Dataset Lora Civitai: Image-Text Pairs for LoRA Training

A set of image and text data scraped from Civitai personal profiles for the purpose of training LoRA models, curated by user vadigr123. Updated in November 2025, the dataset aggregates artistic assets and associated metadata originally sourced from community suggestions on Discord. It serves as a repository for specific artistic styles and characters intended for generative AI fine-tuning.

Use Cases

• Fine-tuning Stable Diffusion LoRA models using the collected image-text pairs
• Style transfer research based on artistic assets sourced from Civitai
• Text-to-image prompt alignment testing using the associated text tags

Strengths

• Aggregates data from multiple Civitai personal profiles into a single repository
• Includes both image and text modalities for multimodal training
• Curated based on community-requested artistic styles from Discord

Limitations

• Lack of explicit permission from original content creators on Civitai as stated by the uploader
• Unknown total record count and file size due to missing metadata
• Potential for inconsistent labeling or captioning quality across different source profiles

Provenance

Source

Civitai personal profiles

Collection Method

Scraped and aggregated based on Discord community suggestions

Freshness

Last updated November 2025.

Geography

United States