ComfyPilotComfyPilot
模型库 / LoRA / Nix Comic [Multiple Styles]
Nix Comic [Multiple Styles]

Nix Comic [Multiple Styles]

2836231

LoRA 4,847 次下载 322 喜欢 更新于 2026-11-17

底模:MOSS Image

comicstyleillustration

下载模型 在源站打开

文件清单 线路:镜像(hf-mirror.com) · 切换

下载后放进对应的 ComfyUI 目录。models/ 指 ComfyUI 的模型根目录。

权重 MOSSNixComic-Eurov1.safetensors 314 MB 下载

说明

Nix Comic [Multiple Styles]

作者:xFennec777

Nix comic is a flexible comic base - with a core style mixture of 1990s Disney animation and 2000s Marvel Comics. It is tuned to be used at 0.7-0.85 strength on most prompts, giving headroom for mixing in other LoRA or style guidance. No keywords, just add, enable, and generate. The colour pallette is largely the same between versions - the big differences are how face and SOME anatomy are handles, some line weighting and shading. MOSS Image Variants MOSS Image variants SHOULD follow similar tonality as the Krea 2. The caveats I have found here are:

  • Too many steps increases saturation (8-step turbo runs best at 7-9 steps, 25 step non-turbo has a wider range of 23-27 steps, depending on complexity and saturation needs)
  • The style CAN get knocked out if you have strong / overtrained character LoRA - fixes include: reduce character LoRA to 0.6-0.85 range, prompt less "photo" terms and add "disney cartoon" or your favourite illustration descriptions (this will influence the output - so beware, though many of you stack your LoRA anyway).

Euro Mix [MOSS only for now] Blends the Nix Comic base with experimentation in Belgian, Italian, and Russian inspired LoRA. While these style differ a bit, I blended the core flat colour work and dynamic/rough feel of the line work. This won't be everyone's go-to, but it's a strong base to lean into style of Watterson, Franquin, Migunov, Hergé, and many others without fighting MOSS to get remotely close. Feel free to mix in your favourite artists via prompt or LoRA and let this LoRA help drive it home! 90s Nostalgia Again, like the others, uses V2 as a core and has some retrains, re-weighting and blends (of another comic LoRA I built, but wasn't pleased with - not distinct enough). This time it leans to what I recall 90s comics and non-disney cartoons were like. Some feels of the indie artists hitting Marvel with wild takes on their art, some feels of Road to El Dorado and Treasure Planet, and some general "Cartoon Promo Art" that Nickelodeon had styled for their cartoons.

  • Thinner line work
  • Foreground/Subjects have line work, background should be flatter
  • Shading/texture with inner lines (like fabric folds or creases)
  • Distinctly different faces from Disney/Pixar - still leaning a bit to the Western style comics

Pixar / Disney (Formerly V3) Leans more to soft/Pixar character side for faces - bodies get a little adjustment, but not as much as the face - has some extended body proportions like v1 with mainly face and detail work changes

  • Softer line work - the lines should be thinner, more tone matched to the item or character they are outlining, and even non existent when the contrast is enough
  • Richer textures - fine lines, hair, skin, and fabrics have a little more roughness and hand paint feel, fine details can be prompted onto fabrics
  • Deeper backgrounds (again, more details can be prompted into the background)
  • Complex prompts (feel) like they are adhered to better - but as we all know, there are many parts at play with this one

Disney / Western Comic (Formerly V2) Similar core data set and and same goal, but much more flexibility, stronger definition of style, and richer scenes!

  • Refined V2 Foundation: Upgraded dataset with richer scene depth, enhanced background detailing, and cleaner base line art.
  • Precision Weight Merging: Blended with re-ranked and stripped LoRA to refine: Krea2 Zass-style Animation (body shape & background depth), Friendly Sketch Krea2 (line details & highlights), Nix Toon (color, highlights, tonality) using low-rank SVD reconstruction.
  • High Prompt Adherence: Text encoders stripped on secondary models to ensure prompt-defined colors, text, and scene details render cleanly without style hijacking.
  • Stackable & Diverse: Designed to prevent same-face/same-body bias, respect anatomical diversity, and stack effortlessly with additional character or style LoRAs at 0.8 – 1.0 strength.

Why not Nix Toon vX? This started as Nix Toon v2, but the core style drifted quite heavily. This is what I intended Nix Toon to be - extensible, but a strong core style. While re-tuning that model, I worked to eliminate same-face and the unintentional loss of cultural identity. While it's not perfect, Nix Comic is much more open to more body shapes/sizes/colours. What's different from other Comic/Toon LoRA? Nix Comic has a strong visual identity, with ability to take direction from other LoRA and additional style prompting (without getting too crunchy, overbaked, or breaking style). It's also built for diversity, where possible.

Special callout to @ZairaSass - some of their LoRA stack was used for inspiration.

示例图