Characters, illustrations, and little objects — ready for your composition.
中文 · English · ComfyUI guide
Author: chinoll
CKMoss-Image-RGBA includes an RGBA VAE and an optional DiT LoRA, allowing MOSS-Image to output PNG files with an alpha channel for character assets, illustration, and layered compositions.
Images can be generated without the DiT LoRA. Keep the original MOSS-Image model and load this RGBA VAE. The optional LoRA adapts MOSS-Image-SFT for transparent-image generation; background transparency and edge quality can differ between the two setups.
Downloads
| File | Purpose | Destination |
|---|---|---|
| RGBA VAE · 336 MB | Required; already merged and ready to load | ComfyUI/models/vae/ |
| DiT LoRA · 298 MB | Optional; use with MOSS-Image-SFT | ComfyUI/models/loras/ |
| ComfyUI nodes on GitHub | Nodes, guides, and example workflows | Clone into ComfyUI/custom_nodes/ |
| Model code on GitHub | Python entry points and model code | Clone and run from the project root |
This repository contains a VAE and a LoRA. Obtain the MOSS-Image base model and its text encoder separately. See the official ComfyUI instructions.
Get started
Install the nodes, place the weights, and drag a workflow into ComfyUI. Select your base model and text encoder:
- RGBA VAE only: no DiT LoRA.
- RGBA VAE + DiT LoRA: default LoRA strength
1.0.
Describe the subject, appearance, pose, and style. You can append transparent background. Connect VAE Decode → Save Image to save the RGBA PNG.
Full installation and node guide: English · 中文.
Showcase
Actual outputs from the RGBA VAE and DiT LoRA, preserving the original alpha. Background colors and checkerboards are for display only.
Original transparent PNG files · Prompts and seeds
Credits and license
Built on MOSS-Image and the FLUX.2 VAE. Thanks to niangao2331 for data support.