HyperAI
Command Palette
Search for a command to run...
Image Generation
Creating realistic or artistic images from scratch, often conditioned on text descriptions or other modalities.
Leaderboard
100 models total
Benchmarks
ImageNet
CIFAR-10
EDM-G++ (conditional)
MS-COCO
ImageNet 256×256
ImageNet-1K
ImageNet 256x256
DiGIT
ImageNet-256
FFHQ
StyleGAN2
Draw bench
COCO-2014
GTAV-to-Cityscapes Labels
HRDA + CLUDA
ImageNet 512x512
MAGVIT-v2
ImageNet 64x64
IC-GAN + DA
CelebA-HQ
StarGAN v2
COCO
COCO-2017
Celeb-A
FFHQ 256 x 256
CIPS-3D
CIFAR10
MJHQ-30K
ImageNet 128x128
EluCD_DDPM
STL-10
LSUN-Bedroom
Parti-Prompts
MNIST
Transition Matrix
CelebA 64x64
HDCGAN
MS COCO-2017
COCO-30K
ImageNet-256×256
MS COCO-2014
DreamBench
VBench
VITON-HD
LSUN Bedroom 256 x 256
Projected GAN
LSUN Churches 256 x 256
MS COCO-30k
ImageNet 512×512
ImageNet 64×64
MJHQ
CIFAR-100
DLSM
COCO-5K
LSUN-Church
Objaverse
FFHQ-128
AFHQ
Pick-a-Pic
ImageNet-512
DreamBooth-dataset
ImageNet-64
DreamBooth
FFHQ 1024 x 1024
StyleGAN2
LAION-5B
Stanford-Cars
Projected GANs
AFHQ-V2
Polarity-StyleGAN3
CelebA-HQ 256x256
RDM
sDCI
ADE20k
COCO-Stuff
PITI
Dress Code
NegOpt
CelebA-64
LSUN-bedrooms
MS-COCO 2017 validation set
AFHQ-Cat
Vision-aided GAN
HPD v2
FFHQ-U
Alias-Free-R
COCO Val2014
COCO 2017 val
LCDG
ImageNet 32x32
i-DODE
ImageNet-512×512
Parti-prompt
PubLayNet
Rico
Toys4K
BarbieCore
COCO Dataset
COCO-10k
custom facial personalization dataset (50 identities)
Cyberpunk
ElementFire
Expedition
Hornify
HPD
HPS v2
LSUN-Churches
MultiGen-20M
Stanford-Dogs
Projected GAN
3D-FRONT
CC3M
COCO-2017 5K
COCO-2017 validation set
Fashion-MNIST
GLF+perceptual loss (ours)
FLORA
ArtBench
Attend-and-Excite Benchmarks
CelebA-HQ 1024x1024
StyleSwin
COCO validation set
CVUSA
UniGAN
DiffusionDB
FFHQ-256
Flux.1-dev
Food
Fundus Fluorescein Angiogram Photographs & Colour Fundus Images of Diabetic Patients
VTGAN
GSO
HPS benchmark
LayoutSAM-Eval
MARIO-Eval
Matterport3D
AFHQ-dog
Vision-aided GAN
Age-DB
Arc2Face
CelebA 256x256
StyleSwin
COCO Captions 2014
Crello
CVTG-2K
ImageNet-32
LAION
MJHQ-5K
MS-COCO 2014 validation
MSCOCO-2017 5K
T2I-CompBench
ArtBench-10
StyleGAN2 + ADA
CelebA-HQ 256
CelebA-HQ 128x128
U-Net GAN
DA-Bench
DIV2K
GenEval
LSUN-Cat
LSUN Cat 256 x 256
Projected GAN
PIP
Replica
ViCo
VizDoom
GSN
AMOS
Anime character pose dataset
Bedroom
CC12M
CelebA-32
Dayton (256×256) - aerial-to-ground
DreamBooth benchmark
