Ink-wash glass dragonExample 01nai-diffusion-5-full
NAI Diffusion 5 Full is a NovelAI image generation API on TTAPI for expressive anime art, broader subject coverage, detailed characters, and reference-guided workflows.
Ink-wash glass dragonExample 01
White-flower valley travelersExample 02
Post-apocalyptic survival UIExample 03
Night tactical duoExample 04Prompt to image, in context
水墨风,中国画,照片背景,风景,真实的,1.2::工笔画::,1.3::厚涂::,水彩,2::晕染::,最好的质量,大师之作,巨大的水潭,水边围着一些巨石,一条黑色的有鳞片的璃龙在水底下,红色的眼睛,从上面看,水面阵阵涟漪,一只非常小的鸟停在石头上, very aesthetic, masterpiece, no text, teXt: 潜龙勿用 NAI V5
2个女孩,双人战术小队,夜间荒野行动,夜间在崎岖的荒野中推进,战术行进,谨慎前进,保持警戒,注意周围环境,协同行动,一名女孩稍微领先,另一名女孩跟随在后,两人互相掩护,两人都在移动中举枪瞄准,枪械抵肩,通过机械瞄具进行瞄准,武器举起并处于随时可以射击的状态,佩戴夜视仪,开启夜视设备,安装在战术头戴装备上的夜视仪,夜视功能开启,通过夜视设备观察,低光环境,没有明显的手电筒光束,枪械上的战术手电关闭,手电筒关闭,关闭所有可见灯光,隐蔽的夜间行动,尽可能降低可见度,观察周围环境,高草丛,茂密植被,散落的岩石,黑暗森林,月光照耀下的荒野,深邃阴影,微弱月光,微弱环境光,真实的夜间氛围,专业战术装备,实用的战术装具,武器背带,通讯电台,详细的装备绑带与收纳袋,电影感构图
res_mult:10x sfw, 2::matt::, tapered lineart, rough lineart,bold lineart, dynamic angle, sketch, rough lineart, sketchy lineart, loose lineart, clothing folds, fabric wrinkles, rough sketch lines, acrylic paint (medium), リビング、テレビ、テーブル、ソファ、 犬の餌のお皿の食べた残骸、 実写背景、 , very aesthetic, masterpiece, no text, teXt: 私が食べました
vast valley, early morning, dense white flower field stretching toward distant mountains, two young travelers walking along a stone path through the flowers, old suitcases, torn maps, faded cloth flags scattered along the path, a huge abandoned bell tower in the distance, white flowering vines covering its stone walls, shattered clock face, a small stone monument standing in the middle of the flower field, dozens of withered bouquets placed in front of it, wind sweeping across the flower field, countless white petals rising into the air and drifting like ash, bright gentle sky, enormous gray storm clouds gathering above the distant horizon, the two travelers stopping and looking back toward the flower field, silent mourning, melancholic atmosphere, quiet beauty, abandoned landscape, sense of loss, remembrance, environmental storytelling, vast scale, distant mountains black jaggy lines,1.9::faux traditional media, ::watercolor effect::,, very aesthetic, masterpiece,res_mult:3x, Hand-painted illustration, painterly style, detailed fantasy concept art, traditional fantasy painting, watercolor and gouache texture, soft brush strokes, ornate storybook illustration, richly detailed illustration
Contemporary shoujo illustration, graceful tapered linework, delicate facial construction, long elegant eyelashes, luminous jewel-like eyes, soft rose blush, flowing ribbon-like hair, pale romantic gradients, gentle highlights, decorative simplicity, light airy finish, premium Japanese romance artbook aesthetic. high complexity , very aesthetic, masterpiece, no text, teXt: Novel AI V5!
solo,1girl,explorer girl, year 2026,very aesthetic, absurdres, best quality, res_mult:3x from side,Snowfield,outdoors,wide shot,solo focus walking,from behind,spread_arms,nature complex background,high complexity huge text,polaroid_photo,handwritten text,Postmark text:Come, see the cliffs and the desert!
