Pico-Banana-400K: A Large-Scale Dataset for Text-Guided Image Editing

Yusu Qian, Eli Bocek-Rivele, Liangchen Song, Jialing Tong, Yinfei Yang, Jiasen Lu, Wenze Hu, Zhe Gan

Introduction

Text-guided image editing is a core capability for modern multimodal large language models (MLLMs). However, the field faces a significant data bottleneck. Existing datasets are often either small and human-curated, which limits scalability, or entirely synthetic, leading to a "domain shift" where models struggle with real-world photographs. Furthermore, the lack of "negative" examples—failed edits—hinders the application of alignment techniques like Direct Preference Optimization (DPO).

To address these challenges, researchers have introduced Pico-Banana-400K, a massive dataset of approximately 400,000 high-quality text-guided image edits derived from real-world photographs. This resource includes single-turn instructions, multi-turn editing sequences, and preference pairs for alignment research.

Methodology

The creation of Pico-Banana-400K utilizes a systematic pipeline designed to scale data generation while maintaining high quality through automated oversight.

Overview of the Pico-Banana-400K data generation pipeline and edit categories.

The pipeline consists of four main stages:

  1. Source Material Selection: Images are sourced from the OpenImages collection to ensure visual realism.
  2. Instruction Generation: Gemini-2.5-Flash generates both detailed prompts for training and concise user-style commands.
  3. Execution: The Nano-Banana model performs the edits based on these instructions.
  4. Automated Quality Control: Gemini-2.5-Pro acts as a judge, scoring results based on instruction compliance (40%), seamlessness (25%), preservation of original content (20%), and technical quality (15%). Failed edits are retried up to three times; persistent failures are retained as negative samples for preference learning.

Dataset Characteristics

The resulting dataset comprises 386,000 samples categorized into three distinct subsets to support various training objectives.

Breakdown of the Pico-Banana-400K dataset composition across SFT and Preference subsets.
  • Single-Turn SFT (258K): High-quality pairs for Supervised Fine-Tuning.
  • Multi-Turn SFT (72K): Sequences of 2–5 edits that require the model to maintain context and handle referential language (e.g., "change the color of it").
  • Preference Pairs (56K): Successful vs. failed edit pairs for reward modeling and DPO.

The dataset spans 35 edit types across 8 categories, including stylistic transfers, object manipulation, and photometric changes.

Results and Analysis

Analysis of the dataset reveals varying levels of difficulty for current MLLMs:

  • High Success Rates: Global style transfers (93.4%) and vintage filters (90.7%) are handled with high reliability.
  • Moderate Success: Object removal is robust, succeeding in 83.3% of cases, though it can occasionally affect adjacent regions.
  • Current Frontiers: Tasks requiring precise spatial reasoning or typography remain challenging. Relocating objects (59.2%) and changing font styles (57.6%) represent the most difficult tasks for current models.

Conclusion and Future Work

Pico-Banana-400K provides a robust foundation for training the next generation of image-editing models by bridging the gap between synthetic scale and real-world realism. While it significantly advances the availability of training data, limitations remain in spatial precision, typography integrity, and identity preservation during transformations. Future work should focus on region-referential prompting and explicit supervision for text rendering to overcome these hurdles.

Summary updated

BibTeX
@inproceedings{qian2026pico,
  author = {Yusu Qian and Eli Bocek-Rivele and Liangchen Song and Jialing Tong and Yinfei Yang and Jiasen Lu and Wenze Hu and Zhe Gan},
  title = {{Pico-Banana-400K: A Large-Scale Dataset for Text-Guided Image Editing}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year = {2026},
  url = {https://openreview.net/forum?id=VkFLji83Sv},
}
Figure