Compressing Image Style Training into a Single Model Forward

• URL: http://arxiv.org/abs/2606.13809v1
• Date: Thu, 11 Jun 2026 18:21:26 GMT
• Title: Compressing Image Style Training into a Single Model Forward
• Abstract summary: i2L (image-to-LoRA) is a framework that amortizes style LoRA training into a single forward pass.<n>We show that i2L improves style fidelity, prompt alignment, and perceptual quality over existing baselines.
• Score: 3.579087003804642
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion-based style transfer must balance inference efficiency with stylization fidelity. Adapter-based methods are efficient, but they inject style as an external condition and can either weaken reference-specific appearance or copy reference semantics into the generated image. Optimization-based personalization methods such as LoRA internalize style more effectively, but require a separate training process for every new style. We introduce i2L (image-to-LoRA), a framework that amortizes style LoRA training into a single forward pass. Given one or more reference images, i2L predicts LoRA weights for a text-to-image model, enabling immediate style instantiation without per-style optimization. The architecture combines an image encoder, learnable LoRA queries, and compressed decoding heads that generate adapted matrices. Training on semantically diverse style pairs encourages the predictor to preserve appearance cues while suppressing reference-content copying. Experiments on Z-Image, FLUX.2, and Hidream-O1 show that i2L improves style fidelity, prompt alignment, and perceptual quality over existing baselines. Because i2L produces explicit LoRA weights, it also supports asymmetric classifier-free guidance, multi-reference style fusion, and composition with controllable-generation modules.

Related papers

• AnyStyle: A Single LoRA is Sufficient for Image-Guided Style Transfer [2.574354224873255]
  We propose AnyStyle, a streamlined framework for image-guided style transfer.<n>The framework adopts a unified single-adapter paradigm for coherent style capture from the style image.<n>Our method delivers competitive quantitative performance and significantly improved perceptual quality.
  arXiv  Detail & Related papers  (2026-07-06T05:06:38Z)
• LatRef-Diff: Latent and Reference-Guided Diffusion for Facial Attribute Editing and Style Manipulation [78.6161238980415]
  Conditional GANs have shown progress, but they are limited by accuracy issues and training instability.<n>We propose LatRef-Diff, a novel diffusion-based framework that addresses these limitations.<n>We show that LatRef-Diff achieves state-of-the-art performance in both qualitative and quantitative evaluations.
  arXiv  Detail & Related papers  (2026-04-23T04:47:40Z)
• DRC: Enhancing Personalized Image Generation via Disentangled Representation Composition [69.10628479553709]
  We introduce DRC, a novel personalized image generation framework that enhances Large Multimodal Models (LMMs)<n> DRC explicitly extracts user style preferences and semantic intentions from history images and the reference image, respectively.<n>It involves two critical learning stages: 1) Disentanglement learning, which employs a dual-tower disentangler to explicitly separate style and semantic features, optimized via a reconstruction-driven paradigm with difficulty-aware importance sampling; and 2) Personalized modeling, which applies semantic-preserving augmentations to effectively adapt the disentangled representations for robust personalized generation.
  arXiv  Detail & Related papers  (2025-04-24T08:10:10Z)
• LoRA.rar: Learning to Merge LoRAs via Hypernetworks for Subject-Style Conditioned Image Generation [28.098287135605364]
  We introduce LoRA$.$rar, a method that improves image quality and achieves a remarkable speedup of over $4000times$ in the merging process.<n>Our method significantly outperforms the current state of the art in both content and style fidelity, as validated by MLLM assessments and human evaluations.
  arXiv  Detail & Related papers  (2024-12-06T16:04:56Z)
• LoRA of Change: Learning to Generate LoRA for the Editing Instruction from A Single Before-After Image Pair [116.48684498656871]
  We propose the LoRA of Change (LoC) framework for image editing with visual instructions, i.e., before-after image pairs.<n>We learn an instruction-specific LoRA to encode the "change" in a before-after image pair, enhancing the interpretability and reusability of our model.<n>Our model produces high-quality images that align with user intent and support a broad spectrum of real-world visual instructions.
  arXiv  Detail & Related papers  (2024-11-28T13:55:06Z)
• ArtWeaver: Advanced Dynamic Style Integration via Diffusion Model [73.95608242322949]
  Stylized Text-to-Image Generation (STIG) aims to generate images from text prompts and style reference images. We present ArtWeaver, a novel framework that leverages pretrained Stable Diffusion to address challenges such as misinterpreted styles and inconsistent semantics.
  arXiv  Detail & Related papers  (2024-05-24T07:19:40Z)
• Implicit Style-Content Separation using B-LoRA [61.664293840163865]
  We introduce B-LoRA, a method that implicitly separate the style and content components of a single image. By analyzing the architecture of SDXL combined with LoRA, we find that jointly learning the LoRA weights of two specific blocks achieves style-content separation.
  arXiv  Detail & Related papers  (2024-03-21T17:20:21Z)
• Latents2Semantics: Leveraging the Latent Space of Generative Models for Localized Style Manipulation of Face Images [25.82631308991067]
  We introduce the Latents2Semantics Autoencoder (L2SAE), a Generative Autoencoder model that facilitates localized editing of style attributes of several Regions of Interest in face images. The L2SAE learns separate latent representations for encoded images' structure and style information, allowing for structure-preserving style editing of the chosen ROIs. We provide qualitative and quantitative results for the same over multiple applications, such as selective style editing and swapping using test images sampled from several datasets.
  arXiv  Detail & Related papers  (2023-12-22T20:06:53Z)
• StyleAdapter: A Unified Stylized Image Generation Model [97.24936247688824]
  StyleAdapter is a unified stylized image generation model capable of producing a variety of stylized images. It can be integrated with existing controllable synthesis methods, such as T2I-adapter and ControlNet.
  arXiv  Detail & Related papers  (2023-09-04T19:16:46Z)

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.