datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
nerf-gs-datasetsI keep a collection compiled of existing datasets from various sources for training NeRFs or Splats. This dataset is most of that collection. All of the individual scenes also have a trained Gaussian Splat.
https://rishit-dagli.github.io/2025/03/28/nerf-gs-datasets.html
bad_prompt
Negative Embedding / Textual Inversion
Idea
The idea behind this embedding was to somehow train the negative prompt as an embedding, thus unifying the basis of the negative prompt into one word or embedding.
Side note: Embedding has proven to be very helpful for the generation of hands! :)
Usage
To use this embedding you have to download the file aswell as drop it into the "\stable-diffusion-webui\embeddings" folder.
Please put the embedding in… See the full description on the dataset page: https://huggingface.co/datasets/Nerfgun3/bad_prompt.nerf-synthetic-mirrordatasetsnerf-syntheticnerf-syntheticMip-NeRF360nerf_syntheticsakimi-chan_LoRA
Sakimi-chan LoRA
Who is Sakimi-chan?
Sakimi-chan is a Canadian artist best known for her digital paintings and unique style. She mainly draws fanart of games and popular characters and creates gifs for her fans with voiceovers.
Patreon: https://www.patreon.com/sakimichan
Use Cases
The LoRA is in itself very compatible with the most diverse model. However, it is most effective when used with Kenshi or AbyssOrangeMix2.
The LoRA itself was trained with the token:… See the full description on the dataset page: https://huggingface.co/datasets/Nerfgun3/sakimi-chan_LoRA.nerfFSCM_Flood_nerfsphere-nerfgreat-e-nerfmiyuki-shiba_LoRA
Miyuki Character LoRA
Use Cases
The LoRA is in itself very compatible with the most diverse model. However, it is most effective when used with Kenshi or AbyssOrangeMix2.
The LoRA itself was trained with the token: miyuki.
I would suggest using the token with AbyssOrangeMix2, but not with Kenshi, since I got better results that way.
The models mentioned right now
AbyssOrangeMix2 from WarriorMama777
Kenshi Model from Luna
Strength
I would personally use… See the full description on the dataset page: https://huggingface.co/datasets/Nerfgun3/miyuki-shiba_LoRA.HSI-SC-NeRF
HSI-SC-NeRF: NeRF-based Hyperspectral 3D Reconstruction using a Stationary Camera for Agricultural Applications
📄 Paper Link
🧾 Overview
This dataset accompanies our work on HSI-SC-NeRF, a stationary-camera-based hyperspectral NeRF framework for 3D plant phenotyping and postharvest agricultural inspection. Unlike conventional NeRF pipelines that require camera motion around a static object, our approach uses a fixed camera and a rotating object, making the acquisition… See the full description on the dataset page: https://huggingface.co/datasets/BGLab/HSI-SC-NeRF.tinafate_LoRA
TinaFate LoRA
Use Cases
The LoRA is in itself very compatible with the most diverse model. However, it is most effective when used with Kenshi or AbyssOrangeMix2.
The LoRA itself was trained with the token: skistyle.
I would suggest using the token with AbyssOrangeMix2, but not with Kenshi, since I got better results that way.
The models mentioned right now
AbyssOrangeMix2 from WarriorMama777
Kenshi Model from Luna
Strength
I would personally use these… See the full description on the dataset page: https://huggingface.co/datasets/Nerfgun3/tinafate_LoRA.Mip-NeRF_360_Processed_with_Nerfstudiomega_nerf_rubble_colmapThis repository redistributes the Rubble dataset released by Mega-NeRF. Their original release uses a different data format, so we reran COLMAP and provide a COLMAP-compatible version of Rubble here.
Please cite the original Mega-NeRF paper if you use this dataset:
@InProceedings{Turki_2022_CVPR,
author = {Turki, Haithem and Ramanan, Deva and Satyanarayanan, Mahadev},
title = {Mega-NERF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughs}… See the full description on the dataset page: https://huggingface.co/datasets/HexuZhao/mega_nerf_rubble_colmap.sonic-nerf
Sonic NeRF
Sample data for a synthetic NeRF pipeline I'm working on. This repository is a temporary backup. I will delete it sometime in the future.
NeRF Dataset
The dataset for training a NeRF can be found in the multi_view_renders folder.
The multi_view_renders/transforms.json file contains a record of the half FOV in radians as well as camera poses for each frame.
The camera poses are given as column-major affine transformation matrices.
FBI-meme_LoRA
FBI Cap Meme LoRA
Use Cases
The LoRA is in itself very compatible with the most diverse model. However, it is most effective when used with Kenshi or AbyssOrangeMix2.
The LoRA itself was trained with the token: skistyle.
You most likely want to add fbi cap, fbi to force the cap.
