API docs by Redocly

AliveAI API (1.0.0)

Download OpenAPI specification:

AliveAI: hello@AliveAi.app URL: https://aliveai.app

API documentation for AliveAI services. For custom integrations or business inquiries, please contact us.

How It Works

  1. Authenticate — choose one of the following methods:
    1. Log in via Member Login. Use the accessToken from the response as the Authorization header with the Bearer prefix.
    2. Log in via API Key. Create an API Key in the Dashboard and use it as the Authorization header with the Key prefix.
  2. Start a generation — the core endpoints are Create Image Generation and Create Video Generation. Copy the promptId from the response.
  3. Receive updates — connect to the WebSocket endpoint at wss://api.aliveai.app/ws/prompts/{promptId} to receive real-time progress and results.
    1. Optional (development only): Add the x-aliveai-request-blocking: true header to a generation request to receive a synchronous response. The connection stays open until generation is complete and the final result is returned in the response body. For production use, the WebSocket connection is strongly recommended — it provides live previews and status updates without blocking.

Enterprise White-Label Solutions

We offer enterprise-ready solutions for businesses that want to integrate state-of-the-art AI generation capabilities into their own platforms. Our unified API covers all aspects of AI generation, including image and video creation, character consistency, roleplay chat, and more. Adult content generation is supported, making the API suitable for a wide range of applications.

Our team can work with you to customize the API and services to meet your specific requirements. Contact us to learn how we can help you leverage our AI technology for your business.

Features

Image Generation

Image Generation
  • Generate high-quality images from text prompts.
  • Customizable parameters for style, resolution, and more.
  • Supported AI models. View Full overview: https://aliveai.app/ai-model-overview
string (Model)
Enum: "DEFAULT" "REALISM" "ANIME" "TEMPORARY" "CHARACTER_CREATOR" "ANIMA" "GROK" "SEEDDANCE" "ZIMAGE" "KREA"

Image Generation model to use.

Value Name Description
DEFAULT Creative v2 Versatile model with strong prompt understanding for realistic or creative characters and scenes.
REALISM Realism (Beta) Advanced model that produces highly photorealistic images with detailed skin and body rendering.
TEMPORARY Limited: Dreamy Realism V2 Limited-time experimental model — try it out and explore the latest AI styles.
CHARACTER_CREATOR Character Creator Build characters step by step by mixing attributes, outfits, scenes and styles.
ANIMA Anima 1.0 Versatile artistic model focused on anime and manga with strong creative capabilities.
GROK Grok Ultra Advanced model for realistic images with great prompt understanding. Does NOT support explicit content. Not available on private servers
ANIME Anime & Cartoon Stylized model for anime, hentai, manga and cartoon-inspired characters and scenes.
SEEDDANCE SeedDance High-quality image generation with strong prompt understanding. Not available on private servers.
ZIMAGE Social Media High-quality realistic images in authentic influencer style, like real Instagram photos.
Krea Krea Uncensored Creative Model with strong prompt understanding
"DEFAULT"

Video Generation

  • Create videos from existing images.
  • Includes audio and speech generation capabilities.
  • Customizable parameters for style, resolution, and more.
  • Supported video models:
string (VideoModel)
Enum: "DEFAULT" "AUDIO" "GROK" "SEEDANCE" "KLING"

Model used for image-to-video generation.

Value Name Description
DEFAULT Creative Standard image-to-video model — versatile, uncensored and works for most scenes. Use templates for more options.
AUDIO Video with Audio Generates video with audio including speech and background audio. Use the script option and templates for best results.
GROK Grok Video with Audio Grok-powered video model with audio and dialog. This model only supports safe (not explicit) content. Not supported on private servers.
SEEDANCE Video Pro Higher-quality, longer video generation with audio and better prompt understanding. Not supported on private servers.
KLING Kling Premium video model with advanced capabilities. This model only supports safe (not explicit) content. Not supported on private servers.
"DEFAULT"

Image Edit

Image Edit

Modify an existing image with a text prompt using the Edit Image Generation endpoint. Pass the source image as the mediaId and describe the change you want — the model preserves the rest of the image while applying your edit.

  • Edit faces, bodies, clothing, backgrounds and scenes from a natural-language prompt.
  • Keep edits minimal and prompts concise for the most faithful results.
  • Choose the model based on the type of edit and content you need.
  • Supported edit models:
string (EditModel)
Enum: "CREATIVE" "REALISM" "QWEN_PRO" "GROK" "SEEDDANCE"

Model used for image editing.

