lora-dataset-studio
Self-hosted, one-tab workbench for the whole training lifecycle: build Character/Concept/Style datasets (generate, scrape, or triage a big dump in the Image Bank), curate, caption, clean watermarks, then train LoRAs on five model families or a full Krea 2 model on a rented GPU, and rank checkpoints
- ai-toolkit
- comfyui
- dataset
- flask
- lora
- react
- stable-diffusion
- diffusion-models
- fine-tuning
- full-model-training
- Stars
- 296
- Forks
- 40
- + today
- +1
- Created
- 3mo
Ranking data as of October 5, 2026 (UTC).
Star History
Today, hour by hour
Overview
Self-hosted, one-tab workbench for the whole training lifecycle: build Character/Concept/Style datasets (generate, scrape, or triage a big dump in the Image Bank), curate, caption, clean watermarks, then train LoRAs on five model families or a full Krea 2 model on a rented GPU, and rank checkpoints It ranks #3014 on GitTiger, gaining +1 star on October 5, 2026 (UTC).
The project is written in Python and has 40 forks. It was created 3mo ago.
git clone https://github.com/perfectgf/lora-dataset-studio.git
cd lora-dataset-studio
# see README for setup