G-Objaverse
I2P
MSTAR
Oxford Flowers
Pick-a-Pic test set
SUN 360
Syn2Real-C
DADA
Visual Genome 64x64
MIGS
Wiki-Art dataset
A&E Dataset
AnyText-benchmark
BTCV
Caltech
CelebAMask-HQ
Sem2NeRF
CirrMRI600+
COCO-MIG
MIGC
COCO-Stuff 128x128
CAL2IM
COCO-Stuff 256x256
COCO-Stuff 64x64
Custom Concept 101
Dayton (64×64) - aerial-to-ground
SelectionGAN
Dayton (64x64) - ground-to-aerial
UniGAN
FFHQ 256×256
FFHQ-64
GoogleEarth
Hunyuan-Video
ImageNette
LAION-COCO
LSUN Tower
MS-COCO 2017 validation split
NSD
PieBench
Places50
SinDiffusion
Pororo
AR-LDM
Simple-animals
Stable-Diffusion-Prompt
StyleDrop style set
T2I-Dataset
unknown
V-COCO
Visual Genome 128x128
LayoutDiffusion
VoxCeleb2 - 1-shot learning
Fast Bi-layer Avatars (medium size)
ACDC
Aesthetic-Eval@4096
AFHQ-64
AFHQ-v2 64x64
AFHQ Wild
Vision-aided GAN
AI-generated Images
ARKITSCENES
GAUDI
Canny
Cat→Dog
CelebA 128x128
U-Net GAN
CelebA-HQ + FFHQ
CIFAR-10 32x32
COCO validation dataset
CUB 128 x 128
Projected GAN
CUB-Birds
Dayton (256×256) - ground-to-aerial
DDPO animal prompts
Depth
DreamFusion gallery
Edge-to-Handbags
MUNIT
Edge-to-Shoes
Ego2Top
SelectionGAN
Emu-Edit
FaceScrub
FFHQ 64×64
FFHQ 64x64
SiDA-EDM
Human-Art
IAM
ImageNet (512×512)
LAION-Aesthetic-6+
LayoutBench-COCO - Number
LayoutBench-COCO - Combination
IterInpaint
LayoutBench-COCO - Position
LayoutBench-COCO - Size
LIFULL
LSUN
LSUN-Bedroom 256×256
LSUN-Church 256×256
LSUN Horse 256 x 256
StyleGAN2
Male→Female
MaterialMVP
Midjourney-30K
MovieLens Latest Small
MS-Bench
MS-COCO 2014 validation set
Multilingual-Cultural (MC)
nuScenes
OSM-Satellite
Pokemon 256x256
StyleGAN-XL
Poster-Benchmark
PRO-teXt
LSDM
SAR-Airplane
ScanNet
Sketchy
Split CIFAR-10
Split Fashion
Split SVHN
Split M-NIST
SVNH-to-MNIST
CyCADA pixel+feat
T$^3$Bench
Textual Inversion dataset
Unsplash-50
Visual Genome 256x256
LayoutDiffusion
VLN-CE
Wild→Dog
Xenium_C1
Xenium_C2
Xenium_P1
30K object-centric images
4SKST
5k evaluation dataset
A3D object pairs
ADE-Indoor
AFHQ-D
AVD
BraTS24
CACD
CAT 256x256
StyleGAN2 + DA + RLC (Ours)
Cats-and-Dogs
CelebA-HQ 64x64
COCO-GAN
CFD-Test
CIFAR-10 (10% data)
DiffAugment-StyleGAN2
CIFAR-10 (20% data)
DiffAugment-StyleGAN2
CIFAR-10-LT
CityScapes
COCO-2014 validation set
COCO-2017-val 30K prompts
COCO-Captions
COCO-val 5K
COCO'14 validation
Concept101
CoPro
Creative Architecture
Creative Birds
Creative Creatures
CVL
DenseLayout
DiffDoctor treating benchmark