The models mentioned right now
AbyssOrangeMix2 from WarriorMama777
Kenshi Model from Luna
Strength
I would personally use these strength with the assosiated model:
0.75-0.85 for… See the full description on the dataset page: https://huggingface.co/datasets/Nerfgun3/FBI-meme_LoRA.HSI-SC-NeRF
HSI-SC-NeRF: NeRF-based Hyperspectral 3D Reconstruction using a Stationary Camera for Agricultural Applications
📄 Paper Link
🧾 Overview
This dataset accompanies our work on HSI-SC-NeRF, a stationary-camera-based hyperspectral NeRF framework for 3D plant phenotyping and postharvest agricultural inspection. Unlike conventional NeRF pipelines that require camera motion around a static object, our approach uses a fixed camera and a rotating object, making the… See the full description on the dataset page: https://huggingface.co/datasets/Smaraharamrita/HSI-SC-NeRF.enaic31_LoRA
Enaic31 Artstyle LoRA
Use Cases
The LoRA is in itself very compatible with the most diverse model. However, it is most effective when used with Kenshi or AbyssOrangeMix2.
The LoRA itself was trained with the token: skistyle.
I would suggest using the token with AbyssOrangeMix2, but not with Kenshi, since I got better results that way.
The models mentioned right now
AbyssOrangeMix2 from WarriorMama777
Kenshi Model from Luna
Strength
I would personally use… See the full description on the dataset page: https://huggingface.co/datasets/Nerfgun3/enaic31_LoRA.shylily
Shylily Character Embedding / Textual Inversion
Disclaimer
This is an embedding based on the VTuber Shylily, which can be found / watched on Twitch:
https://www.twitch.tv/shylily
Usage
To use this embedding you have to download the file aswell as drop it into the "\stable-diffusion-webui\embeddings" folder
To use it in a prompt: "shy_lily"
Personally, I would recommend to use my embeddings with a strength of 0.8, like "(shy_lily:0.8)", but in this case the… See the full description on the dataset page: https://huggingface.co/datasets/Nerfgun3/shylily.nerfonthego-undistortedCustom pre-processing of the NeRF On-the-go dataset (https://arxiv.org/pdf/2405.18715) as used in WildGaussians paper (https://arxiv.org/pdf/2407.08447).
John_Kafka_LoRA
John Kafka Artstyle LoRA
Use Cases
The LoRA is in itself very compatible with the most diverse model. However, it is most effective when used with Kenshi or AbyssOrangeMix2.
The LoRA itself was trained with the token: skistyle.
The models mentioned right now
AbyssOrangeMix2 from WarriorMama777
Kenshi Model from Luna
Strength
I would personally use these strength with the assosiated model:
Soft-Version:
0.85-1 for AbyssOrangeMix2
0.75-0.9 for Kenshi… See the full description on the dataset page: https://huggingface.co/datasets/Nerfgun3/John_Kafka_LoRA.Explicit-NeRF-QAIf you use our dataset, please cite the following article:
@article{xing2024explicit,
title={Explicit-NeRF-QA: A quality assessment database for explicit NeRF model compression},
author={Xing, Yuke and Yang, Qi and Yang, Kaifa and Xu, Yilin and Li, Zhu},
journal={arXiv preprint arXiv:2407.08165},
year={2024}
}
flower_style
Flower Style Embedding / Textual Inversion
Usage
To use this embedding you have to download the file aswell as drop it into the "\stable-diffusion-webui\embeddings" folder
To use it in a prompt: "art by flower_style"
If it is to strong just add [] around it.
Trained until 15000 steps
I added a 7.5k steps trained ver in the files aswell. If you want to use that version, remove the "-7500" from the file name and replace the 15k steps ver in your folder
Have fun :)… See the full description on the dataset page: https://huggingface.co/datasets/Nerfgun3/flower_style.yor_forger
Yor Forger Character Embedding / Textual Inversion
Disclaimer
This is an embedding based on the Anime Character Yor Forger from Spy x Family
Usage
To use this embedding you have to download the file aswell as drop it into the "\stable-diffusion-webui\embeddings" folder
To use it in a prompt: "yor_forger"
Personally, I would recommend to use my embeddings with a strength of 0.8, like "(yor_forger:0.8)", but in this case the embedding basically works on almost… See the full description on the dataset page: https://huggingface.co/datasets/Nerfgun3/yor_forger.tt-nerf-p150-whitedpin_style
Dpin Style Embedding / Textual Inversion
Usage
To use this embedding you have to download the file aswell as drop it into the "\stable-diffusion-webui\embeddings" folder
To use it in a prompt: "dpin_style"
Personally, I would recommend to use my embeddings with a strength of 0.8, like "(dpin_style:0.8)"
I hope you enjoy the embedding. If you have any questions, you can ask me anything via Discord: "Nerfgun3#7508"
License
This embedding is open access and… See the full description on the dataset page: https://huggingface.co/datasets/Nerfgun3/dpin_style.