Obsidian Anise
V2 Update: V2 tones down the lineart and adds more depth through shading, color, texture, and lighting. It can handle both clean 2D anime and a more semi-real finish while keeping a clear manga/anime base.
Notes: I get asked this a lot but if you want to create images the way I do it you can read my articles on using img2img in a lose creative way.
Underpainting for AI: A Creative Approach to SDXL Composition
Some examples of what you can do with the information in my articles. You can use this on Civitai with the img2img feature or use my workflows
Obsidian Anise is a manga-driven SDXL merge built for artists who want strong linework, expressive character styling, and high-fidelity rendering across multiple aesthetics. The model carries a clear manga influence in its contrast, silhouettes, and shading approach, while still supporting a wide range of finishes — from clean anime to semi-real and full realistic rendering.
What sets this merge apart is how consistent and structured it stays across styles. Lineart comes out crisp and intentional. Anime illustrations land with bold forms and clear expressions. Semi-real and realistic prompts maintain their detail without losing the underlying stylization. The model naturally leans toward strong contrast, defined edges, and deeper blacks, giving every output a confident visual weight.
Backgrounds and environments are a major strength. Architectural detail, forests, interiors, industrial scenes — all generate with convincing depth, texture, and atmospheric lighting. Surfaces like metal, fabric, fur, and stone are rendered with clarity and texture breakup, which helps blend stylized characters into richer, more realistic worlds.
Lighting performance is also strong. Rimlight, bloom, dramatic shadows, spell effects, and warm/cool shifts all resolve cleanly, giving images a dynamic finish without washing out the linework.
This merge suits:
Manga-style illustrations
Clean anime art
Lineart-focused compositions
Semi-real and stylized realistic portraits
Fantasy, sci-fi, modern, and anthro
Anyone who wants stylization + texture + depth in one model
🔧 Recommended Settings:
A well-rounded setup for general SDXL prompting.
Steps: 24–32
Sampler: Euler a or DPM++ 2M Karras
CFG: 4–5.5
Resolution: 832×1216 or higher
VAE: Default / model-embedded
🏷️ Recommended Quality Tags
anime screencap, anime style, thin lineart, cel shading, cinematic lighting, dramatic shadows, cinematic lighting,
american comic style, bold outlines, sharp inking, vibrant solid colors, cinematic lighting, dramatic shadows, cinematic lighting,
clean lineart, sharp outlines, precise inking, controlled shadows, high-contrast
semi-realistic details, refined textures, natural lighting, atmospheric depth,
masterwork, masterpiece, best quality, (masterpiece:1.2), (best quality:1.2),(very aesthetic:1.2), (absurdres:1.2), newest,
anime_art_style, 2d, line_art_style, limited_pallette,
Description
Obsidian Anise V1 and V2 use the same manga/anime base, but they handle the final image differently.
V1 leans harder into bold lineart, flatter colors, simpler cel shading, and stronger shape separation. It has a more graphic manga look, but it can also drift too easily into monochrome art, heavy inks, or comic-panel layouts even when the prompt is aiming for a full-color illustration.
V2 was made to reduce that tendency. The lineart is less dominant, while the shading, color, texture, and lighting do more of the work. It has more midtones, deeper shadows, broader color variation, and a stronger sense of volume.
V2 can also swing further toward semi-real rendering, especially in its textures and lighting, while still keeping clear manga/anime anatomy and structure. Since it is a mix model, it can move between a cleaner 2D anime look and a more semi-real finish through prompting rather than being locked into one style.
The main difference is that V1 is more line-driven and graphic, while V2 gives more weight to shading, color, texture, and light. V1 is better suited to hard-line manga images. V2 is more flexible and better at maintaining full-color illustrations without losing the anime base.
FAQ
Comments (3)
You have created a very unique model here. Follows prompting very well and it can go from flat art to semi-realistic work with ease
i love this one, great job
exciting, v1 is one of my favorite models of all time. Do you think a v3 for anima is possible?