Value Name Description
REALISM Realism Photorealistic edits — best for natural-looking changes to faces, bodies and scenes.
QWEN_PRO Pro Edit Higher-quality model with strong prompt understanding for detailed, precise edits. Not supported on private servers.
CREATIVE Creative 2.0 Versatile creative model — flexible edits, stylization and broader scene changes.
GROK Grok Ultra Advanced model for realistic images with great prompt understanding. Does NOT support explicit content. Not supported on private servers.
SEEDDANCE SeedDance High-quality image editing with strong prompt understanding. Does NOT support explicit content. Not supported on private servers.
"CREATIVE"

Consistent Characters

Consistent Characters

Create and maintain consistent characters across multiple generations. This is ideal for storytelling, marketing campaigns, and any project that requires recurring characters with a consistent appearance and personality.

Creating Consistent Character Images

  1. Generate a character image using the Create Image Generation endpoint. For best results, use a clear front-facing image with a simple background. Minimal clothing (bikini or nudity) helps the model learn full-body details.
  2. Use that image as the reference (mediaId) in the Edit Image Generation endpoint. Start your prompt with something like: extract this person keep her appearance and body shape and same background. <add your prompt here> Choose the AI model based on your desired content type:
    • For realistic social media content, use the REALISM or QWEN_PRO model.
    • For nudity and pornographic content, use the CREATIVE or QWEN_PRO model.
    • For specific pornographic content, use a model with a matching Template (LoRA).
    • Note: For best results keep the changes minimal and the prompt concise.

Chatting with AI

Build immersive roleplay and conversational experiences with consistent AI characters. The chat API supports streamed responses, multiple alternative replies, and on-demand image generation that reflects the ongoing conversation.

Characters

Chat characters define who the user talks to. Each character has a name, a long-form bio used as system context (personality, background, scenario), a short bio for previews, and a default first message.

Personas

A persona represents the user inside the chat. It carries a display name and an optional bio that is sent to the character as part of the conversation context, so the character knows who they are talking to.

  • Manage personas via the Chat Persona Resource.
  • One persona can be marked as the default and is reused across new chats.

Starting and Managing Chats

  • Start a chat with Create Chat, supplying a chatCharacterId, a personaId, and the user's opening message.
  • List existing chats with Get Chats and fetch full message history (including all candidates) with Get Chat.
  • Delete a chat with Delete Chat.

Sending Messages (Streaming)

  • Post a user message with Send Chat Message. The response is an NDJSON stream of ChatStreamEvent objects — one JSON object per line — with the following event types:
    • init — stream metadata, including the new message id.
    • token — incremental text tokens as the character's reply is generated.
    • complete — final message payload once generation finishes.
    • error — terminal error event if generation fails.
  • This allows you to render the character's reply progressively, similar to a typing indicator.

Candidates, Regeneration, and Editing

Every character message can have multiple alternative replies (candidates), letting users swipe between variations.

  • Regenerate the most recent character reply as a new candidate with Regenerate Chat Message.
  • Edit the text of a specific candidate via the candidate update endpoint to fine-tune tone or fix details.
  • Delete individual messages from the chat history when needed.

In-Chat Image Generation

Characters can produce images that match the current narrative context.

  • Call Create Chat Image to generate a new image of the character based on the recent chat context. The image is appended to the chat as a media message.
  • Use Regenerate Chat Image to produce alternative image candidates for an existing media message.
  • Image generation reuses the character's reference image, so the visual identity stays consistent across the conversation.

Chat Character Resource

Endpoints for creating and managing chat characters, including AI-assisted character generation from images.

Submit Character

Creates a new chat character for the authenticated user. Optionally links an existing media as the character image.

Authorizations:
SecuritySchemeApiKeyScheme
Request Body schema: application/json
required
name
required
string [ 1 .. 50 ] characters

Display name of the character.

bio
required
string [ 1 .. 15000 ] characters

Long-form bio used as system context for the character. Should describe personality, background, scenario, etc.

shortBio
required
string [ 1 .. 1000 ] characters

Short bio shown in lists and previews.

firstMessage
required
string [ 1 .. 15000 ] characters

Default first message the character sends when a new chat is started.

mediaId
string

Optional public id of an existing media to use as the character image.

promptId
string

Optional id of the prompt that produced the linked mediaId. Only relevant when mediaId is set.

Responses

Request samples

Content type
application/json
{
  • "name": "string",
  • "bio": "string",
  • "shortBio": "string",
  • "firstMessage": "string",
  • "mediaId": "string",
  • "promptId": "string"
}

Response samples

Content type
application/json
{
  • "chatCharacterId": "string"
}

Get Characters For User

Lists all non-deleted chat characters owned by the authenticated user.

