datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
stable-diffusion-v1-5-glazed
Dataset Card for Stable Diffusion v1.5 Glazed Samples
Dataset Description
Dataset Summary
This dataset contains image samples originally generated by runwayml/stable-diffusion-v1-5
and subsequently processed by Glaze tool.
Supported Tasks and Leaderboards
[More Information Needed]
Languages
[More Information Needed]
Dataset Structure
Data Instances
[More Information Needed]
Data Fields
[More Information… See the full description on the dataset page: https://huggingface.co/datasets/hanamizuki-ai/stable-diffusion-v1-5-glazed.stable-diffusion-webui
Stable Diffusion web UI
A browser interface based on Gradio library for Stable Diffusion.
Features
Detailed feature showcase with images:
Original txt2img and img2img modes
One click install and run script (but you still must install python and git)
Outpainting
Inpainting
Color Sketch
Prompt Matrix
Stable Diffusion Upscale
Attention, specify parts of text that the model should pay more attention to
a man in a ((tuxedo)) - will pay more attention to tuxedo
a man in a… See the full description on the dataset page: https://huggingface.co/datasets/PennyJX/stable-diffusion-webui.Stable_Diffusion_3_RecaptionThis dataset is the one specified in the stable diffusion 3 paper which is composed of the ImageNet dataset and the CC12M dataset.
I used the ImageNet 2012 train/val data and captioned it as specified in the paper: "a photo of a 〈class name〉" (note all ids are 999,999,999)
CC12M is a dataset with 12 million images created in 2021. Unfortunately the downloader provided by Google has many broken links and the download takes forever.
However, some people in the community publicized the dataset.… See the full description on the dataset page: https://huggingface.co/datasets/gmongaras/Stable_Diffusion_3_Recaption.stable-diffusion-prompts-stats-full-uncensoredFlux-workflows
1. FLUX Installation Tutorial on ComfyUI/ForgeUI (Native/GGUF/NF4 variant): 👇
https://www.stablediffusiontutorials.com/2024/08/flux-installation.html
2. Flux Kontext Installation + Workflow (Native/GGUF):👇
https://www.stablediffusiontutorials.com/2025/06/flux-kontext.html
3. Flux Kontext Dev LoRA Training on Windows/Linux:👇
https://www.stablediffusiontutorials.com/2025/06/train-flux-kontext-lora.html
4. Train Flux Dev/Schnell LoRA on Windows/Linux:… See the full description on the dataset page: https://huggingface.co/datasets/stablediffusiontutorials/Flux-workflows.stable-diffusion-gallerystable-diffusion-webui-1.7.0
Stable Diffusion web UI
A browser interface based on Gradio library for Stable Diffusion.
Features
Detailed feature showcase with images:
Original txt2img and img2img modes
One click install and run script (but you still must install python and git)
Outpainting
Inpainting
Color Sketch
Prompt Matrix
Stable Diffusion Upscale
Attention, specify parts of text that the model should pay more attention to
a man in a ((tuxedo)) - will pay more attention to tuxedo
a man in a… See the full description on the dataset page: https://huggingface.co/datasets/pluseen/stable-diffusion-webui-1.7.0.stable-diffusion-webui-wd14-tagger
This branch is unmaintained!
https://github.com/toriato/stable-diffusion-webui-wd14-tagger/issues/108
https://github.com/picobyte/stable-diffusion-webui-wd14-tagger
Tagger for Automatic1111's WebUI
Interrogate booru style tags for single or multiple image files using various models, such as DeepDanbooru.
한국어를 사용하시나요? 여기에 한국어 설명서가 있습니다!
Disclaimer
I didn't make any models, and most of the code was heavily borrowed from the DeepDanbooru and MrSmillingWolf's… See the full description on the dataset page: https://huggingface.co/datasets/spawner1145/stable-diffusion-webui-wd14-tagger.stable_diffusion_modelsStableDiffusion-v1-5-Regularization-ImagesA collection of regularization / class instance datasets for the Stable Diffusion v1-5 model to use for DreamBooth prior preservation loss training. Files labeled with "mse vae" used the stabilityai/sd-vae-ft-mse VAE. For ease of use, datasets are stored as zip files containing 512x512 PNG images. The number of images in each zip file is specified at the end of the filename.
