将其添加到不希望出现的内容字段中,看看是否可以阻止AI生成您不想看到的东西! 您还可以从Prompt框右上角的齿轮图标中选择一个预设,并将其与您自己的不希望出现的标签组合使用! 有时您需要从不同角度来避免在生成中出现某些问题。 例如:标签"freckles"可能会创建奇怪的伪影,因此如果您将"tattoo"添加到不希望出现的...
另外还有负prompt，即要求模型避免的 tag，常见如下（可按需求增减）：NSFW, furry, multiple breasts, ...
more than 1 right hand, deformed, (blurry), disfigured, missing legs, extra arms, extra thighs, more than 2 thighs, extra calf, fused calf, extra legs, bad knee, extra knee, more than 2 legs, bad tails, bad
Learn how to harness NovelAI's tools for enhancing your creative writing, from idea generation to story development.
Negative prompt: lowres, bad anatomy, bad hands, text,error, missing fngers,extra digt ,fewer digits,cropped, wort quality ,low quality,normal quality, jpeg artifacts,signature,watermark, username, blurry, bad feet,multiple breasts, (mutated hands and fingers:1.5 ), (long body :1.3), (muta...
Negative prompt: multiple breasts, (mutated hands and fingers:1.5 ), (long body :1.3), (mutation, poorly drawn :1.2) , black-white, bad anatomy, liquid body, liquid tongue, disfigured, malformed, mutated, anatomical nonsense, text font ui, error, malformed hands, long neck, blurred, ...
将novelAI模型按如下文件结构放置: ./models ├── Codeformer ├── ESRGAN ├── GFPGAN ├── hypernetworks │ ├── aini.pt │ ├── anime_2.pt │ ├── anime_3.pt │ ├── anime.pt │ ├── furry_2.pt │ ├── furry_3.pt ...
furry ,pony, pubic hair, mosaic, excrement, faeces, shit, futa, testis" image = pipe(prompt,height=height,width=width,num_inference_steps=steps,guidance_scale=cfg,seed=seed,negative_prompt=negative_prompt).images[0] print('Seed =1993459194', image.argument['seed']) display(image) save_image...
- 默认值:`'https://api.novelai.net'` API 服务器地址。如果你搭建了私服,可以将此项设置为你的服务器地址。 ## 功能设置 ### model - 类型:`'safe' | 'nai' | 'furry'` - 默认值:`'nai'` 默认的生成模型。 ### orient - 类型:`'portrait' | 'square' | 'landscape'` - 默认值:`'port...
Negative prompt: angle, hat, helment, cap, cat ear, fox ear, furry, personSteps: 37, Sampler: Euler a, CFG scale: 7, Seed: 1830121689, Size: 1024x576, Model hash: 925997e9, Batch size: 6, Batch pos: 0, Denoising strength: 0.9, Mask blur: 4Time taken: 1m 47.83sTorch active/...