Authorizations:
SecuritySchemeApiKeyScheme

Responses

Response samples

Content type
application/json
[
  • {
    }
]

Create From Image

Generates a character card (description, personality, scenario, first message, tags) from an image URL using a vision model. Rate limited per user. Contact support if you need to increase your limit.

Authorizations:
SecuritySchemeApiKeyScheme
Request Body schema: application/json
required
imageUrl
required
string

Public URL of the source image. The vision model will analyze appearance, clothing and setting from this image.

characterName
required
string

Name to assign to the generated character.

Responses

Request samples

Content type
application/json
{
  • "imageUrl": "string",
  • "characterName": "string"
}

Response samples

Content type
application/json
{
  • "name": "string",
  • "description": "string",
  • "personality": "string",
  • "scenario": "string",
  • "first_mes": "string"
}

Create From Text

Generates a character card (name, description, personality, scenario, first message) from a short free-form character description using an LLM. Missing details and a name are invented if not provided. Rate limited per user. Contact support if you need to increase your limit.

Authorizations:
SecuritySchemeApiKeyScheme
Request Body schema: application/json
required
characterDescription
required
string [ 2 .. 500 ] characters \S

Short free-form description of the desired character. The LLM expands it into a full character card, inventing any missing details and a fitting name if none is given.

Responses

Request samples

Content type
application/json
{
  • "characterDescription": "string"
}

Response samples

Content type
application/json
{
  • "name": "string",
  • "description": "string",
  • "personality": "string",
  • "scenario": "string",
  • "first_mes": "string"
}

Update Character Card

Refines an existing AI-generated character card based on a free-form update prompt. Rate limited per user. Contact support if you need to increase your limit.

Authorizations:
SecuritySchemeApiKeyScheme
Request Body schema: application/json
required
required
object (ChatCharacterCardResponse)

The current AI-generated character card to refine. Pass back the response from generateCharacterFromImage unchanged.

updatePrompt
required
string

Free-form instruction describing how the character should be modified (e.g. 'make her more shy' or 'change setting to a beach').

Responses

Request samples

Content type
application/json
{
  • "chatCharacterFromImageResponse": {
    },
  • "updatePrompt": "string"
}

Response samples

Content type
application/json
{
  • "name": "string",
  • "description": "string",
  • "personality": "string",
  • "scenario": "string",
  • "first_mes": "string"
}

Get Character

Returns a chat character by its public id, or null if it does not exist.

Authorizations:
SecuritySchemeApiKeyScheme
path Parameters
id
required
string

Responses

Response samples

Content type
application/json
{
  • "chatCharacterId": "string",
  • "characterName": "string",
  • "characterBio": "string",
  • "shortBio": "string",
  • "firstMessage": {
    },
  • "characterImage": {
    }
}

Delete Character

Soft-deletes a chat character. The character is hidden from listings but existing chats with it remain.

Authorizations:
SecuritySchemeApiKeyScheme
path Parameters
id
required
string

Responses

Update Character

Updates name, bio, short bio and first message of an existing chat character. The first message is replaced with a new one.

Authorizations:
SecuritySchemeApiKeyScheme
path Parameters
id
required
string
Request Body schema: application/json
required
name
required
string [ 1 .. 50 ] characters

Display name of the character.

bio
required
string [ 1 .. 15000 ] characters

Long-form bio used as system context for the character. Should describe personality, background, scenario, etc.

shortBio
required
string [ 1 .. 1000 ] characters

Short bio shown in lists and previews.

firstMessage
required
string [ 1 .. 15000 ] characters

Default first message the character sends when a new chat is started.

mediaId
string

Optional public id of an existing media to use as the character image.

promptId
string

Optional id of the prompt that produced the linked mediaId. Only relevant when mediaId is set.

Responses

Request samples

Content type
application/json
{
  • "name": "string",
  • "bio": "string",
  • "shortBio": "string",
  • "firstMessage": "string",
  • "mediaId": "string",
  • "promptId": "string"
}

Chat Persona Resource

Endpoints for managing user personas. A persona controls how the user is presented to a character in a chat.

Get Personas

Lists all personas owned by the authenticated user.

Authorizations:
SecuritySchemeApiKeyScheme

Responses

Response samples

Content type
application/json
[
  • {
    }
]

Create Persona

Creates a new persona for the authenticated user. If marked as default, any previous default persona is unset.

