chinoll/Moss-Image-Edit

Give your images a new expression.
MOSS Image Edit is an image-editing LoRA for MOSS-Image. Edit colors, outfits, lighting, seasons, and visual style with text instructions.
This repository provides LoRA weights and configuration. Use them with the MOSS-Image Base or SFT model.

GitHub · 中文介绍   ·   English   ·   ComfyUI guide

Editing showcase

Explore changes in color, outfits, lighting, seasons, and visual style. Each group starts with the original image, followed by its edits.

Get started

Download this editing LoRA together with either MOSS-Image-Base or MOSS-Image-SFT, then open a ComfyUI workflow. Both base models are supported; choose either one.

Resource	Link
Installation and model placement	English guide · 中文教程
Edit with one reference	Single-reference workflow
Edit with multiple references	Multi-reference workflow

Upload your reference image, describe the change, and generate the result. With multiple references, explain the role of each image in your instruction; up to four images can be connected.

To download the LoRA and base-model files from a terminal, using SFT as the example:

hf download chinoll/Moss-Image-Edit adapter_config.json adapter_model.safetensors --local-dir models/Moss-Image-Edit
hf download OpenMOSS-Team/MOSS-Image-SFT --local-dir models/MOSS-Image-SFT

For Base, use this base-model download command instead:

hf download OpenMOSS-Team/MOSS-Image-Base --local-dir models/MOSS-Image-Base

Set the ComfyUI loader's snapshot_dir to the directory containing your chosen base model.

Credits

Thanks to @onglon114514 for generating the showcase images.

Built on MOSS-Image. Project code is available under GPLv3.