Draw any anime character from one picture – no per-character LoRA training.

Give MOSS-Image a reference picture as Picture 1 and a prompt: CharRef v2 draws that character – face, hair, outfit and art style – in the new scene. It works on single images and on whole comic pages (MOSS JSON page layouts with panels and speech bubbles), so a character stays on-model page after page.

How to use (ComfyUI ≥ 0.42)

The attached workflow has everything wired.

1. Install the ComfyUI-MOSS-Image-Ostris-Edit node (reference latents + KV cache).

2. Load your character picture, keep the LoRA at 1.0.

3. Prompt: Same character and art style as Picture 1. + your scene (tags, sentences or a MOSS JSON page layout).

4. 50 steps, CFG 3, euler / sgm_uniform, SkipLayerGuidance single layer 22.

Tips

• A few appearance words (hair style, eye colour, key outfit pieces) noticeably improve fidelity.

• The outfit follows the reference – unless the prompt names other clothing, so you can change outfits by text.

• Clean, large references (full body or bust, plain background) work best. Crop comic panels to the character, otherwise props and speech bubbles come along.

Limitations

• Fine hair details can drift without appearance words. One reference per image (scenes with several characters keep only Picture 1 reliably).

• Made for anime / illustrated characters: a photorealistic or 3D face is not kept reliably.

Prohibited use

Not for intimate or sexual images of real people without their consent, sexual depictions of minors, facial-recognition scraping or harmful manipulation (EU AI Act Art. 5). If you publish a picture that could pass as a real person or event, say that it is AI-generated (Art. 50(4)).

Also on Hugging Face: 7err4/MOSS-Image-CharRef. Built for the "reference picture" option of Fumika, a local comic and image studio.