Sign In
homemodelsimagesvideos3D Modelshubsarticlescomicscruciblesupdatesshop

MOSS Manga Alpha Image LoRA (transparent PNG manga)

1

Updated: Oct 26, 2026

toolblack and whitemangatransparent backgroundalpha channelmoss image

Recently loaded

Download

1 variant available

fp16 SafeTensor

moss_manga_alpha_image_lora.safetensors

Half precision, best balance • 126.04 MB

Verified:

Type
LoRA
Stats

96

1

Reviews

(10)

Published

Oct 26, 2026

Base Model

MOSS Image

Training
Steps: 1,500
Usage Tips
Strength: 1
Hash
AutoV21D2A5317E5
Trigger Words
isolated on a transparent background
02_cover_any_layout.jpg

Transparent PNGs straight out of MOSS-Image. End your prompt with isolated on a transparent background, decode with the RGBA VAE, and the sampler gives you an image with a real alpha channel: no chroma key, no background removal, no masking.

Trained with black-and-white manga in mind (characters, creatures, props, ink effects, sound effects, speech balloons), but it also works in color.

Everything you need (ComfyUI)

Files, raw RGBA examples, trailer and full notes: huggingface.co/paralaif/MOSS-Manga-Alpha-Image-LoRA

  1. This LoRA → models/loras/

  2. RGBA VAE vae/flux2_klein_alpha_rgba_vae.safetensors (in the Hugging Face repo; originally trmz/flux2-klein-alpha, Apache-2.0) → models/vae/

  3. Load RGBA VAE (Flux2) custom node + minimal workflow: the attached zip (also on Hugging Face). Stock ComfyUI can't load a 4-channel VAE.

  4. MOSS-Image SFT + Qwen3.5-9B text encoder: Comfy-Org/MOSS-Image

  5. 8-step DMD LoRA: lora.safetensors from lodestones/MOSS-Image-SFT-8-steps-dmd, renamed moss_image_sft_8step_dmd.safetensors

Tips

  • Always end the prompt with isolated on a transparent background, and describe one subject, not a place.

  • Say "man" or "boy" explicitly when it matters; ambiguous roles sometimes come out as women.

  • Semi-transparent areas (smoke, plastic umbrellas, ink sprays) can carry a faint purple tint from the RGBA VAE.

  • The preview images here are flattened onto colored backgrounds because Civitai doesn't show transparency. The raw RGBA PNGs are on Hugging Face.

Training

MOSS-Image Base, ai-toolkit, 503 RGBA images, rank 32, AdamW 8-bit 2e-4, step 1500 of 3000, one RTX 5060 Ti 16 GB. The training images are synthetic: generated with MossAD-Demo using its built-in artist-style tags, on a flat indigo background, cut out with a chroma key and reviewed by hand. The artist tags were removed from the captions, but the LoRA may still carry some of those styles.

License

Apache-2.0. Credits: MOSS-Image (OpenMOSS, Apache-2.0), MossAD-Demo (RicemanT, Apache-2.0), RGBA VAE (Xavier Jara / trmz, Apache-2.0, method AlphaVAE), 8-step DMD (lodestones, Apache-2.0), ai-toolkit (Ostris, MIT).

Also available for Krea 2: paralaif/Krea2-Manga-Alpha-Image-LoRA