Authorizations:
SecuritySchemeApiKeyScheme
Request Body schema: application/json
required
name
required
string [ 1 .. 20 ] characters

Display name of the persona.

bio
string <= 150 characters

Optional bio describing the persona. Sent to the character as part of the chat context.

isDefault
required
boolean

If true, this persona becomes the user's default and any previous default is unset.

Responses

Request samples

Content type
application/json
{
  • "name": "string",
  • "bio": "string",
  • "isDefault": true
}

Response samples

Content type
application/json
{
  • "id": "string",
  • "name": "string",
  • "bio": "string",
  • "defaultPersona": true
}

Get Persona For Chat

Returns the persona that is associated with the given chat.

Authorizations:
SecuritySchemeApiKeyScheme
path Parameters
chatId
required
string

Responses

Response samples

Content type
application/json
{
  • "id": "string",
  • "name": "string",
  • "bio": "string",
  • "defaultPersona": true
}

Delete Persona

Deletes a persona. Fails if the persona is the only one of the user or if it is still used in any chat.

Authorizations:
SecuritySchemeApiKeyScheme
path Parameters
id
required
string

Responses

Update Persona

Updates name, bio and default flag of an existing persona. If marked as default, any previous default persona is unset.

Authorizations:
SecuritySchemeApiKeyScheme
path Parameters
id
required
string
Request Body schema: application/json
required
name
required
string [ 1 .. 20 ] characters

Display name of the persona.

bio
string <= 150 characters

Optional bio describing the persona. Sent to the character as part of the chat context.

isDefault
required
boolean

If true, this persona becomes the user's default and any previous default is unset.

Responses

Request samples

Content type
application/json
{
  • "name": "string",
  • "bio": "string",
  • "isDefault": true
}

Chat Resource

Endpoints for managing character chats, streaming chat completions and generating chat images.

Get Chats

Lists all character chats belonging to the authenticated user.

Authorizations:
SecuritySchemeApiKeyScheme

Responses

Response samples

Content type
application/json
[
  • {
    }
]

Create Chat With Custom First Message

Creates a new chat with a character, seeded with a caller-provided first message from the character.

Authorizations:
SecuritySchemeApiKeyScheme
Request Body schema: application/json
required
chatCharacterId
required
string

Public id of the character to chat with.

firstMessage
required
string

Opening message attributed to the character. Shown as the first message in the chat.

personaId
required
string

Public id of the user persona to chat as. The persona controls how the user is presented to the character.

object (ChatSettings)

Effective roleplay style settings of the chat. Optional. If omitted the recommended defaults are used

Responses

Request samples

Content type
application/json
{
  • "chatCharacterId": "string",
  • "firstMessage": "string",
  • "personaId": "string",
  • "settings": {
    }
}

Response samples

Content type
application/json
{
  • "chatId": "string",
  • "chatCharacterId": "string",
  • "messages": [
    ],
  • "settings": {
    },
  • "chatNote": "string",
  • "memory": "string"
}

Get Chat

Returns the chat with all messages and selected candidates.

Authorizations:
SecuritySchemeApiKeyScheme
path Parameters
chatId
required
string

Responses

Response samples

Content type
application/json
{
  • "chatId": "string",
  • "chatCharacterId": "string",
  • "messages": [
    ],
  • "settings": {
    },
  • "chatNote": "string",
  • "memory": "string"
}

Delete Chat

Deletes a chat owned by the authenticated user.

Authorizations:
SecuritySchemeApiKeyScheme
path Parameters
chatId
required
string

Responses

Create Chat Image

Generates an image of the character based on the recent chat context and appends it to the chat as a new media message.

Authorizations:
SecuritySchemeApiKeyScheme
path Parameters
chatId
required
string
query Parameters
serverId
string

Optional id of a private AliveAI server to route the generation through for faster results.

Request Body schema: application/json
required
prompt
string or null <= 500 characters

Optional image generation prompt (max 500 characters). When provided, this prompt is used directly to generate the image. When omitted or blank, a prompt is generated automatically from the recent chat history and character context. Leave empty for the recommended automatic behaviour.

(EditModel (string or null)) or (string or null)
Default: "CREATIVE"

Optional image generation edit model. When provided, this model is used to generate the image. When omitted, the default CREATIVE (recommended) model is used.

Responses

Request samples

Content type
application/json
{
  • "prompt": "extract this person keep her appearance and body shape. standing on windy beach tight and cute sundress, warm sunset",
  • "editModel": "CREATIVE"
}

Response samples

Content type
application/json
{
  • "messageId": "string",
  • "selectedCandidateId": "string",
  • "candidates": [
    ],
  • "messageType": "USER"
}

Regenerate Image

Regenerates the image of an existing media message as a new candidate using the current chat context.

