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.
Install the ComfyUI-MOSS-Image-Ostris-Edit node (reference latents + KV cache).
Load your character picture, keep the LoRA at 1.0.
Prompt: Same character and art style as Picture 1. + your scene (tags, sentences or a MOSS JSON page layout).
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.