{"list":"other","total":66,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2102.09672","title":"Improved Denoising Diffusion Probabilistic Models","created":"2021-02-18","cited_by_count":3761},{"id":"2112.10741","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","created":"2021-12-20","cited_by_count":3614},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"2208.12242","title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation","created":"2022-08-25","cited_by_count":3300},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"2208.01618","title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","created":"2022-08-02","cited_by_count":2245},{"id":"2108.01073","title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations","created":"2021-08-02","cited_by_count":1937},{"id":"2308.06721","title":"IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models","created":"2023-08-13","cited_by_count":1464},{"id":"2302.08453","title":"T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models","created":"2023-02-16","cited_by_count":1351},{"id":"1801.01401","title":"Demystifying MMD GANs","created":"2018-01-04","cited_by_count":1293},{"id":"2211.09794","title":"Null-text Inversion for Editing Real Images using Guided Diffusion Models","created":"2022-11-17","cited_by_count":1179},{"id":"1710.03740","title":"Mixed Precision Training","created":"2017-10-10","cited_by_count":1156},{"id":"2212.04488","title":"Multi-Concept Customization of Text-to-Image Diffusion","created":"2022-12-08","cited_by_count":1106},{"id":"2211.01324","title":"eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers","created":"2022-11-02","cited_by_count":931},{"id":"2109.01903","title":"Robust fine-tuning of zero-shot models","created":"2021-09-04","cited_by_count":797},{"id":"2109.07161","title":"Resolution-robust Large Mask Inpainting with Fourier Convolutions","created":"2021-09-15","cited_by_count":738},{"id":"1711.10485","title":"AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks","created":"2017-11-28","cited_by_count":664},{"id":"2108.02938","title":"ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models","created":"2021-08-06","cited_by_count":635},{"id":"1904.01310","title":"DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis","created":"2019-04-02","cited_by_count":308},{"id":"2103.16874","title":"VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalization","created":"2021-03-31","cited_by_count":287},{"id":"1711.08447","title":"VITON: An Image-based Virtual Try-on Network","created":"2017-11-22","cited_by_count":286},{"id":"2101.04702","title":"Cross-Modal Contrastive Learning for Text-to-Image Generation","created":"2021-01-12","cited_by_count":259},{"id":"2303.09522","title":"P+: Extended Textual Conditioning in Text-to-Image Generation","created":"2023-03-16","cited_by_count":242},{"id":"2203.15270","title":"MAT: Mask-Aware Transformer for Large Hole Image Inpainting","created":"2022-03-29","cited_by_count":218},{"id":"2211.14305","title":"SpaText: Spatio-Textual Representation for Controllable Image Generation","created":"2022-11-25","cited_by_count":217},{"id":"1706.08500","title":"GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium","created":"2017-06-26","cited_by_count":213},{"id":"1807.07688","title":"Toward Characteristic-Preserving Image-based Virtual Try-On Network","created":"2018-07-20","cited_by_count":192},{"id":"2211.13752","title":"Sketch-Guided Text-to-Image Diffusion Models","created":"2022-11-24","cited_by_count":180},{"id":"2303.15247","title":"Zero-Shot Composed Image Retrieval with Textual Inversion","created":"2023-03-27","cited_by_count":176},{"id":"2108.07009","title":"Pixel Difference Networks for Efficient Edge Detection","created":"2021-08-16","cited_by_count":168},{"id":"2008.05865","title":"DF-GAN: A Simple and Effective Baseline for Text-to-Image Synthesis","created":"2020-08-13","cited_by_count":162},{"id":"2204.08532","title":"Dress Code: High-Resolution Multi-Category Virtual Try-On","created":"2022-04-18","cited_by_count":162},{"id":"2205.12952","title":"Pretraining is All You Need for Image-to-Image Translation","created":"2022-05-25","cited_by_count":160},{"id":"2003.05863","title":"Towards Photo-Realistic Virtual Try-On by Adaptively Generating$\\leftrightarrow$Preserving Image Content","created":"2020-03-12","cited_by_count":149},{"id":"2103.04559","title":"Parser-Free Virtual Try-on via Distilling Appearance Flows","created":"2021-03-08","cited_by_count":143},{"id":"2306.08276","title":"TryOnDiffusion: A Tale of Two UNets","created":"2023-06-14","cited_by_count":141},{"id":"1703.05593","title":"Convolutional neural network architecture for geometric matching","created":"2017-03-16","cited_by_count":138},{"id":"1708.01311","title":"Automatic Spatially-aware Fashion Concept Discovery","created":"2017-08-03","cited_by_count":134},{"id":"2007.02721","title":"Do Not Mask What You Do Not Need to Mask: a Parser-Free Virtual Try-On","created":"2020-07-03","cited_by_count":77},{"id":"2103.02440","title":"OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association","created":"2021-03-03","cited_by_count":55},{"id":"1710.07346","title":"Be Your Own Prada: Fashion Synthesis with Structural Coherence","created":"2017-10-19","cited_by_count":49},{"id":"2208.12675","title":"Adaptively-Realistic Image Generation from Stroke and Sketch with Diffusion Model","created":"2022-08-26","cited_by_count":39},{"id":"2303.08767","title":"Highly Personalized Text Embedding for Image Manipulation by Stable Diffusion","created":"2023-03-15","cited_by_count":39},{"id":"2211.17115","title":"Multiresolution Textual Inversion","created":"2022-11-30","cited_by_count":34},{"id":"2205.15996","title":"Text2Human: Text-Driven Controllable Human Image Generation","created":"2022-05-31","cited_by_count":31},{"id":"2212.04437","title":"C-VTON: Context-Driven Image-Based Virtual Try-On Network","created":"2022-12-08","cited_by_count":29},{"id":"1902.03646","title":"Context-Aware Visual Compatibility Prediction","created":"2019-02-10","cited_by_count":26},{"id":"1712.02662","title":"Creating Capsule Wardrobes from Fashion Images","created":"2017-12-07","cited_by_count":24},{"id":"2204.04812","title":"OutfitTransformer: Learning Outfit Representations for Fashion Recommendation","created":"2022-04-11","cited_by_count":24},{"id":"2301.02110","title":"FICE: Text-Conditioned Fashion Image Editing With Guided GAN Inversion","created":"2023-01-05","cited_by_count":21},{"id":"2309.05551","title":"OpenFashionCLIP: Vision-and-Language Contrastive Learning with Open-Source Fashion Data","created":"2023-09-11","cited_by_count":9},{"id":"2104.02061","title":"Query2Prod2Vec Grounded Word Embeddings for eCommerce","created":"2021-04-02","cited_by_count":8}],"next_cursor":null}