datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
blip3o-256GenRef-wds
GenRef-1M
We provide 1M high-quality triplets of the form (flawed image, high-quality image, reflection) collected across
multiple domains using our scalable pipeline from [1]. We used this dataset to train our reflection tuning model.
To know the details of the dataset creation pipeline, please refer to Section 3.2 of [1].
Project Page: https://diffusion-cot.github.io/reflection2perfection
Dataset loading
We provide the dataset in the webdataset format for fast… See the full description on the dataset page: https://huggingface.co/datasets/diffusion-cot/GenRef-wds.GenRef-CoT
GenRef-CoT
We provide 227K high-quality CoT reflections which were used to train our Qwen-based reflection generation model in ReflectionFlow [1]. To
know the details of the dataset creation pipeline, please refer to Section 3.2 of [1].
Dataset loading
We provide the dataset in the webdataset format for fast dataloading and streaming. We recommend downloading
the repository locally for faster I/O:
from huggingface_hub import snapshot_download
local_dir =… See the full description on the dataset page: https://huggingface.co/datasets/diffusion-cot/GenRef-CoT.ImagePulseV2-Edit-Structure
ImagePulseV2 Dataset - Image Structure
The ImagePulseV2 dataset is a collection we constructed for training the Diffusion Templates series of models. It comprises multiple subsets generated using models such as Z-Image-Turbo, Qwen-Image, and Qwen-Image-Edit, based on prompts randomly sampled from DiffusionDB.
Open-source code: DiffSynth-Studio
Technical report: arXiv
Project homepage: GitHub
Documentation: English Version, Chinese Version
Online demo: ModelScope Studio
Model… See the full description on the dataset page: https://huggingface.co/datasets/DiffSynth-Studio/ImagePulseV2-Edit-Structure.video-diffusion-perceptionDF_DiFF_FAS_dataset_in_FSFM_FSVFM
FSFM / FS-VFM Downstream Datasets
Processed downstream fine-tuning datasets for cross-dataset deepfake detection, cross-domain face anti-spoofing, and unseen diffusion-generated face detection used with FSFM and FS-VFM.
This archive is intended for research use with the FSFM/FS-VFM release scripts.
DiffusionDB-300k-processedBimanualUR5eExample
Dataset Summary
This dataset provides shards in the WebDataset format for fine-tuning RDT-2 or other policy models on bimanual manipulation.
Each sample packs:
a binocular RGB image (left + right wrist cameras concatenated horizontally)
a relative action chunk (continuous control, 0.8s, 30Hz)
a discrete action token sequence (e.g., from an Residual VQ action tokenizer)
a metadata JSON with an instruction key sub_task_instruction_key to index corresponding instruction from… See the full description on the dataset page: https://huggingface.co/datasets/robotics-diffusion-transformer/BimanualUR5eExample.Diffusion4RobustDepth
Diffusion4RobustDepth
This repository contains the generated dataset and trained network weights used in the paper "Diffusion Models for Monocular Depth Estimation: Overcoming Challenging Conditions" (ECCV 2024).
Dataset Structure
The dataset is organized into three main categories:
driving/: Contains autonomous driving datasets with challenging images.
ToM/: Contains the Transparent and Mirrored (ToM) objects dataset.
weights/: Contains the weights of models trained in… See the full description on the dataset page: https://huggingface.co/datasets/fabiotosi92/Diffusion4RobustDepth.video-diffusion-perception-feasibilityDiffusionDB-300kDiff-training-teststable_diffusion_dataDIffueraser_resDiffuEraser-finetune-prompt-codediffted_keypointsdiffted_audioDiffHeadSwapmol_diff_ae_datadiffted_meanposediffted_tpsm_test