sd3
Datasets
All datasets matching “sd3”sd3_5_fine_sixcard
DreamBooth training example
DreamBooth is a method to personalize text2image models like stable diffusion given just a few(3~5) images of a subject.
The train_dreambooth.py script shows how to implement the training procedure and adapt it for stable diffusion.
Running locally with PyTorch
Installing the dependencies
Before running the scripts, make sure to install the library's training dependencies:
Important
To make sure you can successfully run the latest… See the full description on the dataset page: https://huggingface.co/datasets/yyyzzzzyyy/sd3_5_fine_sixcard.sd3-tssd3_5_dataset700k_Human_Preference_Dataset_FLUX_SD3_MJ_DALLE3
NOTE: A newer version of this dataset is available Imagen3_Flux1.1_Flux1_SD3_MJ_Dalle_Human_Preference_Dataset
Rapidata Image Generation Preference Dataset
This Dataset is a 1/3 of a 2M+ human annotation dataset that was split into three modalities: Preference, Coherence, Text-to-Image Alignment.
Link to the Coherence dataset: https://huggingface.co/datasets/Rapidata/Flux_SD3_MJ_Dalle_Human_Coherence_Dataset
Link to the Text-2-Image Alignment dataset:… See the full description on the dataset page: https://huggingface.co/datasets/Rapidata/700k_Human_Preference_Dataset_FLUX_SD3_MJ_DALLE3.Flux_SD3_MJ_Dalle_Human_Alignment_Dataset
NOTE: A newer version of this dataset is available Imagen3_Flux1.1_Flux1_SD3_MJ_Dalle_Human_Alignment_Dataset
Rapidata Image Generation Alignment Dataset
This Dataset is a 1/3 of a 2M+ human annotation dataset that was split into three modalities: Preference, Coherence, Text-to-Image Alignment.
Link to the Coherence dataset: https://huggingface.co/datasets/Rapidata/Flux_SD3_MJ_Dalle_Human_Coherence_Dataset
Link to the Preference dataset:… See the full description on the dataset page: https://huggingface.co/datasets/Rapidata/Flux_SD3_MJ_Dalle_Human_Alignment_Dataset.sd3-images
Stable Diffusion 3 Images
A dataset of 1:1 images generated by Stable Diffusion 3, through glif.app.
Find the prompts in prompts.json, they correspond to the image based on number, for example the first element in the JSON array is x, then the image you're looking for is 0.jpg, and so on.
Prompts sourced from MohamedRashad/midjourney-detailed-prompts.
Data
You can find enhanced images by Gigapixel AI in the enhanced folder; these are the same 1024x1024 quality, but… See the full description on the dataset page: https://huggingface.co/datasets/leafspark/sd3-images.