Authorizations:
SecuritySchemeApiKeyScheme
path Parameters
chatId
required
string
messageId
required
string
query Parameters
serverId
string

Optional id of a private AliveAI server to route the generation through for faster results.

Request Body schema: application/json
required
prompt
string or null <= 500 characters

Optional image generation prompt (max 500 characters). When provided, this prompt is used directly to generate the image. When omitted or blank, a prompt is generated automatically from the recent chat history and character context. Leave empty for the recommended automatic behaviour.

(EditModel (string or null)) or (string or null)
Default: "CREATIVE"

Optional image generation edit model. When provided, this model is used to generate the image. When omitted, the default CREATIVE (recommended) model is used.

Responses

Request samples

Content type
application/json
{
  • "prompt": "extract this person keep her appearance and body shape. standing on windy beach tight and cute sundress, warm sunset",
  • "editModel": "CREATIVE"
}

Response samples

Content type
application/json
{
  • "messageId": "string",
  • "selectedCandidateId": "string",
  • "candidates": [
    ],
  • "messageType": "USER"
}

Update Chat Memory

Overwrites the chat memory ('Story So Far') with user-provided text, or — when memory is null/blank — discards it and regenerates the memory from the chat history. Returns the new effective memory; null when the chat is too short to need one.

Authorizations:
SecuritySchemeApiKeyScheme
path Parameters
chatId
required
string
Request Body schema: application/json
required
memory
string <= 3500 characters

New memory text. Null or blank requests a regeneration.

Responses

Request samples

Content type
application/json
{
  • "memory": "string"
}

Response samples

Content type
application/json
{
  • "memory": "string"
}

Send Message

Sends a user message to the character and streams the assistant response as NDJSON

Authorizations:
SecuritySchemeApiKeyScheme
path Parameters
chatId
required
string
Request Body schema: application/json
required
userMessage
required
string [ 1 .. 4000 ] characters

Text of the user message to send to the character.

Responses

Request samples

Content type
application/json
{
  • "userMessage": "string"
}

Response samples

Content type
application/x-ndjson
Example
{
  • "type": "init",
  • "chatId": "string",
  • "userMessageId": "string",
  • "userCandidateId": "string",
  • "assistantMessageId": "string",
  • "assistantCandidateId": "string"
}

Delete Messages

Deletes the given message and all messages that follow it in the chat.

Authorizations:
SecuritySchemeApiKeyScheme
path Parameters
chatId
required
string
messageId
required
string

Responses

Update Selected Candidate

Switches the selected candidate of a message to a different existing candidate.

Authorizations:
SecuritySchemeApiKeyScheme
path Parameters
chatId
required
string
messageId
required
string
query Parameters
candidateId
required
string

Id of the candidate to mark as selected.

Responses

Update Candidate Message

Updates the text content of a single message candidate.

Authorizations:
SecuritySchemeApiKeyScheme
path Parameters
candidateId
required
string
chatId
required
string
messageId
required
string
Request Body schema: application/json
required
message
required
string [ 1 .. 20000 ] characters

New text content for the candidate. Replaces the previous text in full.

Responses

Request samples

Content type
application/json
{
  • "message": "string"
}

Regenerate Message

Regenerates the last character message of the chat as a new candidate and streams it as NDJSON. Only the most recent character message can be regenerated.

Authorizations:
SecuritySchemeApiKeyScheme
path Parameters
chatId
required
string
messageId
required
string

Responses

Response samples

Content type
application/x-ndjson
Example
{
  • "type": "init",
  • "chatId": "string",
  • "userMessageId": "string",
  • "userCandidateId": "string",
  • "assistantMessageId": "string",
  • "assistantCandidateId": "string"
}

Update Chat Note

Sets or overwrites the free-text note attached to a chat

Authorizations:
SecuritySchemeApiKeyScheme
path Parameters
chatId
required
string
Request Body schema: application/json
required
note
string <= 200 characters

Note text for the chat. Replaces any existing note in full. May be null or empty to clear the note.

Responses

Request samples

Content type
application/json
{
  • "note": "string"
}

Update Chat Settings

Sets or overwrites the roleplay style settings of a chat (prose style, POV, NSFW mode, response length, ...). Omitted fields fall back to the recommended defaults. Returns the effective settings.