DIODE-Outdoor (256 × 256)
DressCode-Upper
EcoMapper dataset
Edges→Handbags (64 × 64)
Edges2Shoes
Emotion
EPFL NIR-VIS
In2I
FFHQ 64 × 64
FFHQ 128 x 128
Anycost GAN
FFHQ 512 x 512
Anycost GAN
FIGR-8
Flintstones-SV
FLUX
Fonts
Food-101
Freiburg Forest Dataset
GenAI Bench
HBE
HED
HICO-DET
Human and Hand Generation (H&H) Dataset
Hyper-Sim
ImageNet-128
ImageNet-64×64
iNat-Seen
iNat-Unseen
internal human image dataset
KADID-10k
KITTI
GaussianCity
L
LAION subset (10k image-text pairs)
LAION-Art
LAVAL Indoor
Lay2Story-Bench
LayoutBench
IterInpaint
LLVIP
Pix2pix
LSUN Bedroom 64 x 64
WGAN-GP + TTUR + Alex-Adam
M3FD
MagicBrush
MAGICK dataset
MetFaces
MetFaces-U
MFNet
MIMIC
ML
MLT benchmark
Model2Model
Model2Street
NABLA
ObjectsRoom
Occupation
OpenSARShip
Part-Mobility
Pick-a-Pic v2
PixArt-XL-2-256-MS
Pokemon 1024x1024
StyleGAN-XL
S
SD-Prompt
SDXL
ShapeStacks
Shop2Model (VITON-HD)
Shop2Street
Sliver07
StyleGAN2 with DiffAugment
Stable Diffusion 3
Stable Diffusion 3.5
Stacked MNIST
VAEBM
stereotype prompts
Street2Street
Style5
test subset (all brands used for training)
Text-to-Image Generation
Unseen brands test set
User Study
VITON
WinoBias
512×2048 panorama
Aesthetic Score
AFHQ-D 256×256
AnE
ArchiMetricsNet
ARTIST-Eval
Babies
BBBC021
BCI
BDD100K-Subsets
MIGS
BindBench
Bird. S
Brodatz
CALTECH-101
CarlaSC
Cars
Cat
CelebA 64×64
CelebA-3DChair
CelebA-CACD
CelebAHQ 256×256
ChestXray14 1024x1024
Church
CIFAR
CIFAR 32×32
CIFAR10 (CS)
CIFAR10 (LS)
Class-Conditional ImageNet 256×256
CLIC
COCO IFG benchmark
COCO-Animals
U-Net GAN
COCO-CN
COCO-WholeBody
COCO2014-30K
Complex-Benchmark
Compo20
Conceptual Captions
Conditional ImageNet 128×128
CosmicMan
CSD-100
CUB
CUB-200-2011
CultureBench
Custom 680-image dataset
Custom benchmark
D-LORD
D.C.Upper
Deep DoF dataset
DeepEyeNet
DeepFashion In-Shop Clothes Retrieval Benchmark
Deformable Subject Set
DMC-120k
DreamBench++
DreamBooth Set
DreamFusion prompts
DressCode dresses
DressCode lower-body
DressCode upper-body
EMU-Edit test set
Existence and Attribute Binding (A&E) Dataset
F-mnist
FANVID
FFHQ (256×256)
FFHQ (64 × 64)
FFHQ 1024×1024
FFHQ 128×128
Flicker30K
Flickr
Flickr-30K
FLIR
FLUX-5K
FSCG-8
Game Asset
GDP-HMM
GeoDE
GOD
Google Scanned Objects (GSO)
GSO
ground terrain
GSO Dataset
HAIG-2.9M
HM3D+MP3D
Home Action Genome
HPDv2 photo+painting prompts
HPS
ICD-Watermark
ICDAR13
ImageNet (64 × 64)
ImageNet (cond.)
