paper-with-me

홈 › Papers

Enhancing AI Face Realism: Cost-Efficient Quality Improvement in Distilled Diffusion Models with a Fully Synthetic Dataset

2025-05-04 · Jakub Wasala, Bartlomiej Wrzalski, Kornelia Noculak, Yuliia Tarasenko, Oliwer Krupa, Jan Kocon, Grzegorz Chodak

This study presents a novel approach to enhance the cost-to-quality ratio of image generation with diffusion models. We hypothesize that differences between distilled (e.g. FLUX.1-schnell) and baseline (e.g. FLUX.1-dev) models are consistent and, therefore, learnable within a specialized domain, like portrait generation. We generate a synthetic paired dataset and train a fast image-to-image translation head. Using two sets of low- and high-quality synthetic images, our model is trained to refine the output of a distilled generator (e.g., FLUX.1-schnell) to a level comparable to a baseline model like FLUX.1-dev, which is more computationally intensive. Our results show that the pipeline, which combines a distilled version of a large generative model with our enhancement layer, delivers similar photorealistic portraits to the baseline version with up to an 82% decrease in computational cost compared to FLUX.1-dev. This study demonstrates the potential for improving the efficiency of AI solutions involving large-scale image generation.

📄 PDF Abstract BibTeX arXiv:2505.02255

Code (0)

등록된 구현이 없습니다.

Tasks

Image GenerationImage-to-Image Translation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Your Data Manifold is Secretly a Reward Model: Shell-LCC for Text-to-Video Generation

2026-06-29 · Shihao Zhang, Yuguang Yan, Junzhe Zhang, Wei Zhao 외 arxiv

Recent text-to-video (T2V) diffusion models rely heavily on auxiliary reward signals (e.g., via reward models or DPO) to align generated content with human aesthetics and improve realism. These signals, however, incur su…

Text-to-Video Generation

REGEN: Real-Time Photorealism Enhancement in Games via a Dual-Stage Generative Network Framework

2025-08-23 · Stefanos Pasios, Nikos Nikolaidis arxiv

Photorealism is an important aspect of modern video games since it can shape player experience and impact immersion, narrative engagement, and visual fidelity. To achieve photorealism, beyond traditional rendering pipeli…

Image-to-Image Translation

Quality-Driven Selective Mutation for Deep Learning

2026-04-24 · Zaheed Ahmed, Emmanuel Charleson Dapaah, Philip Makedonski, Jens Grabowski arxiv

Mutants support testing and debugging in two roles: (i) as test goals and (ii) as substitutes for real faults. Hard-to-kill mutants provide better guidance for test improvement, while realism is essential when mutants ar…

Enhancing Photorealism Enhancement

2021-05-10 · Stephan R. Richter, Hassan Abu Alhaija, Vladlen Koltun

We present an approach to enhancing the realism of synthetic images. The images are enhanced by a convolutional network that leverages intermediate representations produced by conventional rendering pipelines. The networ…

Image-to-Image TranslationTranslation

Digi2Real: Bridging the Realism Gap in Synthetic Data Face Recognition via Foundation Models

2024-11-04 · Anjith George, Sebastien Marcel

The accuracy of face recognition systems has improved significantly in the past few years, thanks to the large amount of data collected and advancements in neural network architectures. However, these large-scale dataset…

Face Recognition