Authorizations:
SecuritySchemeApiKeyScheme
path Parameters
chatId
required
string
Request Body schema: application/json
required
proseStyle
string (ProseStyle)
Enum: "STORY" "CINEMATIC"

Narrative prose style. STORY = novel-like, atmospheric with emotional flourish. CINEMATIC = gritty show-don't-tell realism. Default: CINEMATIC.

pov
string (Pov)
Enum: "FIRST" "SECOND" "THIRD" "HYBRID"

Point of view of the narration. HYBRID narrates in 3rd person but describes the user's physical sensations in 2nd person. Default: HYBRID.

nsfwMode
string (NsfwMode)
Enum: "ROMANTIC" "REALISM" "FREAKY"

Mature content style. ROMANTIC = suggestive but non-graphic. REALISM = explicit only when the story naturally goes there. FREAKY = erotic tension woven into every scene. Default: REALISM.

echoMode
string (EchoMode)
Enum: "ANTI_ECHO" "EMBELLISH"

How the character handles the user's written actions. ANTI_ECHO = never repeat or narrate the user's input. EMBELLISH = retell the user's actions enriched with detail. Default: ANTI_ECHO.

responseLength
string (ResponseLength)
Enum: "SHORT" "MEDIUM" "LONG"

Target length of character replies. Default: SHORT.

realisticCharacters
boolean

Characters are bold and fallible: they commit fully to actions, pursue their own goals and may refuse or confront the user. Default: true.

antiOmniscience
boolean

Characters only know what they have witnessed or been told; no mind reading or sensing unseen events. Default: true.

antiRepetition
boolean

Forbid reusing sensory details and phrases from recent messages. Default: true.

emotionalRealism
boolean

Emotions visibly shape actions, tone and pacing instead of being named. Default: true.

Responses

Request samples

Content type
application/json
{
  • "proseStyle": "STORY",
  • "pov": "FIRST",
  • "nsfwMode": "ROMANTIC",
  • "echoMode": "ANTI_ECHO",
  • "responseLength": "SHORT",
  • "realisticCharacters": true,
  • "antiOmniscience": true,
  • "antiRepetition": true,
  • "emotionalRealism": true
}

Response samples

Content type
application/json
{
  • "proseStyle": "STORY",
  • "pov": "FIRST",
  • "nsfwMode": "ROMANTIC",
  • "echoMode": "ANTI_ECHO",
  • "responseLength": "SHORT",
  • "realisticCharacters": true,
  • "antiOmniscience": true,
  • "antiRepetition": true,
  • "emotionalRealism": true
}

Prompts Manager Resource

Endpoints for managing completed prompts.

Get Prompts

Authorizations:
SecuritySchemeApiKeyScheme
query Parameters
page
required
integer <int32> >= 0
pageSize
integer <int32> <= 20
promptType
Array of strings (PromptType)
Items Enum: "IMAGE_DEFAULT" "VIDEO_EXPRESSION" "FACE_IMPROVE" "AFTER_FACE_SWAP" "EDIT_BREASTS" "PORTRAIT" "IMAGE_TO_VIDEO" "EXTEND_VIDEO" "UPSCALE_VIDEO" "INPAINT" "IMPROVE_EYES" "GOOGLE_INPAINT" "EDIT_IMAGE" "EDIT_VIDEO_INCREASE_FPS" "EDIT_UPSCALE_IMAGE" "CHARACTER_IMAGE" "EDIT_IMPROVE_FACE" "CREATE_FACE" "EDIT_ENHANCE" "EDIT_VAGINA" "CHARACTER_TRAINING_DATA" "CREATE_CLOTHES"
query
string

Search query

Responses

Response samples

Content type
application/json
{
  • "prompts": [
    ],
  • "hasNextPage": true,
  • "totalPageCount": 0
}

Get Prompt

Authorizations:
SecuritySchemeApiKeyScheme
path Parameters
promptId
required
string

Responses

Response samples

Content type
application/json
{
  • "promptId": "string",
  • "originalPrompt": {
    },
  • "originalVideoExpressionPrompt": {
    },
  • "faceImprovePrompt": {
    },
  • "afterFaceSwapPrompt": {
    },
  • "editBreastsRequest": {
    },
  • "createPortraitRequest": {
    },
  • "imageToVideoRequest": {
    },
  • "inpaintRequest": {
    },
  • "eyeImproveRequest": {
    },
  • "googleInpaintRequest": {
    },
  • "editVideoIncreaseFpsRequest": {
    },
  • "createExtendVideoRequest": {
    },
  • "createEditImageRequest": {
    },
  • "createUpscaleImageRequest": {
    },
  • "createUpscaleVideoRequest": {
    },
  • "createCharacterImageRequest": {
    },
  • "createEditImproveFaceRequest": {
    },
  • "createFaceRequest": {
    },
  • "createEnhanceImageRequest": {
    },
  • "createEditVaginaRequest": {
    },
  • "createCharacterTrainingDataRequest": {
    },
  • "createClothesImageRequest": {
    },
  • "isFavorite": true,
  • "medias": [
    ],
  • "creditCost": 0
}