ImageNet 128×128
ImageNet-100
ImageNet-LT
StyleGAN2 + NoisyTwins
ImageReward
IMM Face Dataset
in-the-wild
iNaturalist-2019
BigGAN + gSR
Inert-CompBench
Inf3DLayout
InnoComposer-Bench
InstructPix2Pix
InteriorVerse
internal dataset
Kontext-Bench
LAION-5k
LAION-Aesthetics
LAION-Aesthetics V2
LAION-Aesthetics V2 6.5+
LC-Mis
LEVIR-CC
LIGER benchmark
LottieBench
LSUN Bridge
LSUN Bedroom 128 x 128
LadaGAN
LSUN-Bedroom-256
LSUN-Bedrooms 256×256
LSUN Car 512 x 384
StyleGAN2
LSUN-Churches 256×256
MapillaryVistas 2048×2048
Matterport
MIMIC-CXR
MIST
Mix-of-Show dataset
ML-latest
MLCID
MM-Celeba-HQ
MMSVG-Icon
MMSVG-Illustration
MPOM
MS COCO 512x512
MS COCO Dataset
MS-Bench-Random
MS-COCO 2017 captions
MS-COCO 30k validation set
MSCOCO-2014 30K
Multi prompts
multi-subject generation
multilingual benchmark
MVShoes
NeRF4
Occupational Prompts
OmniObject3D
OpenFWI
OpenImages 6K
OpenImages-Test
OxAAA
Oxford 102 Flowers 256 x 256
Projected GAN
Panda
PanNuke
PANORAMA
Pic-a-Pick prompts
PixartEval30K
Pororo-SV
RealFusion15
REQUITE-Prostate
RPLAN
RSICD
S2Looking
SArena-Icon
Scenario 1
Scenario 3
Scribble
AODB (full)
SECOND
Segmentation
SG-FRONT
Shallow DoF dataset
ShapeNet
single-subject generation
SketchyCOCO
SOCOFing
Split-miniImageNet
SSHQ-1.0
standardized image prompt set
Style-Aligned
StyledTextSynth
Subjects200K
SubjectSpatial200K
SUN-397
Sunglasses
SVG-Hub-5M
synthetic human dataset
SynthRAD2023
T2ICompBench-3D
Tag2pix
Test Set
Text-to-3D Generation
text-to-3D sketch prompts
text-to-image
TextGround4M
UCF-101
UFSC
UltraHR-eval4K
UNLEARNCANVAS
Van Gogh
VisDial
VoxCeleb1 - 1-shot learning
Few-shot Adversarial Model
VoxCeleb1 - 32-shot learning
Few-shot Adversarial Model
VoxCeleb1 - 8-shot learning
Few-shot Adversarial Model
VoxCeleb2 - 8-shot learning
CainGAN
Wan2.1 1.3B
WebRPG dataset
WHU-CD
XM12
Zero-shot LAION-5k 1024×1024
100 Artistic Styles
100 Celeb.
100 Styles
100-shot Grumpy
100-shot Obama
100-shot Panda
10K High-Quality Test Set
11k-hands
15 prompt pairs
20-concept dataset
200 prompt and bounding-box pairs
25 concepts
25% ImageNet 128x128
LeCAM + DA
2K benchmark
2k test set
310k synthetic images and caption pairs
32 diverse 3D objects
3D Brain MRIs
3D-SynthPlace
3DFRONT-NC
3DOc-Bench
40 text prompts
4K benchmark
61 text prompts
AbHuman
ACROBAT
ActorBench
ADNI
AdProd-100K
AFHQ_Large_5X
AFHQ-512
AFHQv2 64×64
AgeDB-IT2I-L
AgeDB-IT2I-S
AHP
AI-Generated Prompts
ANHIR
Animal
Animal Faces
Animal-Face
Animation Dataset
Anime
AnyWord-Eval
AP-10K
Artist-created Mesh
Artist-created mesh benchmark
ATLAS
Attend-n-Excite prompts
Attend&Excite
AudioSet-Eval
autoPET 2023
AutoPP1M
AVIID
AVMS
AVT aorta (CT)
BDD100K+NYUv2
Bitmoji dataset
Blender-rendered synthetic dataset
BlindWays
blurred VOC 2012
Boson-night
Bosonplus-day
Bosonplus-night
BP4D
BraTS 2021
BRATS18
Building images
BUSI
CAMELYON-16
CangJie
Canny Edge
CANVAS
car
Carpark
cars
Cars-196
CART
Casia
CASIA-OLHWDB
Cat2Dog(C2D)
Cats
CE+CH
CE+FCE
CE+FT
CE+MT
CelebA (64 × 64)
CelebA_Large
CelebA_Large_5X
CelebA-7
