mlsanityData to 7 Oct 2026

Ovis-Image Technical Report

arXiv 2511.22982 ↗First posted 28 Nov 2025cs.CV cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

We introduce Ovis-Image, a 7B text-to-image model specifically optimized for high-quality text rendering, designed to operate efficiently under stringent computational constraints. Built upon our previous Ovis-U1 framework, Ovis-Image integrates a diffusion-based visual decoder with the stronger Ovis 2.5 multimodal backbone, leveraging a text-centric training pipeline that combines large-scale pre-training with carefully tailored post-training refinements. Despite its compact architecture, Ovis-Image achieves text rendering performance on par with significantly larger open models such as Qwen-Image and approaches closed-source systems like Seedream and GPT4o. Crucially, the model remains deployable on a single high-end GPU with moderate memory, narrowing the gap between frontier-level text rendering and practical deployment. Our results indicate that combining a strong multimodal backbone with a carefully designed, text-focused training recipe is sufficient to achieve reliable bilingual text rendering without resorting to oversized or proprietary models.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 31 of its 39 references that are in the map. First posted on arXiv 28 Nov 2025.

Builds on

31 of 39 references.

References · 31

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  3. 2025Qwen2.5-VL Technical Reportcited by 5,418
  4. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,581
  5. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  6. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,611
  7. 2023FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioningcited by 2,551
  8. 2025Qwen-Image Technical Reportcited by 973
  9. 2023Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generationcited by 950
  10. 2023GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignmentcited by 946
  11. 2025Emerging Properties in Unified Multimodal Pretrainingcited by 855
  12. 2025Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scalingcited by 787
19 more
  1. 2023Diffusion Model Alignment Using Direct Preference Optimizationcited by 767
  2. 2016Language Modeling with Gated Convolutional Networkscited by 688
  3. 2025Flow-GRPO: Training Flow Matching Models via Online RLcited by 605
  4. 2024ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignmentcited by 455
  5. 2025BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Datasetcited by 363
  6. 2022Reducing Activation Recomputation in Large Transformer Modelscited by 300
  7. 2025OmniGen2: Towards Instruction-Aligned Multimodal Generationcited by 241
  8. 2025Seedream 4.0: Toward Next-generation Multimodal Image Generationcited by 233
  9. 2025HPSv3: Towards Wide-Spectrum Human Preference Scorecited by 196
  10. 2025Seedream 3.0 Technical Reportcited by 146
  11. 2025HiDream-I1: A High-Efficient Image Generative Foundation Model with Sparse Diffusion Transformercited by 131
  12. 2025X-Omni: Reinforcement Learning Makes Discrete Autoregressive Image Generative Models Great Againcited by 105
  13. 2025Ovis2.5 Technical Reportcited by 103
  14. 2025OneIG-Bench: Omni-dimensional Nuanced Evaluation for Image Generationcited by 81
  15. 2025Ovis-U1 Technical Reportcited by 65
  16. 2025Coefficients-Preserving Sampling for Reinforcement Learning with Flow Matchingcited by 55
  17. 2024Region-Aware Text-to-Image Generation via Hard Binding and Soft Refinementcited by 37
  18. 2025Investigating Text Insulation and Attention Mechanisms for Complex Visual Text Generationcited by 22
  19. 2025Diffusion-SDPO: Safeguarded Direct Preference Optimization for Diffusion Modelscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 8.

8 papers.

  1. 2026InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editingcited by 23
  2. 2026NTIRE 2026 Challenge on Robust AI-Generated Image Detection in the Wildcited by 18
  3. 2026Trust Your Critic: Robust Reward Modeling and Reinforcement Learning for Faithful Image Editing and Generationcited by 9
  4. 2026Fine-T2I: An Open, Large-Scale, and Diverse Dataset for High-Quality T2I Fine-Tuningcited by 4
  5. 2026Amber-Image: Efficient Compression of Large-Scale Diffusion Transformerscited by 1
  6. 2026Advances in GRPO for Generation Models: A Surveycited by 1
  7. 2026Faithful, Enriched, and Precise: Benchmarking Natural-Science Illustration Generation by T2I modelscited by 0
  8. 2026REALIS: A Curated Dataset for Studying the Challenges of AI Image Detectioncited by 0