spanning 113 topics and seven presentation scenes, X+Slides employs a dynamic evaluation framework constructed from 8,133 deduplicated, source-grounded probes. By assigning audience-specific utility weights to the same source-grounded probes, X+Slides reports four complementary metrics: Audience Coverage measures how much audience-essential information is conveyed, Domain-wise Coverage shows which information types are covered, Efficiency measures delivered utility per unit of attention cost, and Correctness verifies whether slide claims are supported by the source. Experiments on DeepPresenter, SlideTailor, and NotebookLM show that current systems can recover a substantial but still incomplete part of audience-essential information: at

τ_A=0.7

, DeepPresenter reaches a best Audience Coverage of 0.714, SlideTailor reaches 0.594, and the NotebookLM ablation reaches 0.853 while showing clear grounding differences. These results indicate that visual quality and broad topic coverage should not be treated as evidence support without source-grounded evaluation.

Abstract

Generative AI Evaluation

Explore similar work

X+Slides: Benchmarking Audience-Conditioned Slide Generation

PresentBench: A Fine-Grained Rubric-Based Benchmark for Slide Generation

SLIDEFORGE: An LLM Agent for Controllable Editing of Slides as Structured Artifacts