frankluise5220/ComfyUI-Lorahelper
A professional automation toolkit for ComfyUI to prepare LoRA training data using LLMs. New support for Qwen 3.5
This tool helps generative AI artists and designers automatically create high-quality, detailed text prompts for image generation, and organize their training data. It takes in images or simple text descriptions and outputs rich, elaborate prompts ready for use in image generation models. It also helps you save and manage images, their associated prompts, and workflow metadata in one click, streamlining the creation of datasets for training your own custom image models (LoRAs).
Use this if you are a generative artist or designer working with ComfyUI and want to automate the creation of detailed image prompts and effortlessly manage your LoRA training datasets.
Not ideal if you are looking for a standalone image generation application rather than a specialized tool to enhance your ComfyUI workflow.
Stars
10
Forks
1
Language
Python
License
—
Category
Last pushed
Mar 05, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/frankluise5220/ComfyUI-Lorahelper"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
unslothai/unsloth
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama,...
huggingface/peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
modelscope/ms-swift
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.5, DeepSeek-R1, GLM-5,...
oumi-ai/oumi
Easily fine-tune, evaluate and deploy gpt-oss, Qwen3, DeepSeek-R1, or any open source LLM / VLM!
linkedin/Liger-Kernel
Efficient Triton Kernels for LLM Training