-
Image Multi-Adjustment Dataset (I-MAD-Dense)
The dataset used in the paper is the Image Multi-Adjustment Dataset (I-MAD-Dense). It contains approximately 22,000 triplets, each containing a source image, an edited image,... -
Benchmark Dataset for Text-Grounded Object Generation in Real Images
A benchmark dataset for text-grounded object generation in real images -
Editing-Mask
Editing-Mask dataset is used for semantic image editing task. -
ImageNet and Imagen
ImageNet and Imagen datasets are used for semantic image editing task. -
ImageNet, Imagen and Editing-Mask
ImageNet, Imagen and Editing-Mask datasets are used for semantic image editing task. -
LoMOE-Bench
LoMOE-Bench is a dataset for multi-object editing, featuring 64 images with 2 to 7 masks, paired with corresponding text prompts. -
Paint by Example: Exemplar-based image editing with diffusion models
Exemplar-based image editing with diffusion models -
Learning to follow image editing instructions
Learning to follow image editing instructions. -
Multimodal Garment Designer
Multimodal Garment Designer: Human-Centric Latent Diffusion Models for Fashion Image Editing -
Customized Image Editing
The dataset used in the paper for image editing tasks -
Midjourney dataset
The dataset used in the paper for text-driven image editing, consisting of synthetic images generated by Midjourney. -
COCO-animals-10k
The dataset used in the paper for text-driven image editing, consisting of synthetic images generated by Midjourney and COCO dataset images. -
LSUN Churches
The dataset used for training and testing the Conditionally-Independent Pixel Synthesis (CIPS) generator. -
Flickr-Faces-HQ
Flickr-Faces-HQ contains 70,000 face images at 1024 × 1024 resolution, which were originally crawled from Flickr, manually checked to discard low-quality samples, and then... -
Expanding small-scale datasets with guided imagination
The dataset is used for image generation and editing tasks. -
Non-Hair-FFHQ
The Non-Hair-FFHQ dataset is a high-quality image dataset that contains 6,000 non-hair-FFHQ portraits.