Tagged articles
style transfer
27 articles · Page 1 of 1
The paper identifies instability and identity distortion in existing portrait relighting approaches, proposes the Consistent Feature Transport (CFT) framework that models lighting as a feature‑transfer problem within a Rectified Flow diffusion model, and demonstrates superior quantitative and qualitative results on a large‑scale relighting dataset as well as improved style‑transfer performance.
Computer VisionRectified Flowconsistent feature transport
0 likes · 9 min read

The article presents AutoFigure-Edit, an open‑source AI system that turns long‑form scientific text into fully editable SVG figures, solves the uneditable‑image problem of existing AIGC tools, and demonstrates superior performance on the FigureBench benchmark and real‑user studies.
AIAutoFigureSVG
0 likes · 11 min read

This article proposes an ASR‑driven pipeline that creates high‑quality AI‑reply vs. human‑like reply pairs, trains a rewrite model and a reward model, and uses GRPO reinforcement learning to generate natural, helpful, and less AI‑sounding responses in digital‑human live streaming, achieving 92% accuracy and 97% helpfulness while improving user experience.
ASR dataLLMQwen
0 likes · 20 min read

TTT‑Video‑Dit is an open‑source framework that uses test‑time‑training and hierarchical attention to generate coherent 63‑second videos with style‑transfer, dramatically reducing GPU memory requirements so a single RTX 4090 can replace costly H100 clusters, enabling creators and developers to produce long AI videos efficiently.
GPU optimizationTTT-Video-Ditlong video AI
0 likes · 11 min read

Google’s Nano Banana, an advanced multimodal AI model integrated into Gemini, delivers unprecedented role‑consistency and multi‑step editing, and this article walks through fifteen concrete use cases—from virtual try‑on and background swapping to style transfer, product visualisation, educational graphics, and 3D conversion—showcasing how the tool can streamline creative workflows across industries.
AI image generationGeminiGoogle
0 likes · 9 min read

Nano Banana, Google’s internal code name for Gemini 2.5 Flash Image, reshapes AI image creation with ten‑fold speed gains over Photoshop, consistent multi‑step editing, dialogue‑driven image manipulation, style‑transfer capabilities, and a community‑validated reputation earned through blind tests on LMArena, while also exposing typical generative‑AI limits such as text rendering glitches and occasional anatomical errors.
AI image generationGemini 2.5 Flash ImageLMArena
0 likes · 20 min read

The paper introduces Single Trajectory Distillation (STD), a novel training framework that aligns full PF‑ODE trajectories from a fixed noisy state, uses a Trajectory Bank to cut training cost, and adds an Asymmetric Adversarial Loss to markedly improve style consistency and aesthetic quality while accelerating image and video style‑transfer diffusion models.
AI accelerationconsistency modelsdiffusion models
0 likes · 14 min read


AIWalkerMar 5, 2025 · Artificial Intelligence
The paper introduces a novel attention‑distillation loss and a guided‑sampling scheme that together enable diffusion models to faithfully transfer visual features from reference images, dramatically speeding synthesis and surpassing prior plug‑and‑play attention methods across style transfer, text‑to‑image generation, and texture synthesis tasks.
AI researchImage Generationattention distillation
0 likes · 15 min read


AIWalkerJan 13, 2025 · Artificial Intelligence
ArtCrafter introduces a novel text‑image style transfer framework that leverages attention‑based style extraction, text‑image alignment enhancement, and explicit modulation to achieve controllable, diverse, and high‑fidelity visual results, outperforming existing methods in both qualitative and quantitative evaluations.
Attention Mechanismdiffusion modelsmultimodal alignment
0 likes · 10 min read

Li Yilin’s AI project blends Peking Opera characters with traditional ink‑wash painting by using PaddleHub for style transfer and PaddleGAN’s First‑Order Motion model for facial motion, then adds music and Wav2Lip lip‑sync, producing videos that modernize Chinese heritage and gauge public cultural awareness.
AIComputer VisionPaddleGAN
0 likes · 9 min read

This article details Baidu APP’s AI Publisher, explaining the research behind its offline and online stylization modes, the complete generation pipelines, core AI technologies such as template creation, face‑merging, large‑model style transfer, custom model training, and showcases the resulting festive visual effects.
AI image generationBaidu AIface merging
0 likes · 10 min read

This article explains how AI‑generated content (AIGC) technologies such as text‑to‑image diffusion models, Lora fine‑tuning, and IP‑Adapter style transfer are applied to interior design, dramatically reducing design time, cutting costs, and enabling personalized, high‑quality visualizations for both consumers and furniture merchants.
AIGCGenerative AIIP-Adapter
0 likes · 9 min read