Delete Prompt

Deletes a completed prompt

Authorizations:
SecuritySchemeApiKeyScheme
path Parameters
promptId
required
string

Responses

Prompts Resource

Endpoints for creating and managing prompt queue for image and video generation.

Create Prompt

Create a new prompt for image generation

Authorizations:
SecuritySchemeApiKeyScheme
query Parameters
serverId
string

Optional server ID to use for prompt processing. If empty it will select an available server.

header Parameters
x-aliveai-request-blocking
boolean

Returns a synchronous response with the generation result. Waits max 40 seconds for the generation to complete.

Request Body schema: application/json
required
seed
string^\d{1,18}$

Optional seed for image generation. Must be a numeric string (max 18 digits).

name
required
string <= 200 characters

Name of the character. Affects the characters face. A unique and realistic First and Last name is recommended.

appearance
required
string <= 1500 characters

Describe the appearance of the character.

gender
string (Gender)
Enum: "MALE" "FEMALE" "TRANS"
background
string <= 1000 characters
fromLocation
string <= 100 characters
faceDetails
string <= 1000 characters

Details only affecting the face

faceImproveEnabled
boolean
Default: true

If enabled it will improve the face using the faceDetails prompt.

faceModel
string (FaceModel)
Default: "REALISM"
Enum: "REALISM" "CREATIVE"

Specify the model used for the face improve step. Only applies if faceImproveEnabled is true.

faceImproveStrength
integer <int32> [ 0 .. 10 ]
Default: 5

Strength of the face details improvement. Higher values will make the face details more dominant but can also lead to less coherent images. Only applies if faceImproveEnabled is true. Recommended default value is 5.

negativeDetails
string <= 1000 characters

Negative details to avoid in the image generation.

scene
string <= 1000 characters

Additional scene details to enhance the image generation.

object (PoseRequest)
object (FaceSwapRequest)

Optional Face swap configuration

model
string (Model)
Enum: "DEFAULT" "REALISM" "ANIME" "TEMPORARY" "CHARACTER_CREATOR" "ANIMA" "GROK" "SEEDDANCE" "ZIMAGE" "KREA"

Image Generation model to use.

Value Name Description
DEFAULT Creative v2 Versatile model with strong prompt understanding for realistic or creative characters and scenes.
REALISM Realism (Beta) Advanced model that produces highly photorealistic images with detailed skin and body rendering.
TEMPORARY Limited: Dreamy Realism V2 Limited-time experimental model — try it out and explore the latest AI styles.
CHARACTER_CREATOR Character Creator Build characters step by step by mixing attributes, outfits, scenes and styles.
ANIMA Anima 1.0 Versatile artistic model focused on anime and manga with strong creative capabilities.
GROK Grok Ultra Advanced model for realistic images with great prompt understanding. Does NOT support explicit content. Not available on private servers
ANIME Anime & Cartoon Stylized model for anime, hentai, manga and cartoon-inspired characters and scenes.
SEEDDANCE SeedDance High-quality image generation with strong prompt understanding. Not available on private servers.
ZIMAGE Social Media High-quality realistic images in authentic influencer style, like real Instagram photos.
Krea Krea Uncensored Creative Model with strong prompt understanding
modelTemplate
string (ModelTemplate)
Deprecated
Enum: "BUKKAKE" "FEET" "SELFIE" "LESBIAN" "SOCIALMEDIA"
Array of objects (TemplateRequest) [ 1 .. 10 ] items
blockExplicitContent
boolean

If enabled AI will avoid nudity. Works best with DEFAULT AI model

detailLevel
required
string (DetailLevel)
Enum: "MEDIUM" "HIGH"
aspectRatio
string (AspectRatio)
Enum: "DEFAULT" "SQUARE" "PORTRAIT" "LANDSCAPE"
cfg
integer <int32> [ 1 .. 10 ]
Default: 5

Classifier-Free Guidance scale. Higher values will make the image generation more closely follow the prompt, but can also lead to less coherent images. Recommended default value is 5.

object (ClothesRequest)

Optional clothes configuration. Only applies to the CHARACTER_CREATOR model and will be ignored for other models.