CelebA-HQ 256×256
CelebA-HQ 512x512
WaveDiff
CelebHQ
CelebV-HQ
CESC
chairs
Challenging viewpoints
CHAOS liver (CT)
CHARTIST-30K
ChartQA
ChatGenBench
Chest X-ray 14
Chinese
Chinese benchmark
Chinese cultural dataset
Chinese SVG dataset
ChineseDrawText, DrawTextCreative, TMDBEval500
CHTR-110K
CI+MI
CI+MT
CIFAR-10 (Unconditional)
CIFAR-10 (Conditional)
CIFAR-100-IT2I
CIFAR10 32×32
CIFAR10-INRs
Cityscapes-25K 256x512
SB-GAN
Cityscapes-5K 256x512
SB-GAN
CityVista
CLEVR-SV
Clothing-1M
CM-Fashion
cmc
COAD
COCO 256×256
COCO validation
COCO-1K
COCO
COCO-en
COCO-Layout
COCO-no-person
COCO-Pose
COCO-Position
COCO-UM
COCO-val 1K
COCO-val2017
COCO17-Val
COCO2014 5K validation
COCO2014-10k
COCO2017 validation
code-to-style
collected dataset of 25 identities
Colorization
Colorized MNIST
ColorSVG-100K
CompCars
ComposLoRA
CoNIC
ConsiStory-Human
ConsiStory+
ContraStyles
Controllable Generation
COYO+Midjourney
CTIR
CTP-HD
CUB Bird
CUB-200
Custom
Custom dataset (10 prompts × 5 variations × 6 objects)
Custom dataset of 12 scenarios
Custom Hand Test Set
Custom image generation evaluation dataset
Custom Indoor Scenes
Custom Test Set
Custom test set (800 meshes)
Custom101-StyleDrop
CVACT
cvact-1
Sat2Density
CVC-Clinic DB
CVTG-Style
Danbooru 2021
DAVIS-2017
DAWN
Deblurring
Decathlon heart (MRI)
Decathlon liver (CT)
Deep-Fashion
design websites
Dex-YCB
DF-20M
DF20-Mini
dHCP
DigiFace-IT2I
Dining room
DIODE
DIOR-H
DISFA
DiT-XL/2
Dog
Drag-a-Move
DreamBench Plus
DreamBooth dataset and Custom-Concept101
Dreambooth-StyleDrop
DreamFusion & MVDream prompts
DreamFusion gallery prompts
DreamLayer
Dressing-Pair
DS1
DS2
DTC
E-ReDial
Edges2handbags (64 × 64)
ElementFont
EMNIST-letters
Spiking-Diffusion
emotional prompts dataset
EndoNuke
English benchmark
English user inputs
EPFL
ETH3D
ETTm1
European Art
evaluation data set
ExDark
Face-blurred ImageNet-256
FaceForensics
FacesHQ
FaceX
FastComposer benchmark
FFHQ (1024×1024)
FFHQ & CelebA-HQ
FFHQ 64 × 64 (Unconditional)
FFHQ-100
FFHQ-256×256
FFHQ-512
FFHQ 512 x 512 - 4x upscaling
IDE-3D
FFHQ 64x64 - 4x upscaling
PFGM++
FFHQ-Babies
FFHQ-Sunglasses
FG-TI2I
FID Dataset
FishNet
Flickr-30k-en
Flickr-8k
Flickr-8k-cn
FLIR-ADAS
Flowers
FMC
FontBench
FoundHand-10M
G2A-3
GardenVerse
GBM
General objects
General Personalized Face Generation benchmark
Generative Mesh
GenerativeFont
GenText-Microstruct
Geometries 2000
Gibson
GlyphMM-benchmark
Google Fonts
Google Scanned Object
GPT-1k
GPT-4 generated prompts
GPTEval3D
GQN
Graph200K
Great Lakes Invasives Network (GLIN) fish dataset
Grumpy Cat
GSO T2T benchmark
Hand-Drawn Dataset
Handfit-3K
Haze4K
HCP1200
HCT
HDTF
HED Boundary
HG-FRONT
HiCoPrompt
horse zebra
HP3D
HPS v2 benchmark
HuGe100K
Human
Human customization
Human3.6M
IAM Offline Handwriting Database
ICD-QR
ICD-Text
ICVL
Im2Oil
image-to-3D sketch
image-to-texture
ImageNet (256×256) validation subset
ImageNet (32 × 32)
ImageNet (64×64)
ImageNet 1024×1024
ImageNet 256 × 256 (Conditional)
ImageNet 256 256
ImageNet 256p
ImageNet 64 × 64
ImageNet 64 × 64 Cond.
