// Dataset Library

Training datasets,
ready to use.

Every LoRA on neuraldrift was trained on one of these datasets. Curated, captioned, and structured for Kohya SS. Download and start training in minutes.

6
Datasets
01

01

Download dataset

Get the image + caption ZIP

02

02

Check captions

Verify trigger word is first in every .txt

03

03

Configure Kohya

Use the linked training guide

04

04

Train your LoRA

Follow the guide for optimal settings

6 datasets
CharacterSDXL
Released

Fat Bigfoot — Character Dataset v4

42 curated images of Fat Bigfoot in varied settings, poses, and lighting. WD14-captioned with trigger word. Used to train the Fat Bigfoot Character LoRA v4.

Trigger Wordfatbigfoot
Images
42
Resolution
1024×1024
Captions
WD14 Tags

Training Notes

Repeat count: 10. Best results at 8–10 epochs with SDXL + Kohya SS.

CharacterBigfootComedyOriginal IP
Trained on RTX 5080 16GB42 images
CharacterSDXL
Released

Slacker Alien — Character Dataset v2

38 images of the Slacker Alien character in suburban environments. Diverse angles and expressions. Captioned with WD14 + manual edits.

Trigger Wordslackeralien
Images
38
Resolution
1024×1024
Captions
WD14 Tags

Training Notes

Repeat count: 10. 8 epochs optimal. Strong character lock at 0.75 LoRA weight.

CharacterAlienComedySuburban
Trained on RTX 5080 16GB38 images
StyleFLUX
Released

Highway Ghost — Style Dataset v3

85 cinematic night highway reference images. Rain-soaked asphalt, neon light reflections, motion blur, and dramatic street photography. Used for the Highway Ghost style LoRA.

Trigger Wordhighwayghost
Images
85
Resolution
1024×1024
Captions
Natural Language

Training Notes

FLUX natural language captions. Rank 32, 10 epochs. Style transfers well to LTX Video.

StyleCinematicNightNeonAction
Trained on RTX 5080 16GB85 images
StyleFLUX
Beta

Desert Pursuit — Style Dataset v1

64 golden hour desert chase reference images. Dust trails, dramatic shadows, wide open landscapes, and action cinematography aesthetics.

Trigger Worddesertpursuit
Images
64
Resolution
1024×1024
Captions
Natural Language

Training Notes

Still in beta — works well for still images, video transfer WIP.

StyleDesertGolden HourActionCinematic
Trained on RTX 5080 16GB64 images
ConceptFLUX
Beta

ComfyUI Node Graph — Concept Dataset

30 dark tech node graph images. Glowing connections, dark backgrounds, cyan accents. Used to train the Node Graph concept LoRA for tech thumbnails.

Trigger Wordnodegraph
Images
30
Resolution
1024×1024
Captions
WD14 Tags

Training Notes

Small dataset — concept LoRAs need fewer images. Rank 8 works best.

ConceptTechUIDarkNodes
Trained on RTX 3080 16GB30 images
StyleSDXL
Released

GoPro POV Fisheye — Style Dataset v2

120 handheld GoPro POV images with fisheye distortion. Action sports, forest runs, vehicle mounts. Covers wide variety of POV angles.

Trigger Wordgopropov
Images
120
Resolution
1024×1024
Captions
WD14 Tags

Training Notes

Larger dataset = subtle style. Use 0.55–0.7 weight for best fisheye effect.

StylePOVGoProActionFisheye
Trained on RTX 3080 16GB120 images

// Coming Soon

Community dataset uploads

Submit your own curated datasets. Get them verified, listed here, and linked to your trained LoRAs.

Start with the Training Guide →