--- license: other tags: - stable-diffusion - stable-diffusion-diffusers - text-to-image - NovelAI - anime inference: true --- # NovelAI Diffusion Anime V2 ![1girl, purple eyes, short hair, smile, open mouth, ruffled blouse, red blouse, pleated skirt, blonde hair, green scarf, peace sign, blunt bangs, blue skirt, fang, hand on own hip, standing](nai-anime-v2-sample.png) This is our old, more capable SD1.5 based anime model. We are now making the weights publicly available for research and personal use. To keep the release compact, it only contains the Unet and VAE components. If you require the other components, you can copy them into the folder from the original [Stable Diffusion 1.4](https://huggingface.co/CompVis/stable-diffusion-v1-4) release. For convenience, are also providing a checkpoint in the classic ckpt format, but we have not verified its correctness. The model was trained using the text embeddings produced by CLIP's penultimate layer, so, depending on your inference software, you will need to set "CLIP skip" to 2. It supports 1 megapixel resolutions (e.g. 832x1216, 1024x1024 and 1216x832). References: * [Announcement blog post for V2](https://blog.novelai.net/introducing-novelai-diffusion-anime-v2-dc668ebca34b) * [NovelAI Improvements on Stable Diffusion](https://blog.novelai.net/novelai-improvements-on-stable-diffusion-e10d38db82ac) * [The Magic behind NovelAIDiffusion](https://blog.novelai.net/the-magic-behind-novelaidiffusion-b4797e0d27b2) * [NovelAI Aspect Ratio Bucketing Source Code Release (MIT Licensed)](https://blog.novelai.net/novelai-aspect-ratio-bucketing-source-code-release-mit-licensed-c33fdd25e4ad) You can always check out our latest models on the [NovelAI website](https://novelai.net/) or take a gander at our [blog](https://blog.novelai.net/). ## License This model is based upon Stable Diffusion 1.5. It is distributed under the terms of the CreativeML Open RAIL-M and the terms of the CC BY-NC-SA 4.0 license. This means that the terms of both licenses apply at the same time.