<blockquote>⚠️ Experimental – first version. MOSS-Image is new and this kit was built and tested in a few days. Expect bugs and rough edges. Feedback and bug reports in the comments are very welcome.</blockquote><blockquote>🖥️ Now available: Fumika, the standalone app. The same doujin pipeline in a free desktop app for Windows and Linux: one installer, models downloaded and managed for you, series and chapters, a story editor with panel cards, drawn covers, a reader and PDF / CBZ export. No nodes, no workflows. <a target="_blank" rel="ugc" href="https://github.com/7err4/fumika">GitHub</a> · <a target="_blank" rel="ugc" href="https://civarchive.com/articles/37215/fumika-a-free-local-studio-for-comics-images-and-lora-training">Civitai article</a>. This ComfyUI kit stays available if you prefer ComfyUI.</blockquote>Make complete manga / doujin pages, or a whole book in one Run, with MOSS-Image. You get panel borders, readable speech bubbles, sound effects and title lettering, and the same characters on every page. No JSON, no photo editing, no node spaghetti.<h2 id="how-it-works-(easy-mode)">How it works (easy mode)</h2>Open Templates → ComfyUI-MOSS-Doujin → Make a whole manga and fill in 3 fields:<pre><code>characters: Tifa: Tifa Lockhart, an adult woman with long black hair, red eyes, white tank top, black mini skirt
 Aerith: Aerith Gainsborough, an adult woman with a long brown braid with a pink ribbon, green eyes, long pink dress

story: Tifa and Aerith pose together in a neon-lit street at night | #SLUM NIGHTS

 Tifa wipes the counter of a cosy bar at night | Slow night...
 Aerith bursts through the door holding a flyer | I found us a job!
 Tifa and Aerith lean over the counter face to face | Night work... good pay?
</code></pre><ul><li>One block per page, with an empty line between pages.</li><li>One line per panel: <code>what happens | what she says</code>. The number of lines (1–5) picks the panel layout.</li><li><code>!</code> before a text = sound effect, <code>#</code> = big title (covers).</li><li>Outfit changes: define the same character twice with different names, e.g. <code>Hooker Tifa: …</code>, and use that name in the story.</li><li>Press Run. Every page is drawn 3 times and the version with the fewest gibberish bubbles is kept. Pages + PDF are saved to <code>output/doujin/&lt;title&gt;/</code>.</li></ul>There is also Make a manga page (one page per Run) for trying things out.Optional settings below the main fields (all have working defaults):<ul><li>character LoRA and its strength</li><li>base model (MOSS Base or a fine-tune like Kromoss)</li><li>speed: fast / quality / auto</li><li>versions per page</li><li>page size</li><li>seed</li></ul><h2 id="speed">Speed</h2>About 5 s per page version on an RTX 5090 with the 8-step turbo LoRA. A 30-page doujin takes about 8 minutes. Title pages automatically use the slower 50-step mode, which spells titles correctly.<h2 id="models-(put-them-in-your-normal-comfyui-folders-any-sub-folder-file-name-works)">Models (put them in your normal ComfyUI folders; any sub-folder / file name works)</h2><ul><li>MOSS-Image Base (or a MOSS fine-tune) → <code>models/diffusion_models</code></li><li>Qwen3.5-9B text encoder of MOSS-Image → <code>models/text_encoders</code></li><li>FLUX.2 VAE → <code>models/vae</code></li><li>8-step DMD turbo LoRA (optional, much faster) → <code>models/loras</code></li></ul>The nodes find the files by name (<code>auto</code>). If yours are named differently, pick them in the dropdowns.Downloads (right-click → save into the folder in brackets):<ul><li>MOSS-Image Base: <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/MOSS-Image/resolve/main/diffusion_models/moss_image_base_bf16.safetensors">bf16, 24 GB+ VRAM</a> or <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/MOSS-Image/resolve/main/diffusion_models/moss_image_base_int8_convrot.safetensors">int8, smaller GPUs</a> (<code>models/diffusion_models</code>)</li><li><a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/MOSS-Image/resolve/main/text_encoders/qwen3.5_9b_int8_convrot.safetensors">Qwen3.5-9B text encoder</a> (<code>models/text_encoders</code>)</li><li><a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/MOSS-Image/resolve/main/vae/flux2-vae.safetensors">FLUX.2 VAE</a> (<code>models/vae</code>)</li><li><a target="_blank" rel="ugc" href="https://huggingface.co/lodestones/Kromoss/resolve/main/8-steps-dmd-lora.safetensors">8-step turbo LoRA</a> (<code>models/loras</code>)</li></ul><h2 id="install">Install</h2>Extract the zip into <code>ComfyUI/custom_nodes/</code>, restart ComfyUI and press F5. The workflows are under Templates. Needs a ComfyUI version with MOSS-Image support. The gibberish-bubble check needs opencv: if it is missing (e.g. a fresh ComfyUI portable), the pack installs <code>opencv-python-headless</code> by itself on the first start.<h2 id="tips">Tips</h2><ul><li>Write each character once in full (hair, eyes, body, outfit) and use the same text in every page.</li><li>Keep bubbles short (up to about 12 words); 3–4 panels per page look best.</li><li>Black-and-white style LoRAs: no colour words. Describe the characters by shape (hair length, glasses, body, outfit type), not by colour ("red hair", "black blouse"). Colour words override the ink look.</li><li>For explicit panels, start the line with "Explicit uncensored:" and name what is visible. MOSS-Base is uncensored.</li><li>Famous characters (FF7, Fate, Re:Zero …) work without a LoRA. Niche or original characters need a character LoRA; make one with the <a target="_blank" rel="ugc" href="https://civarchive.com/models/3010231">MOSS LoRA Trainer</a> kit.</li></ul>For advanced users: the zip also contains the building-block nodes and 4 advanced workflows in <code>example_workflows/advanced/</code>:<ul><li>free JSON page layouts</li><li>double-page spreads</li><li>fixed-camera pages</li><li>stray-bubble cleanup</li></ul>Full guide: <a target="_blank" rel="ugc" href="https://civarchive.com/articles/37029">Whole doujins with MOSS-Image</a>. License: MIT.

MOSS Doujin Kit for ComfyUI - whole manga in one Run

Update v1.1 – the EASY nodes now take up to 3 LoRAs (<code>character_lora</code>, <code>lora_2</code>, <code>lora_3</code>, each with its own strength), e.g. two characters or a character + a style. LoRAs can fight each other – if faces or styles start to blend, lower the strengths to ~0.6–0.8. Old workflows keep working.v1.0 – first experimental release. Easy workflows "Make a manga page" and "Make a whole manga" (3 fields, models found automatically), plus 4 advanced workflows and the building-block nodes (JSON page builder, layout preview, stray-bubble mask, pages to PDF).

Files with SHA256: 61c152040ed6cdaf8713cd0bee2ba63aea7a3a02a4d3c7f195db8fbc530612ba