画面是一张横向 2D 生存冒险游戏界面截图,采用俯视与等距视角结合的构图。场景位于一片阴暗、荒凉的针叶林或枯树林中,中央是一处废弃营地。背景遍布高大的灰色枯树、低矮灌木和斑驳的林地,整体使用灰绿、灰白、深灰和暗黄色调,具有低饱和、末日生存游戏的视觉风格。 营地位于画面中央偏右,由两顶灰绿色的简易帐篷组成。帐篷周围散落着数个金属油桶、木箱或杂物,中央有一处已经熄灭的篝火和几根木柴,旁边放着一把简易折叠椅。营地后方有一个被绿色轮廓高亮的装置,外形类似简易雨水收集器或净水设备,旁边悬浮着交互按钮“OBSERVE”和“SEARCH”。 画面右侧站着一名年轻女性角色,身体占据右下方区域,呈半身至大腿的近距离构图。她有黑色齐肩短发,厚重刘海遮住部分额头和眼睛,脸色苍白,表情疲惫而警惕,嘴唇紧闭。她穿着白色短袖上衣,颈部围着深灰色围巾,手臂缠有白色绷带,肩部带有背带或装备带,下身穿着深蓝色裤子。她双手握着一件黄色和黑色的简易工具或武器,身体略微转向左侧,似乎正在观察营地。人物轮廓带有醒目的黄色描边或高亮效果,右上方有一个写着“……”的对话气泡。 左侧是完整的游戏状态面板,包括角色简笔头像、装备栏、统计数据、记忆任务区域、状态条和物品栏。左上角能看到版本号“V1.01a”,右上角场景标题为“ABANDONED CAMP”。底部横跨画面的白色对话框中写着:“A HOMEMADE RAIN COLLECTOR, THERE IS STILL SOME GERM SOUP IN IT.” 右侧带有一个小型橙色下三角标记。 整体采用黑色粗线勾勒、有限色彩、半色调颗粒和复古漫画式数字插画风格,画面兼具生存游戏 UI、手绘图像小说和末日露营场景的特点。, very aesthetic, masterpiece, no text, teXt: OBSERVE SEARCH …… V1.01a ABANDONED CAMP A HOMEMADE RAIN COLLECTOR, THERE IS STILL SOME GERM SOUP IN IT.
year 2026, amazing quality, best quality, very aesthetic, high complexity, res_mult:1.5x, detailed texturea, subsurface_scattering, chromatic aberration, mud, dirt, grey skies, knights and vikings fighting on background,
tree branch, outdoors, sky, square background, yellow caption with text "hang in there!", transparent background, very aesthetic, masterpiece, no text, teXt: hang in there!
What you can build with nai-diffusion-5-full
Prompt driven generation
Submit a concise prompt and get production-ready image output through one TTAPI job.
Core controls only
Keep integration simple with prompt, model, output settings, and callback handling.
Async result flow
Use polling or webhook callbacks so long-running generations do not block your UI.
Ready for product UI
Return NovelAI results that can be displayed, stored, or passed into downstream workflows.
Per-action, in quota
Usage is metered in quota by model, action, and output settings.
Headers and submit parameters
Use the endpoint below with your TTAPI key and the request fields shown.
/novelai/text-to-imageSubmit a NovelAI text-to-image task.
Official reference/novelai/image-to-imageTransform a reference image with NovelAI.
Official reference/novelai/fetchRetrieve the generated NovelAI task result.
Official referenceHeaders
TT-API-KEYstringrequiredYour TTAPI API key.
Content-TypestringrequiredUse application/json.
Body
promptstringrequiredPositive illustration prompt.
modelenumrequirednai-diffusion-5-full, nai-diffusion-5-curated, nai-diffusion-4-5-full, or nai-diffusion-4-5-curated. Defaults to nai-diffusion-5-curated.
nintegeroptionalNumber of images to generate, from 1 to 4. Defaults to 1.
widthintegeroptionalOutput width in pixels. Defaults to 1024.
heightintegeroptionalOutput height in pixels. Defaults to 1024.
seedstringoptionalSeed used to reproduce or vary a generation.
stepsintegeroptionalDiffusion step count. Defaults to 23.
scalenumberoptionalPrompt guidance scale. Defaults to 5.
negative_promptstringoptionalElements and qualities to avoid.
quality_togglebooleanoptionalEnable the documented quality preset. Defaults to true.
samplerenumoptionalEuler Ancestral, Euler, DPM++ 2S Ancestral, DPM++ 2M SDE, DPM++ 2M, or DPM++ SDE. Defaults to Euler Ancestral.
noise_scheduleenumoptionalkarras, exponential, or polyexponential. Defaults to karras.
character_promptsobject[]optionalCharacter prompt and position definitions.
vibe_transferobject[]optionalAtmosphere reference images and strengths.
character_referenceobject[]optionalCharacter and style reference definitions.
hook_urlstringoptionalCallback URL for job completion.
From key to first result
Copy the resolved endpoint, authentication headers, and request body for this model.
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-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"}'