Download
1 variant available
bf16 SafeTensor
Anime background art style.safetensors
BF16, good balance • 175.11 MB
Verified: 6 days ago
4920 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
1 / 10 images
(77)
Aug 5, 2026

6.7K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
61.1K0 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K

License:
AnimaThe Anima Model is licensed by CircleStone Labs LLC. Copyright CircleStone Labs LLC. IN NO EVENT SHALL CIRCLESTONE LABS LLC BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.
Built on NVIDIA Cosmos
大家好,我是chosen鲷,这次给大家带来的是日系动画场景lora anima版本。
风格类似动画背景中的原画,还有一些新海诚的风格,但是也不完全是,配色偏青绿色,整体氛围明亮清新,适合生成那种有复杂城市或乡村景观的图片。
触发词:Anime background art style
推荐增加质量tag:
masterpiece, score 7, highres, absurdres, best quality, explicit, safe, sfw, scenery
multicolored这个tag可以给画面增加更多色彩,如果你不喜欢也可以去掉。
具体的tag信息大家可以看我的例图,值得注意的是,例图中的cfg和step信息是不正确的,我常用的是cfg1 step18(有加速lora的情况下),cfg4 step50(无加速lora的情况下),采样器是eular simple
大模型推荐使用chosen-mix_anima或者miaomiao anima V1.4(下方推荐),或者其他的anima模型也都可以使用。
具体的tag可以看我例图。
感谢大家的下载使用,如果喜欢的话欢迎关注我,我的bilibili pixiv ID均为chosen鲷,欢迎大家关注我的频道https://space.bilibili.com/3867754?spm_id_from=333.337.0.0 https://www.pixiv.net/users/102907778 谢谢。
The following content is from machine translation
Hello everyone, I am chosen-diao. This time, I am bringing you the Anima version of the Anime background art style LoRA.
The style is similar to the original background art in anime, with some hints of Makoto Shinkai's style, but not exactly the same. The color palette leans towards a refreshing cyan/teal-green, creating a bright and clear overall atmosphere. It is well-suited for generating complex urban or rural landscape images.
Trigger word: Anime background art style
Recommended quality tags:
masterpiece, score 7, highres, absurdres, best quality, explicit, safe, sfw, scenery
The multicolored tag can add more color variety to the image; you can remove it if you don't like it.
For specific tag details, please refer to my example images. Please note that the CFG and step information shown in the example images are incorrect. The settings I usually use are:
CFG 1, Steps 18 (when using the acceleration LoRA)
CFG 4, Steps 50 (without the acceleration LoRA)
The sampler is Euler simple.
For the base model, I recommend using Miaomiao Anima V1.4 (linked below), or other Anima models should also work well. You can check my example images for specific tags.
Thank you for downloading and using it. If you like it, please feel free to follow me. My Bilibili and Pixiv IDs are both chosen-diao. You are welcome to follow my channels:
https://space.bilibili.com/3867754?spm_id_from=333.337.0.0
https://www.pixiv.net/users/102907778
Thank you!
大家好,我是chosen鲷,这次给大家带来的是动画场景lora。
就是类似于动画中的背景原画,亦或是vituber直播的背景那种感觉的图,用了很多这类的场景素材,训练了这个lora,效果还蛮不错的,室内和室外场景都可以,很有意思。
推荐的tag:
(masterpiece:1.2), best quality,PIXIV,cozy animation scenes,scenery,<lora:cozy animation scenes_20230824111332-000018:1>Negative prompt: EasyNegative, badhandsv5-neg,Subtitles,(word:1.5),Steps: 32, Sampler: DPM++ 2M Karras, CFG scale: 5, Seed: 1890143821, Size: 800x400, Model hash: 0ac9feaf4e, Model: chosen impasto-mix, Denoising strength: 0.5, Clip skip: 2, Hires upscale: 2, Hires upscaler: R-ESRGAN 4x+ Anime6B, Lora hashes: "cozy animation scenes_20230824111332-000018: e858434aa9bf", Version: v1.4.1
关于大模型,首推ghost,兼容性非常棒,多种风格都能出,然后是majic fantasy效果也不错,但是这模型二次元方面不行,然后我的chosen mix与impasto也都行,例图可以读取tag,大家可以自行尝试。
感谢大家的下载使用,如果喜欢的话欢迎关注我,我的bilibili pixiv ID均为chosen鲷,欢迎大家关注我的频道https://space.bilibili.com/3867754?spm_id_from=333.1007.0.0,https://www.pixiv.net/users/40911695 谢谢。