There is currently a bug where HuggingFace is incorrectly reporting that the datasets are pickled. They are not picked… See the full description on the dataset page: https://huggingface.co/datasets/ProGamerGov/StableDiffusion-v1-5-Regularization-Images.Stable_Diffusion_LLavastable-diffusion-2.1-random
Stable Diffusion 2.1 Random Images
A dataset of 5010 synthetic images (768 x 768) generated via ComfyUI to explore the latent space of Stable Diffusion 2.1 in a completely unbiased, randomized way.
Generation Parameters
Model: v2-1_768-ema-pruned.safetensors
VAE: default
Sampler: euler_ancestral | Steps: 20 | CFG: 8.0 | Seed: Random
Prompt Configuration
Both prompts are dynamically assembled to fill the 75-token limit:
Positive Prompt: 75… See the full description on the dataset page: https://huggingface.co/datasets/agentlans/stable-diffusion-2.1-random.stable-diffusion-xl___individual-filesstable-diffusion-2-1_obj15_set4_seed100StableDiffusion-v1-5-Regularization-ImagesA collection of regularization / class instance datasets for the Stable Diffusion v1-5 model to use for DreamBooth prior preservation loss training. Files labeled with "mse vae" used the stabilityai/sd-vae-ft-mse VAE. For ease of use, datasets are stored as zip files containing 512x512 PNG images. The number of images in each zip file is specified at the end of the filename.
There is currently a bug where HuggingFace is incorrectly reporting that the datasets are pickled. They are not picked… See the full description on the dataset page: https://huggingface.co/datasets/lingcarzy/StableDiffusion-v1-5-Regularization-Images.stable-diffusion-1.5-random
Stable Diffusion 1.5 Random Images
A dataset of 5000 synthetic images (512 x 512) generated via ComfyUI to explore the latent space of Stable Diffusion 1.5 in a completely unbiased, randomized way.
Generation Parameters
Model: v1-5-pruned-emaonly.safetensors
VAE: vae-ft-mse-840000-ema-pruned.ckpt
Sampler: euler_ancestral | Steps: 20 | CFG: 8.0 | Seed: Random
Prompt Configuration
Both prompts are dynamically assembled to fill the 75-token limit:… See the full description on the dataset page: https://huggingface.co/datasets/agentlans/stable-diffusion-1.5-random.Stable-diffusionstable-diffusion-xlstable-diffusion-prompts-stats-full-uncensoredWikiart_with_StableDiffusion
Artistic Images Transformed by Stable Diffusion XL Refiner 1.0
Overview
This dataset contains 81,444 AI-generated images derived from famous paintings across 27 artistic genres. The transformation process involved resizing the original images to 768px, generating detailed descriptions using BLIP2, and creating customized prompts with LLaMA 3 8B. These prompts were then used with Stable Diffusion XL Refiner 1.0 to generate modified versions of the original artworks.
The… See the full description on the dataset page: https://huggingface.co/datasets/Dant33/Wikiart_with_StableDiffusion.stable_diffusion_Swami_Vivekananda
Swami Vivekananda Image Dataset
This dataset contains images of a young Indian monk in various poses and settings, dressed in traditional robes. The dataset is intended for use in image classification, generation, and other computer vision tasks. Each image is accompanied by metadata that includes descriptions and labels.
Dataset Structure
The dataset is structured as follows:
images/: Directory containing the images.
metadata.csv: CSV file containing metadata… See the full description on the dataset page: https://huggingface.co/datasets/Nitin9sitare/stable_diffusion_Swami_Vivekananda.AnimateDiff-SDv1.5-workflowstable-diffusion-xl-base-1.0-imagesstable-diffusion-prompts-stats-full-uncensoredstable-diffusion-prompts-stats-full-uncensoredstable-diffusion-2-1-with-imagesstable-diffusion-prompts-stats-full-uncensoredstable-diffusion3.5-workflowsStable-diffusion-normal-and-ddpstable-diffusion-xl_training