Pith. sign in

REVIEW 18 cited by

SEED-Data-Edit Technical Report: A Hybrid Dataset for Instructional Image Editing

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2405.04007 v1 pith:F35YA67X submitted 2024-05-07 cs.CV

classification cs.CV
keywords editingimageseed-data-editdatadatasetmodeldatasetsdiverse
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In this technical report, we introduce SEED-Data-Edit: a unique hybrid dataset for instruction-guided image editing, which aims to facilitate image manipulation using open-form language. SEED-Data-Edit is composed of three distinct types of data: (1) High-quality editing data produced by an automated pipeline, ensuring a substantial volume of diverse image editing pairs. (2) Real-world scenario data collected from the internet, which captures the intricacies of user intentions for promoting the practical application of image editing in the real world. (3) High-precision multi-turn editing data annotated by humans, which involves multiple rounds of edits for simulating iterative editing processes. The combination of these diverse data sources makes SEED-Data-Edit a comprehensive and versatile dataset for training language-guided image editing model. We fine-tune a pretrained Multimodal Large Language Model (MLLM) that unifies comprehension and generation with SEED-Data-Edit. The instruction tuned model demonstrates promising results, indicating the potential and effectiveness of SEED-Data-Edit in advancing the field of instructional image editing. The datasets are released in https://huggingface.co/datasets/AILab-CVC/SEED-Data-Edit.

Discussion (0). Sign in to comment.

Forward citations

Cited by 18 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. CV-Arena: An Open Benchmark for Instructional Computer Vision Problem Solving with Human-AI Collaborative Preferences

    cs.CV 2026-05 unverdicted novelty 7.0 of 10

    CV-Arena is a new 12K-pair benchmark for instruction-guided real-image editing with 16 task types, CogRetriever curation, and Active Elo mixed human-AI evaluation that finds gaps in 21 models and presents CV-Agent.

  2. VINS-120K: Ultra High-Resolution Image Editing with A Large-Scale Dataset

    cs.CV 2026-05 unverdicted novelty 7.0 of 10

    VINS-120K supplies the first large-scale set of instruction-image-edited-image triplets at ultra-high resolution together with an adaptation strategy that improves detail synthesis.

  3. Do-Undo Bench: Reversibility for Action Understanding in Image Generation

    cs.CV 2025-12 unverdicted novelty 7.0 of 10

    Do-Undo Bench is a new evaluation task and dataset that forces models to simulate forward action effects and then undo them to measure genuine action understanding in image generation.

  4. VACE: All-in-One Video Creation and Editing

    cs.CV 2025-03 unverdicted novelty 7.0 of 10

    VACE unifies reference-to-video generation, video-to-video editing, and masked video-to-video editing in one Diffusion Transformer framework using a Video Condition Unit for inputs and a Context Adapter for task injection.

  5. OmniGen-AR: AutoRegressive Any-to-Image Generation

    cs.CV 2026-06 unverdicted novelty 6.0 of 10

    OmniGen-AR is a unified autoregressive framework for any-to-image generation that tokenizes text and visual conditions together and uses disentangled causal attention to support tasks like text-to-image, depth-to-imag...

  6. STARFlow2: Bridging Language Models and Normalizing Flows for Unified Multimodal Generation

    cs.CV 2026-05 unverdicted novelty 6.0 of 10

    STARFlow2 presents an autoregressive flow-based architecture for unified multimodal text-image generation by interleaving a VLM stream with a TarFlow stream via residual skips and a unified latent space.

  7. SpatialEdit: Benchmarking Fine-Grained Image Spatial Editing

    cs.CV 2026-04 unverdicted novelty 6.0 of 10

    SpatialEdit provides a benchmark, large synthetic dataset, and baseline model for precise object and camera spatial manipulations in images, with the model beating priors on spatial editing.

  8. Under One Sun: Multi-Object Generative Perception of Materials and Illumination

    cs.CV 2026-03 conditional novelty 6.0 of 10

    Factorizing video editing into semantic-token anchoring and motion-restoration pre-training produces strong zero-shot and SOTA open-source instruction-guided video edits without heavy external structural priors.

  9. Hierarchical Concept-to-Appearance Guidance for Multi-Subject Image Generation

    cs.CV 2026-02 conditional novelty 6.0 of 10

    A diffusion-transformer framework with VLM-grounded masked attention and VAE dropout improves identity and prompt fidelity for multi-subject image generation.

  10. EditVerse: Unifying Image and Video Editing and Generation with In-Context Learning

    cs.CV 2025-09 unverdicted novelty 6.0 of 10

    EditVerse unifies image and video editing and generation in one transformer model via unified token sequences and in-context learning, trained jointly on curated video editing data plus image/video corpora and evaluat...

  11. ImgEdit: A Unified Image Editing Dataset and Benchmark

    cs.CV 2025-05 conditional novelty 6.0 of 10

    ImgEdit supplies 1.2 million curated edit pairs and a three-part benchmark that let a VLM-based model outperform prior open-source editors on adherence, quality, and detail preservation.

  12. Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling

    cs.CV 2026-04 unverdicted novelty 5.0 of 10

    Visual generation models are evolving from passive renderers to interactive agentic world modelers, but current systems lack spatial reasoning, temporal consistency, and causal understanding, with evaluations overemph...

  13. FineEdit: Fine-Grained Image Edit with Bounding Box Guidance

    cs.CV 2026-04 unverdicted novelty 5.0 of 10

    FineEdit adds multi-level bounding box injection to diffusion image editing, releases a 1.2M-pair dataset with box annotations, and shows better instruction following and background consistency than prior open models ...

  14. Draw-In-Mind: Rebalancing Designer-Painter Roles in Unified Multimodal Models Benefits Image Editing

    cs.CV 2025-09 unverdicted novelty 5.0 of 10

    Rebalancing designer-painter roles by assigning design to the understanding module via the new DIM dataset yields SOTA image editing performance with a 4.6B model.

  15. GenTune: Toward Traceable Prompts to Improve Controllability of Image Refinement in Environment Design

    cs.HC 2025-08 conditional novelty 5.0 of 10

    GenTune improves AI image refinement by tracing image regions back to prompt labels and allowing element-level, semantic-guided edits.

  16. OmniGen2: Towards Instruction-Aligned Multimodal Generation

    cs.CV 2025-06 unverdicted novelty 5.0 of 10

    OmniGen2 introduces a unified generative model with two distinct decoding pathways and a decoupled image tokenizer that achieves competitive results on text-to-image and editing benchmarks plus state-of-the-art consis...

  17. Emerging Properties in Unified Multimodal Pretraining

    cs.CV 2025-05 unverdicted novelty 5.0 of 10

    BAGEL is a unified decoder-only model that develops emerging complex multimodal reasoning abilities after pretraining on large-scale interleaved data and outperforms prior open-source unified models.

  18. Step1X-Edit: A Practical Framework for General Image Editing

    cs.CV 2025-04 unverdicted novelty 4.0 of 10

    Step1X-Edit integrates a multimodal LLM with a diffusion decoder, trained on a custom high-quality dataset, to deliver image editing performance that surpasses open-source baselines and approaches proprietary models o...

Pith tools