https://github.com/tamarott/SinGAN
공식 코드SinGAN: Learning a Generative Model from a Single Natural Image
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/tan5o/anime2clothing
공식 코드Anime-to-Real Clothing: Cosplay Costume Generation via Image-to-Image Translation
https://github.com/tang-bd/fuse-dit
공식 코드https://github.com/tanlei0/costg
공식 코드https://github.com/tanvir-utexas/adave
공식 코드Ada-VE: Training-Free Consistent Video Editing Using Adaptive Motion Prior
https://github.com/taowangzj/lldiffusion
공식 코드https://github.com/taozh2017/HiNet
공식 코드Hi-Net: Hybrid-fusion Network for Multi-modal MR Image Synthesis
https://github.com/tau-yihouxiang/X-Ray
공식 코드https://github.com/taufikxu/MOG-ASR
공식 코드Multi-objects Generation with Amortized Structural Regularization
https://github.com/taufikxu/Triple-GAN
공식 코드https://github.com/tavihalperin/AV-sync
공식 코드https://github.com/taylorjocelyn/d2-dpm
공식 코드D$^2$-DPM: Dual Denoising for Quantized Diffusion Probabilistic Models
https://github.com/tchuanm/iterinv
공식 코드https://github.com/tcl9876/Denoising_Student
공식 코드Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed
https://github.com/tdchaitanya/MMTOD
공식 코드Borrow from Anywhere: Pseudo Multi-modal Object Detection in Thermal Imagery
https://github.com/tear-kitty/moedit
공식 코드MoEdit: On Learning Quantity Perception for Multi-object Image Editing
https://github.com/technion-cs-nlp/refact
공식 코드ReFACT: Updating Text-to-Image Models by Editing the Text Encoder
https://github.com/tedyhabtegebrial/gvsnet
공식 코드Generative View Synthesis: From Single-view Semantics to Novel-view Images
https://github.com/tencent-ailab/PCDMs
공식 코드Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion Models
https://github.com/tencent-ailab/bddm
공식 코드BDDM: Bilateral Denoising Diffusion Models for Fast and High-Quality Speech Synthesis
https://github.com/tencent-ailab/frequency_aug_vae_moesr
공식 코드https://github.com/tencent/flashvdm
공식 코드https://github.com/tencent/hunyuandit
공식 코드https://github.com/tencent/instantcharacter
공식 코드InstantCharacter: Personalize Any Characters with a Scalable Diffusion Transformer Framework
https://github.com/tencentarc/animegamer
공식 코드AnimeGamer: Infinite Anime Life Simulation with Next Game State Prediction
https://github.com/tencentarc/brushnet
공식 코드BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion
https://github.com/tencentarc/masactrl
공식 코드MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing
https://github.com/tencentarc/seed-story
공식 코드SEED-Story: Multimodal Long Story Generation with Large Language Model
https://github.com/tencentarc/seed-voken
공식 코드Open-MAGVIT2: An Open-Source Project Toward Democratizing Auto-regressive Visual Generation
https://github.com/tencentarc/t2i-adapter
공식 코드https://github.com/tengteng95/Pose-Transfer
공식 코드Progressive Pose Attention Transfer for Person Image Generation
https://github.com/tensorflow/community
공식 코드https://github.com/terarachang/ACCV_TinyGAN
공식 코드https://github.com/tetrzim/diffusion-human-feedback
공식 코드Censored Sampling of Diffusion Models Using 3 Minutes of Human Feedback
https://github.com/tetsuyaodaka/steerablepyramid
공식 코드https://github.com/tfonta/semantic-vae
공식 코드Automatic Generation of Semantic Parts for Face Image Synthesis
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.