AI Image StyleLab

Anima is a 2 billion parameter text-to-image model created via a collaboration between CircleStone Labs and Comfy Org. It is focused mainly on anime concepts, characters, and styles, but is also capable of generating a wide variety of other non-photorealistic content. The model is designed for making illustrations and artistic images, and will not work well at realism. It is trained on several million anime images and about 800k non-anime artistic images. No synthetic data was used for training. The knowledge cut-off date for the anime training data is September 2025.

NovelAI's in-house Diffusion V4.5 Full model, closed-source. Key Features: - Multi-Character Prompting: Generate up to 6 unique characters in a single scene with complex interactions - Natural Language Understanding: Use natural English descriptions instead of complex tag systems — just describe what you want to create - Action Tags: Control character interactions with smart tags like source#, target#, and mutual# for dynamic poses - Character Positioning: Precisely position each character for perfect scene composition - Text Integration: Add customized text elements with natural language descriptions of text appearance - Focused Inpainting: Selected regions are upscaled to ~1 megapixel before inpainting for higher-resolution detail

After a long period of underlying refactoring and a baptism of tens of millions of data points, ChenkinNoob-XL-V0.5 is officially released! As the latest major milestone from the ckn Mainline Lab, V0.5 completely shakes off the "cheap AI-generated look" of traditional anime models and truly steps into the standard of industrial-grade productivity. This update not only takes a massive lead in data knowledge base but also achieves a qualitative leap in compositional tension and lighting texture.

A continuation of ChenkinRF 0.2, which is a conversion to rectified flow of the Chenkin 0.2. RF allows this model to get away from greyness of the base EPS solutions, provides vivid colors and unlocks better lighting adherence, like very dark or contrasty scenes, while not requiring training-time tricks like offset noise. It also allows to sustain high stability at wide range of CFG, while not suffering from common downfalls of other base models

ChenkinNoob is an independent open-source team continuing the noobai-XL-1.1 lineage. Version 0.2 officially released on 2025-12-25 and keeps the familiar high-quality aesthetics while integrating newer Danbooru data (extended through 2025-11-23). Internal evaluations show noticeable gains over V0.1 in character consistency, detail rendition, and prompt fidelity.