The article details NetEase Fuxi's research on AI‑Generated Action (AIGA) for game AI bots, covering the shift from AIGC to AIGA, advances in making bots more human‑like and stylized, and the application of RLHF fine‑tuning to bridge objective metrics with subjective player experience.
AIAIGAHuman-like Bots
0 likes · 20 min read

This article introduces neural style transfer, explains its underlying principles using VGG19 feature extraction, content and style loss definitions, and provides a complete PyTorch implementation with code for loading images, extracting features, computing Gram matrices, and optimizing the output image.
Computer VisionPyTorchdeep learning
0 likes · 14 min read

This article introduces ModelScope's community‑released visual models, detailing the categorization of understanding versus editing models, the two‑stage coarse‑to‑fine segmentation pipeline for matting, and four editing applications—style transfer, portrait beautification, skin enhancement, and anime‑style conversion—while also previewing upcoming sky‑replacement and video‑matting models.
AIModelScopeimage segmentation
0 likes · 9 min read

Alibaba’s advertising AI team presents a comprehensive study of four new multimodal copywriting tasks—image overlay text generation, video narration, text style transfer, and detail-page extraction—detailing model architectures, training on billions of images, experimental results, and practical deployment in the “Xiyu” product.
advertising copydetail extractionlarge-scale training
0 likes · 17 min read

This paper proposes SSAN, a novel dual‑stream network that separates content and style features to achieve domain‑generalized face anti‑spoofing, employing adversarial learning for content, contrastive learning for style, and a large‑scale evaluation protocol across twelve public datasets, achieving state‑of‑the‑art performance.
Contrastive LearningSSANdomain generalization
0 likes · 16 min read

Jack Cui presents three recently open‑sourced CVPR 2022 algorithms—DualStyleGAN for high‑resolution portrait style transfer, RQ‑VAE Transformer for improved text‑to‑image generation, and VFD for deep‑fake detection—detailing their functionality, usage options, and providing links to code repositories and demo platforms.
AIGenerative Modelsdeepfake detection
0 likes · 5 min read

This article explores how AI and natural language processing technologies are applied to music lyric creation, covering background challenges, rhyme retrieval methods, advanced language models such as SongNet, decoding strategies, style transfer, and a multi‑level generation platform that aims to streamline professional songwriting.
AI lyric generationSongNetlanguage models
0 likes · 14 min read

This article provides a comprehensive overview of Generative Adversarial Networks, covering their original formulation, training dynamics, loss functions, major variants such as DCGAN and WGAN, and practical implementations for image‑to‑image translation, style transfer, and handwriting font synthesis at Laiye Technology.
Computer VisionGANGenerative Adversarial Networks
0 likes · 28 min read

This article provides an in‑depth overview of Generative Adversarial Networks (GANs), covering their original formulation, major variants such as DCGAN and WGAN, challenges like mode collapse, image‑to‑image translation techniques (cGAN, pix2pix, CycleGAN), and practical handwriting style‑transfer implementations using BicycleGAN and Zi2Zi.
GANGenerative Adversarial Networksimage-to-image translation
0 likes · 27 min read

The Baidu ACL 2020 paper sharing live session recap presents three NLP research papers—on unsupervised style transfer, sentiment‑knowledge‑enhanced pre‑training, and conversational recommendation over multi‑type dialogs—detailing their novel models, methodologies, and key contributions.
ACL 2020NLPconversational recommendation
0 likes · 4 min read

This article introduces AnimeGAN, a lightweight GAN that converts real photos into Japanese anime‑style illustrations, explains its architecture, loss functions, model size advantages, and provides step‑by‑step instructions with code for setting up, training, and testing the TensorFlow implementation.
AnimeGANGANTensorFlow
0 likes · 8 min read

This article explains how to build a neural style‑transfer application by preprocessing input and style images, loading a pretrained VGG16 network, defining content, style, and total‑variation losses, and finally optimizing the output image using the L‑BFGS algorithm.
CNNL-BFGSVGG16
0 likes · 5 min read

Learn how to turn an AI robot into a gallery‑ready painter by setting up Docker and nvidia‑docker, installing GPU drivers, and running a neural‑style transfer pipeline that blends photographs with Monet’s brushstrokes, producing high‑quality artwork in minutes.
AI artDockerGPU
0 likes · 8 min read

This article details how Alibaba’s AliPlayStudio combines advanced computer‑vision algorithms—such as human semantic segmentation, gesture and pose detection, controllable style transfer, and face‑fusion—optimised for low‑power mobile and embedded devices, to deliver engaging real‑time video interactions across online and offline marketing scenarios.
face fusiongesture recognitionmobile AI
0 likes · 17 min read

This paper introduces a style‑adversarial autoencoder that separates content and style latent variables, uses a multi‑class discriminator, and demonstrates superior image generation and data augmentation across MNIST, face, and text datasets tasks.
Generative Adversarial Networksautoencodersdeep learning
0 likes · 15 min read