ImageNet-10K
ImageNet-1K classes
ImageNet 256x256 - 1% labeled data
DPT
ImageNet 256x256 - 1 labeled data per class
ImageNet 256x256 - 2 labeled data per class
ImageNet 256x256 - 5 labeled data per class
ImageNet-50k
ImageNet-EEG
ImageNet-R-TI2I
ImageNet1024
Imbalanced CIFAR10
IMGUR5K
IN2N scenes
iNaturalist
Indian Celebs 256 x 256
MSG-StyleGAN
INSPIRED
InterHand2.6M
Internal Benchmark
InterpBench
Japanese
JUMP-cpg0000
KAIST
Kinetics-700
KIRP
KiTS19
KITTI-360
KMNIST
LAION-10k
LAION-400M
LAION-50k
LAION-Aesthetics 6.5+
LAION-Aesthetics-6+
LAION-Aestheticsv2 6.5plus
LAION-High-Resolution
LAION-Human
LAION-MSCOCO
LAKE-RED
Landmark photo sets (6 landmarks)
Landscape
Landscapes 256 x 256
CIPS
LayoutSAM
LDM
LenCom-Eval
Lexica
LHQ
LIDC-IDRI
LiTiV2012
LiTS17
Living room
Lizard
LLAVA-558K
LLP-multi
Location
Loco-3D-FRONT
logo dataset
LPFF
LPI simulation dataset
LSDIR
LSUN 256×256
LSUN Bedroom 256×256
LSUN Bedrooms 256×256
LSUN Church (256×256)
LSUN Church (64 × 64)
LSUN Church 64
LSUN Car 256 x 256
StyleGAN2
LSUN-Horse
LSUN tower 64x64
DDPM-IP
LUAD
M-LSD
M6Doc
MA5K
MagicBrush test set
MAGICK
Male-to-Female (128x128)
Male-to-Female (64x64)
MARIO-10M
Matrix City
MatSynth + Deschaintre et al.
MC++
MeSH
Mickey
MiniText-Benchmark
MIT Indoor Scenes
MM-CelebA
MM-FFHQ
MMDGarment
MME-3DR
MMSVG-2M
MNIST-INRs
MoNuSAC
Morph4Data
MorphBench
MorphoGene
Movielens
MRBench
MS-COCO 256×256
MS-COCO validation set
MS-COCO_Large_5X
MSD
MSD Task 06
MSD Task07
MSD Task08
MSIC
MSR-VTT
MSRS
Multi-dSprites
GENESIS
Multi-Entity Draw Bench
Multi-Human Benchmark
Multi-Spatial
multi-subject driven generation benchmark
Multi-Subject Personalization
MultiRels
MUSAR-Gen
MVG
MVTec-3D-AD
MVTec-AD
Natural Scenes Dataset (NSD)
NeRSemble
NeuMERL
NI-Bench
NII-CU
NIRScene
noisy-ADE20K-DS
noisy-ADE20K-Edge
noisy-ADE20K-Random
SCDM
Normal
Noto-Emoji
novel human-object dataset
nuImages
NYU-v2
NYUv2, ScanNet, OpenImages 6K
Obama
Objaverse and game assets
Objaverse subset
Objaverse T2T Benchmark
Objaverse-LVIS
Objaverse-XL
objaverse, shapenet, Stanford 3D Scanning Repository
occupation prompts
OMSIV
Open Benchmark
Open Images validation set
OpenImages
ORIBENCH-Multi
ORIBENCH-Single
OSU
Our Bench
Our Dataset
Oxford 102 Flowers 128x128
QSNGAN
P2P Template
PACS
PanFusion prompts
PanoLlama benchmark dataset
Parti
PASCAL
Pexels
PHOENIX14-T
Picasso
PickV2
PixelRec
Planes
PlanGen-1K
POG
Point cloud
Pokemon
Pokemon BLIP Captions
Polyhaven
Porcelain
Pose
PosterDNA
Pre-set Collection
PrefBench
ProcTHOR
Promeai
Proposed Dataset
Proprietary Dataset
PSRBench
PT2I
QUANT-Bench
Quick, Draw!
