{"list":"other","total":61,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631},{"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":"2508.02324","title":"Qwen-Image Technical Report","created":"2025-08-04","cited_by_count":1044},{"id":"2506.15742","title":"FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space","created":"2025-06-17","cited_by_count":1006},{"id":"2304.08465","title":"MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing","created":"2023-04-17","cited_by_count":727},{"id":"2311.17117","title":"Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation","created":"2023-11-28","cited_by_count":688},{"id":"2303.13439","title":"Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators","created":"2023-03-23","cited_by_count":670},{"id":"2202.09368","title":"Mixture-of-Experts with Expert Choice Routing","created":"2022-02-18","cited_by_count":623},{"id":"1708.03985","title":"AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wild","created":"2017-08-14","cited_by_count":492},{"id":"2305.16322","title":"Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models","created":"2023-05-25","cited_by_count":359},{"id":"2008.02401","title":"StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flows","created":"2020-08-06","cited_by_count":349},{"id":"2011.12799","title":"StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation","created":"2020-11-25","cited_by_count":332},{"id":"2311.16498","title":"MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model","created":"2023-11-27","cited_by_count":330},{"id":"2207.12393","title":"CelebV-HQ: A Large-Scale Video Facial Attributes Dataset","created":"2022-07-25","cited_by_count":250},{"id":"2411.15738","title":"AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea","created":"2024-11-24","cited_by_count":241},{"id":"2407.03168","title":"LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control","created":"2024-07-03","cited_by_count":206},{"id":"2407.08136","title":"EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditions","created":"2024-07-11","cited_by_count":196},{"id":"2403.17694","title":"AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation","created":"2024-03-26","cited_by_count":194},{"id":"2205.03409","title":"VFHQ: A High-Quality Dataset and Benchmark for Video Face Super-Resolution","created":"2022-05-06","cited_by_count":176},{"id":"2406.01900","title":"Follow-Your-Emoji: Fine-Controllable and Expressive Freestyle Portrait Animation","created":"2024-06-04","cited_by_count":174},{"id":"2004.00060","title":"HOPE-Net: A Graph-based Model for Hand-Object Pose Estimation","created":"2020-03-31","cited_by_count":112},{"id":"2403.11641","title":"Arc2Face: A Foundation Model for ID-Consistent Human Faces","created":"2024-03-18","cited_by_count":101},{"id":"2112.05142","title":"HairCLIP: Design Your Hair by Text and Reference Image","created":"2021-12-09","cited_by_count":80},{"id":"2211.14068","title":"Fine-Grained Face Swapping via Regional GAN Inversion","created":"2022-11-25","cited_by_count":67},{"id":"2405.12970","title":"Face Adapter for Pre-Trained Diffusion Models with Fine-Grained ID and Attribute Control","created":"2024-05-21","cited_by_count":67},{"id":"2303.02936","title":"UniHCP: A Unified Model for Human-Centric Perceptions","created":"2023-03-06","cited_by_count":59},{"id":"2503.18860","title":"HunyuanPortrait: Implicit Condition Control for Enhanced Portrait Animation","created":"2025-03-24","cited_by_count":59},{"id":"2206.04674","title":"Uni-Perceiver-MoE: Learning Sparse Generalist Models with Conditional MoEs","created":"2022-06-09","cited_by_count":58},{"id":"2311.15230","title":"GAIA: Zero-shot Talking Avatar Generation","created":"2023-11-26","cited_by_count":43},{"id":"2510.06679","title":"DreamOmni2: Multimodal Instruction-based Editing and Generation","created":"2025-10-08","cited_by_count":38},{"id":"2409.07269","title":"Realistic and Efficient Face Swapping: A Unified Approach with Diffusion Models","created":"2024-09-11","cited_by_count":36},{"id":"2407.14078","title":"Stable-Hair: Real-World Hair Transfer via Diffusion Model","created":"2024-07-19","cited_by_count":35},{"id":"2502.10841","title":"SkyReels-A1: Expressive Portrait Animation in Video Diffusion Transformers","created":"2025-02-15","cited_by_count":33},{"id":"2405.20851","title":"MegActor: Harness the Power of Raw Video for Vivid Portrait Animation","created":"2024-05-31","cited_by_count":28},{"id":"2204.13100","title":"Few-Shot Head Swapping in the Wild","created":"2022-04-27","cited_by_count":21},{"id":"2406.18958","title":"AnyControl: Create Your Artwork with Versatile Control on Text-to-Image Generation","created":"2024-06-27","cited_by_count":20},{"id":"2409.17508","title":"Uni-Med: A Unified Medical Generalist Foundation Model For Multi-Task Learning Via Connector-MoE","created":"2024-09-26","cited_by_count":19},{"id":"2310.10651","title":"HairCLIPv2: Unifying Hair Editing via Proxy Feature Blending","created":"2023-10-16","cited_by_count":17},{"id":"2507.02691","title":"CanonSwap: High-Fidelity and Consistent Video Face Swapping via Canonical Space Modulation","created":"2025-07-03","cited_by_count":16},{"id":"2109.03672","title":"On Recognizing Occluded Faces in the Wild","created":"2021-09-08","cited_by_count":15},{"id":"2212.06458","title":"HS-Diffusion: Semantic-Mixing Diffusion for Head Swapping","created":"2022-12-13","cited_by_count":13},{"id":"2403.09500","title":"Faceptor: A Generalist Model for Face Perception","created":"2024-03-14","cited_by_count":13},{"id":"2404.01094","title":"HairFastGAN: Realistic and Robust Hair Transfer with a Fast Encoder-Based Approach","created":"2024-04-01","cited_by_count":10},{"id":"2504.14509","title":"DreamID: High-Fidelity and Fast diffusion-based Face Swapping via Triplet ID Group Learning","created":"2025-04-20","cited_by_count":10},{"id":"2411.18293","title":"HiFiVFS: High Fidelity Video Face Swapping","created":"2024-11-27","cited_by_count":9},{"id":"2408.16450","title":"What to Preserve and What to Transfer: Faithful, Identity-Preserving Diffusion-based Hairstyle Transfer","created":"2024-08-29","cited_by_count":8},{"id":"2312.17205","title":"EFHQ: Multi-purpose ExtremePose-Face-HQ dataset","created":"2023-12-28","cited_by_count":6},{"id":"2502.18417","title":"GHOST 2.0: generative high-fidelity one shot transfer of heads","created":"2025-02-25","cited_by_count":5},{"id":"2503.22179","title":"High-Fidelity Diffusion Face Swapping with ID-Constrained Facial Conditioning","created":"2025-03-28","cited_by_count":5},{"id":"2402.07370","title":"SelfSwapper: Self-Supervised Face Swapping via Shape Agnostic Masked AutoEncoder","created":"2024-02-12","cited_by_count":4},{"id":"2412.01254","title":"EmojiDiff: Advanced Facial Expression Control with High Identity Preservation in Portrait Generation","created":"2024-12-02","cited_by_count":4},{"id":"2503.00861","title":"Zero-Shot Head Swapping in Real-World Scenarios","created":"2025-03-02","cited_by_count":4},{"id":"2504.21497","title":"MagicPortrait: Temporally Consistent Face Reenactment with 3D Geometric Guidance","created":"2025-04-30","cited_by_count":4},{"id":"2502.02465","title":"Towards Consistent and Controllable Image Synthesis for Face Editing","created":"2025-02-04","cited_by_count":3},{"id":"2410.22771","title":"FuseAnyPart: Diffusion-Driven Facial Parts Swapping via Multiple Reference Images","created":"2024-10-30","cited_by_count":2}],"next_cursor":null}