vibehacker

Vision SFT

Skill

Fine-tune vision-language models on image and text data

by wshobson Listed Jul 24, 2025

Clone or download it from github.com, then drop the folder into ~/.claude/skills/ (Claude Code) or your agent's skills directory.

Product badge

Share this product's name and rating in your README or on your website.

Vision SFT: rating on VibeHacker

Updates may be delayed by image caching.

Vision SFT cover

About Vision SFT

A wshobson/agents skill for supervised fine-tuning of VLMs: adapting to a visual domain, setting up LoRA with a frozen vision tower, and debugging runs that train without learning.

Used Vision SFT?

Log in to write a review.

No reviews yet

Used it? Write the first review.