https://github.com/luosiallen/latent-consistency-model
공식 코드Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference
Papers with Code 아카이브
Image Generation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 23
- 평가표
- 93
- 보존된 평가 기록
- 870
Image Generation (synthesis) is the task of generating new images from an existing dataset.
- Unconditional generation refers to generating samples unconditionally from the dataset, i.e. $p(y)$
- Conditional image generation (subtask) refers to generating samples conditionally from the dataset, based on a label, i.e. $p(y|x)$.
In this section, you can find state-of-the-art leaderboards for unconditional generation. For conditional generation, and other types of image generations, refer to the subtasks.
<span style="color:grey; opacity: 0.6">( Image credit: StyleGAN )</span>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/lupalab/ACFlow
공식 코드https://github.com/luping-liu/PNDM
공식 코드https://github.com/luping-liu/detector-guidance
공식 코드https://github.com/lutao2021/BrightDreamer
공식 코드BrightDreamer: Generic 3D Gaussian Generative Framework for Fast Text-to-3D Synthesis
https://github.com/luv91/vqgan_project
공식 코드https://github.com/luyvlei/BiSMAPs
공식 코드https://github.com/lxa9867/ControlVAR
공식 코드ControlVAR: Exploring Controllable Visual Autoregressive Modeling
https://github.com/lxa9867/imagefolder
공식 코드ImageFolder: Autoregressive Image Generation with Folded Tokens
https://github.com/lxasqjc/mcpl
공식 코드https://github.com/lxbuaa/urn
공식 코드Exposing Image Splicing Traces in Scientific Publications via Uncertainty-guided Refinement
https://github.com/ly403/emrdm
공식 코드https://github.com/lyan62/data-curation
공식 코드https://github.com/lychenyoko/content-aware-gan-compression
공식 코드https://github.com/lydialy8/openset_attribution_synthetic_images
공식 코드A Siamese-based Verification System for Open-set Architecture Attribution of Synthetic Images
https://github.com/lyhkevin/mt-net
공식 코드Multi-scale Transformer Network with Edge-aware Pre-training for Cross-Modality MR Image Synthesis
https://github.com/lyhkevin/slmt-net
공식 코드Multi-scale Transformer Network with Edge-aware Pre-training for Cross-Modality MR Image Synthesis
https://github.com/lyndonzheng/Pluralistic-Inpainting
공식 코드https://github.com/lyndonzheng/TFill
공식 코드Bridging Global Context Interactions for High-Fidelity Image Completion
https://github.com/lyupang/crossinitialization
공식 코드Cross Initialization for Personalized Text-to-Image Generation
https://github.com/lzhxmu/accdiffusion
공식 코드AccDiffusion: An Accurate Method for Higher-Resolution Image Generation
https://github.com/lzhxmu/accdiffusion_v2
공식 코드AccDiffusion v2: Towards More Accurate Higher-Resolution Diffusion Extrapolation
https://github.com/m-3lab/fedmed-gan
공식 코드FedMed-GAN: Federated Domain Translation on Unsupervised Cross-Modality Brain Image Synthesis
https://github.com/m-e-agi-lab/muddit
공식 코드Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model
https://github.com/m3dv/lefusion
공식 코드LeFusion: Controllable Pathology Synthesis via Lesion-Focused Diffusion Models
https://github.com/m4xim4l/dig-in
공식 코드https://github.com/ma-labo/promptcharm
공식 코드PromptCharm: Text-to-Image Generation through Multi-modal Prompting and Refinement
https://github.com/machinevision-seoultech/evci
공식 코드Image-to-Image Translation-based Data Augmentation for Robust EV Charging Inlet Detection
https://github.com/maelic/vg_curated
공식 코드Fine-Grained is Too Coarse: A Novel Data-Centric Approach for Efficient Scene Graph Generation
https://github.com/magdalena-wysocki/ultra-nerf
공식 코드https://github.com/magic-research/magic-boost
공식 코드Magic-Boost: Boost 3D Generation with Multi-View Conditioned Diffusion
https://github.com/magic-research/vector_quantization
공식 코드Image Understanding Makes for A Good Tokenizer for Image Generation
https://github.com/magiccircuit/enhance-finegrained
공식 코드https://github.com/mahdi-darvish/gans-augmented-pet-classifier
공식 코드https://github.com/mahfuzmohammad/brainomaly
공식 코드https://github.com/mahfuzmohammad/healthygan
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.