ProductConsistency: Improving Product Identity Preservation in Instruction-Based Image Editing via SFT and RL

• URL: http://arxiv.org/abs/2606.19103v1
• Date: Wed, 17 Jun 2026 14:16:47 GMT
• Title: ProductConsistency: Improving Product Identity Preservation in Instruction-Based Image Editing via SFT and RL
• Abstract summary: We introduce the ProductConsistency dataset which is designed to improve product-centric image editing.<n>Our approach includes a supervised fine-tuning (SFT) dataset of 87k samples for product editing, and a reinforcement learning (RL) dataset with 869 unique product images.<n>To guide RL training, we propose a Cyclic Consistency reward that enforces semantic preservation of product identity.
• Score: 4.71547360356314
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advances in instruction-based image editing have enabled models to perform complex visual edits from natural language instructions. However, in product-centric scenarios where preserving product features, branding, and textual elements are critical, current open and closed source models often struggle to maintain this fine-grained object identity. This issue is further compounded by the lack of datasets for instruction-based product image editing with text fidelity constraints, leaving it largely treated as an implicit capability of instruction-based image editing models. In this work, we introduce the ProductConsistency dataset which is designed to improve product-centric image editing. Our approach includes a supervised fine-tuning (SFT) dataset of 87k samples for product editing, a reinforcement learning (RL) dataset with 869 unique product images, and a new benchmark dataset, the ProductConsistency Benchmark, to allow rigorous and standardized evaluation of editing models. To guide RL training, we propose a Cyclic Consistency reward that enforces semantic preservation of product identity by using caption similarity between the original product description and captions generated from the edited image. We fine-tune both Qwen-Image-Edit-2511 and Flux.1-Kontext-dev using our dataset and demonstrate consistent improvements over baseline models in OCR and Perceptual metrics, and MLLM-based evaluations as well, indicating stronger product consistency, text rendering, and overall visual quality; with the Qwen-Image-Edit-2511 model achieving a 5x reduction in the character error rate. The code and pipeline is available at https://anonymous.4open.science/r/ProductConsistency-6FCC/README.md

Related papers

• Group Editing: Edit Multiple Images in One Go [48.78947366708772]
  GroupEditing is a framework that builds explicit and implicit relationships among images within a group.<n>GroupEditData is a dataset containing high-quality masks and detailed captions for numerous image groups.<n>We present GroupEditBench, a benchmark designed to evaluate the effectiveness of group-level image editing.
  arXiv  Detail & Related papers  (2026-03-24T07:31:47Z)
• CycleCap: Improving VLMs Captioning Performance via Self-Supervised Cycle Consistency Fine-Tuning [65.10059440725041]
  Visual-Language Models (VLMs) have achieved remarkable progress in image captioning, visual question answering, and visual reasoning.<n>They remain prone to vision-language misalignment, often producing overly generic or hallucinated descriptions.<n>Existing approaches address this via instruction tuning-requiring costly, large-scale annotated datasets or via complex test-time frameworks for caption refinement.<n>In this work, we revisit image-text alignment through the lens of cycle consistency.
  arXiv  Detail & Related papers  (2026-03-18T20:57:31Z)
• Trust Your Critic: Robust Reward Modeling and Reinforcement Learning for Faithful Image Editing and Generation [67.26349227500084]
  Current reward models, which act as critics during reinforcement learning, often suffer from hallucinations and assign noisy scores.<n>We present FIRM, a comprehensive framework that develops robust reward models to provide accurate and reliable guidance for faithful image generation and editing.<n> FIRM mitigates hallucinations, establishing a new standard for fidelity and instruction adherence over existing general models.
  arXiv  Detail & Related papers  (2026-03-12T17:57:21Z)
• EditInfinity: Image Editing with Binary-Quantized Generative Models [64.05135380710749]
  We investigate the parameter-efficient adaptation of binary-quantized generative models for image editing.<n>Specifically, we propose EditInfinity, which adapts emphInfinity, a binary-quantized generative model, for image editing.<n>We propose an efficient yet effective image inversion mechanism that integrates text prompting rectification and image style preservation.
  arXiv  Detail & Related papers  (2025-10-23T05:06:24Z)
• Describe, Don't Dictate: Semantic Image Editing with Natural Language Intent [38.61468007698179]
  We propose a descriptive-prompt-based editing framework, named DescriptiveEdit.<n>The core idea is to re-frame instruction-based image editing' as reference-image-based text-to-image generation'
  arXiv  Detail & Related papers  (2025-08-28T07:45:08Z)
• ImgEdit: A Unified Image Editing Dataset and Benchmark [14.185771939071149]
  We introduce ImgEdit, a large-scale, high-quality image-editing dataset comprising 1.2 million carefully curated edit pairs.<n>ImgEdit surpasses existing datasets in both task novelty and data quality.<n>For comprehensive evaluation, we introduce ImgEdit-Bench, a benchmark designed to evaluate image editing performance.
  arXiv  Detail & Related papers  (2025-05-26T17:53:33Z)
• An Evaluation Framework for Product Images Background Inpainting based on Human Feedback and Product Consistency [4.177224329586615]
  In product advertising applications, the automated inpainting of backgrounds utilizing AI techniques in product images has emerged as a significant task.<n>Human Feedback and Product Consistency (HFPC) can automatically assess the generated product images based on two modules.<n> HFPC achieves state-of-the-art(96.4% in precision) in comparison to other open-source visual-quality-assessment models.
  arXiv  Detail & Related papers  (2024-12-23T12:03:35Z)
• ReEdit: Multimodal Exemplar-Based Image Editing with Diffusion Models [11.830273909934688]
  Modern Text-to-Image (T2I) Diffusion models have revolutionized image editing by enabling the generation of high-quality images. We propose ReEdit, a modular and efficient end-to-end framework that captures edits in both text and image modalities. Our results demonstrate that ReEdit consistently outperforms contemporary approaches both qualitatively and quantitatively.
  arXiv  Detail & Related papers  (2024-11-06T15:19:24Z)
• Preserve or Modify? Context-Aware Evaluation for Balancing Preservation and Modification in Text-Guided Image Editing [26.086806549826058]
  Text-guided image editing seeks the preservation of core elements in the source image while implementing modifications based on the target text.<n>Existing metrics have a context-blindness problem, indiscriminately applying the same evaluation criteria on completely different pairs of source image and target text.<n>We propose AugCLIP, a context-aware metric that adaptively coordinates preservation and modification aspects.
  arXiv  Detail & Related papers  (2024-10-15T08:12:54Z)
• Localizing and Editing Knowledge in Text-to-Image Generative Models [62.02776252311559]
  knowledge about different attributes is not localized in isolated components, but is instead distributed amongst a set of components in the conditional UNet. We introduce a fast, data-free model editing method Diff-QuickFix which can effectively edit concepts in text-to-image models.
  arXiv  Detail & Related papers  (2023-10-20T17:31:12Z)
• iEdit: Localised Text-guided Image Editing with Weak Supervision [53.082196061014734]
  We propose a novel learning method for text-guided image editing. It generates images conditioned on a source image and a textual edit prompt. It shows favourable results against its counterparts in terms of image fidelity, CLIP alignment score and qualitatively for editing both generated and real images.
  arXiv  Detail & Related papers  (2023-05-10T07:39:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.