nai-diffusion-4-5-full

由 NovelAI 提供图像

NAI Diffusion 4.5 Full 可依据正向提示词、负向提示词和参考图生成插画、漫画和角色。

更新于:
输入提示词文本
模型4款可用
返回方式异步结果链接
价格8 quota / 张
Girl in a black dress reaching through candlelight in a gothic Victorian roomGothic candlelight示例 01
White-haired samurai in red armor posing beneath a cloudy moonCrimson samurai示例 02
Pastel painterly fox knight and elf wizard character duoFox knight and wizard示例 03
Futuristic cyborg ninja wielding a glowing blade amid sparksCyborg ninja示例 04
生成示例

从提示词到成图

1girl, black dress, reaching out, candlelight, victorian room, gothic, shadows, textured paint, looking at viewer

1boy, 1.5::amazing quality::, 1.5::masterpiece::, year 2025, solo, armor, helmet, mask, cyborg ninja, black hair, spiky hair, holding sword, katana, weapon, action pose, dynamic angle, motion blur, speed lines, orange accents, white armor, black bodysuit, mechanical, futuristic, cyberpunk, sparks, particles, bokeh, depth of field, dramatic lighting, warm lighting, sunset, combat, battle, science fiction, detailed armor, mecha, ninja, warrior, glowing, energy blade

1.5::amazing quality::,1.5::masterpiece::,year 2025,2girls, multiple girls, blue hair, long hair, ponytail, blue eyes, pointy ears, elf, sitting, lap pillow, purple hair, closed eyes, sleeping, smile, peaceful, flowers, flower field, outdoors, fantasy, armor, blue dress, white dress, striped, knee up, leaning against wall, wooden wall, sunlight, soft lighting, warm lighting, wholesome, relaxed, friendship, anime, detailed background, nature, grass, pink flowers, white flowers, serene, tranquil, afternoon, golden hour , location, very aesthetic, masterpiece, no text

1boy, masterpiece, best quality, dynamic angle, scar across eye, handsome, male focus, broad shoulders, smug, white hair, manly, long face, strong chin, long hair, silver hair, ponytail, parted bangs, red scabbard, samurai knight armor, red eyes, red armor, red headband, gold trim, skinny, tall male, young, dramatic sword pose, red cloudy sky, from below, monochrome, moon, very aesthetic, location, masterpiece, no text, -0.8::feet::, rating:general

2boys, outdoors, brick wall, blue sky, contrail, cowboy shot. Character 1: boy, leather jacket, chains, mutual#fist bump, grin, black eyes. Fist bump with spark. Character 2: boy, white shirt, torn shirt, mutual#fist bump, grin, brown eyes. Fist bump with spark.

1girl, cat girl, cat ears, pink hair, short hair, [[blue eyes]], school uniform, holding chalk, chalk, writing, classroom, chalkboard, text, english text. Writing on chalkboard can be seen saying "V4.5 Full" along with a heart, right next to the girl's head., location, very aesthetic, masterpiece, no text Text: V4.5 Full

2girls, multiple girls, deformed, very big eyes, white pupils, colored lineart, painterly, soft style, pastel colors, year 2025, location. Character 1: girl, furry female, fox girl, armor, sword, large breasts, :3, fang. Character 2: girl, wizard, wizard hat, staff, flat chest, :o, elf.

1girl, muscular female, faceless, tall female, long ponytail, white hair, large hat, silver dress, white gloves, glowing skin, glowing hair, dutch angle, wide shot, grand scale, ruins, sand castle, night sky, traditional media, painting (medium), painterly, location

background dataset, best quality, very aesthetic, concept art, no lines, rating:general, 1::thick brushstrokes::, 2::simple is best::, no humans, scenery, amazing quality, very aesthetic, a vibrant coastline, colored clouds, red clouds, purple clouds, pink clouds, water, beach, land on the right, ocean on the left, wispy clouds, location, very aesthetic, masterpiece, no text

模型能力

nai-diffusion-4-5-full 能做什么

根据提示词生成

提交简洁提示词,通过一个 TTAPI 任务获取图像结果。

常用参数

设置提示词、模型、输出参数和回调即可接入。

异步查询

通过轮询或 Webhook 接收结果,避免耗时生成阻塞界面。

接入产品

NovelAI 的输出可以展示、保存或交给后续流程处理。

计费

按操作计费,单位为 quota

按模型、操作和输出设置扣除 quota。

图像生成官方定价
模型价格计费单位
NAI Diffusion 5 Full · Curated8 quota / 张
NAI Diffusion 4.5 Full · Curated8 quota / 张
API 请求

请求头与提交参数

使用 TTAPI 密钥,按下方字段向接口发送请求。

POSThttps://api.ttapi.io/novelai/text-to-image

请求头

TT-API-KEYstring必填

填写 TTAPI API 密钥。

Content-Typestring必填

使用 application/json。

请求体

promptstring必填

描述想在插画中出现的内容。

modelenum必填

可选 nai-diffusion-5-full、nai-diffusion-5-curated、nai-diffusion-4-5-full、nai-diffusion-4-5-curated,默认 nai-diffusion-5-curated。

ninteger选填

生成图像数量,范围 1 至 4,默认 1。

widthinteger选填

输出宽度,单位为像素,默认 1024。

heightinteger选填

输出高度,单位为像素,默认 1024。

seedstring选填

复现或改变生成结果时使用的随机种子。

stepsinteger选填

扩散步数,默认 23。

scalenumber选填

提示词引导强度,默认 5。

negative_promptstring选填

描述要避免的元素或效果。

quality_toggleboolean选填

启用文档所述的质量预设,默认 true。

samplerenum选填

可选 Euler Ancestral、Euler、DPM++ 2S Ancestral、DPM++ 2M SDE、DPM++ 2M、DPM++ SDE,默认 Euler Ancestral。

noise_scheduleenum选填

可选 karras、exponential 或 polyexponential,默认 karras。

character_promptsobject[]选填

角色提示词与位置设置。

vibe_transferobject[]选填

氛围参考图及影响强度。

character_referenceobject[]选填

角色和风格参考设置。

hook_urlstring选填

任务完成时调用的回调 URL。

查看 TTAPI 接入文档
接入示例

发送请求并获取结果

复制当前模型的请求地址、鉴权请求头和请求体。

curl --request POST \
  --url https://api.ttapi.io/novelai/text-to-image \
  --header "TT-API-KEY: $TTAPI_KEY" \
  --header 'Content-Type: application/json' \
  --data '{"prompt":"anime character portrait, detailed eyes","model":"nai-diffusion-4-5-full","n":1,"width":1024,"height":1024,"steps":23,"scale":5,"quality_toggle":true,"sampler":"Euler Ancestral","noise_schedule":"karras","hook_url":"https://example.com/webhooks/novelai"}'