Instructions to use lightx2v/MiniMax-H3-Prompt-Rewriter-LoRA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use lightx2v/MiniMax-H3-Prompt-Rewriter-LoRA with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.6-27B") model = PeftModel.from_pretrained(base_model, "lightx2v/MiniMax-H3-Prompt-Rewriter-LoRA") - Notebooks
- Google Colab
- Kaggle
Is it usable in comfyui? How?
Any workflow please.
nope ...
i think its for raw python ...
Hi! Here you go, I’ve created my nodes for this - https://github.com/pytraveler/MiniMax-H3-Prompt-Rewriter-ComfyUI.
Can you extend the node to support adding images beside prompt, for the models which accept images like Gemma 4 or others?
My typical way of working is to use LM Studio, load some image capable model, provide images and initial prompt so the model can cook the final prompt based on images and my skeleton prompt.
If you’re talking about that, then the latest version supports it.Can you extend the node to support adding images beside prompt, for the models which accept images like Gemma 4 or others?
My typical way of working is to use LM Studio, load some image capable model, provide images and initial prompt so the model can cook the final prompt based on images and my skeleton prompt.