RareFace-50
RAVDESS
real2paint
RealOcc
Reference dataset
Rembrandt
RenderPeople
RGB2NIR
Rifles
ROAD
Rohban et al.
RoleBench
Rotated-MNIST
ROVI validation set
RST2I-110K
RTTS
RUOD
RxRx1
S320M
SACap-Eval
SAM
SAM dataset
Satellite-Buildings 256 x 256
CIPS
Satellite-Landscapes 256 x 256
CIPS
SceneVTG-benchmark
SD-generated images
SD2.1
SDSS Galaxies
SER30K
ShapeNet Cars
ShapeNet-Car
ShapeNet Chair
Shells
Simulator video dataset
Skeleton
Sketch
Sketch2Stitch-Dress Code
Sketch2Stitch-VITON-HD
Sketchfab
SketchGraphs
Skulls
Sky Time-lapse
Snoopy
Something-Something (V2)
SonicUrban
SoundingSVI
Spongebob
Sprite Fright
SRN-Cars
SSVTP
Stable Diffusion Prompts Dataset
Stable Diffusion v1.5
Stable-Diffusion-Prompts
StagePro-V1
Stanford Car
STGarment
Sticker
StorySalon
Structured3D
Style30K
StyleAligned benchmark
StyleAligned-DreamBooth
Styles and IP
StyleText-CE
Subject-Canny
Subject-Depth
Subject-Insertion
Subjectplop
Subjectplop-StyleDrop
SubObj
SubShape
SubTex
summer2autumn
SUN
SVHN
SWiG-Event
Syn Prompt
SyncTweedies mesh and prompt pairs
Synth-500
Synth-M
Synth-U
Synthetic dataset
T2I-CompBench++
T2I-CompBench++ (3D Spatial)
T3bench+GPTEval3D
TABLETOP
Tai-Chi-HD
TCGA
TCIA COVID-19
Template 1
Template 2
Template 3
text-to-2D
Text-to-3D
Text2Place
TexTalker4D-Test-A
THuman2.0
TIFA v1.0
Tiny-ImageNet
ADC-GAN
Traffic
TU-Berlin
TV-Logic
UBC-Fashion
UEC-256
UFUC
UIUC Pascal
US cities urban layout dataset
USO-Bench
USTC-CSL
VBench-2.0
VCIP2020
Vector-Fusion prompts
VectorFont
VectorFont (Test)
VFHQ
VFHQ-Test
VFN
VG
VGGFace-IT2I
VGGFace2
VIGOR
VIGOR-Chicago
ViHTGen
Virtual try-on
VisA
VisDrone
Visual Capitalist
Visual Genome
VisualCloze
VITON-HD In-the-Wild
VOBench
VoxCeleb2 - 32-shot learning
VRoid-Hub garment dataset
Walkway
Wave-ui-25k
Weather
web-sourced test set
WikiArt and StyleDrop
Wild-TI2I
Wild-to-Cat (64x64)
XM3600
XVerse Bench