object

Optional prompt metadata. Not used for image generation but can be used to store additional information about the prompt

Responses

Request samples

Content type
application/json
{
  • "name": "Marcielle Strongmaid",
  • "appearance": "a strong viking woman, blonde hair, hazel eyes, powerful face, wearing revealing viking armour, full body",
  • "gender": "FEMALE",
  • "fromLocation": "NORWAY",
  • "faceImproveEnabled": true,
  • "model": "DEFAULT"
}

Response samples

Content type
application/json
{
  • "promptId": "string",
  • "seed": "string",
  • "promptContainer": {
    }
}

Create After Face Swap

Changes the face of an existing image

Authorizations:
SecuritySchemeApiKeyScheme
query Parameters
serverId
string
Request Body schema: application/json
required
seed
string
mediaId
required
string
required
object (FaceSwapRequest)
createdFromPromptId
string

Responses

Request samples

Content type
application/json
{
  • "seed": "string",
  • "mediaId": "string",
  • "faceSwap": {
    },
  • "createdFromPromptId": "string"
}

Response samples

Content type
application/json
{
  • "promptId": "string",
  • "seed": "string",
  • "promptContainer": {
    }
}

Create Character Image

Authorizations:
SecuritySchemeApiKeyScheme
query Parameters
serverId
string
Request Body schema: application/json
required
seed
string^\d{1,18}$

Optional seed for image generation. Must be a numeric string (max 18 digits).

prompt
required
string <= 1000 characters
profileId
required
string
aspectRatio
required
string (AspectRatio)
Enum: "DEFAULT" "SQUARE" "PORTRAIT" "LANDSCAPE"
highResolution
required
boolean
characterType
required
string (CharacterType)
Enum: "ZIMAGE" "FLUX"
Array of objects (QwenTemplateRequest) [ 1 .. 5 ] items
characterStrength
number <double> [ 0 .. 2 ]
object (PoseRequest)

Optional pose information for the character. If provided, it will influence the character's pose in the generated image. Only for character type FLUX

object (ClothesRequest)

Optional clothes information for the character. If provided, it will influence the character's clothing in the generated image. Only for character type FLUX

improveFace
required
boolean
improveBreasts
required
boolean
improveVagina
required
boolean

Responses

Request samples

Content type
application/json
{
  • "seed": "string",
  • "prompt": "string",
  • "profileId": "string",
  • "aspectRatio": "DEFAULT",
  • "highResolution": true,
  • "characterType": "ZIMAGE",
  • "modelTemplates": [
    ],
  • "characterStrength": 2,
  • "pose": {
    },
  • "clothesRequest": {
    },
  • "improveFace": true,
  • "improveBreasts": true,
  • "improveVagina": true
}

Response samples

Content type
application/json
{
  • "promptId": "string",
  • "seed": "string",
  • "promptContainer": {
    }
}

Create Character Training Data

Authorizations:
SecuritySchemeApiKeyScheme
query Parameters
serverId
string
Request Body schema: application/json
required
seed
string
mediaId
required
string
createdFromPromptId
required
string
prompt
required
string <= 300 characters

Responses

Request samples

Content type
application/json
{
  • "seed": "string",
  • "mediaId": "string",
  • "createdFromPromptId": "string",
  • "prompt": "string"
}

Response samples

Content type
application/json
{
  • "promptId": "string",
  • "seed": "string",
  • "promptContainer": {
    }
}

Create Clothes

Extracts the outfit from an input image and returns a clean front/back clothing collage.

Authorizations:
SecuritySchemeApiKeyScheme
query Parameters
serverId
string
Request Body schema: application/json
required
seed
string^\d{1,18}$

Optional seed for image generation. Must be a numeric string (max 18 digits).

mediaId
required
string

Responses

Request samples

Content type
application/json
{
  • "seed": "string",
  • "mediaId": "string"
}

Response samples

Content type
application/json
{
  • "promptId": "string",
  • "seed": "string",
  • "promptContainer": {
    }
}

Create Face

Authorizations:
SecuritySchemeApiKeyScheme
query Parameters
serverId
string
Request Body schema: application/json
required
seed
string^\d{1,18}$

Optional seed for image generation. Must be a numeric string (max 18 digits).

faceCreationModel
required
string (FaceCreationModel)
Default: "DEFAULT"
Enum: "DEFAULT" "NANOBANANA"
prompt
required
string <= 500 characters
extraRandomness
required
boolean

Add more randomness to the face generation. This can lead to more unique and varied results, but may also result in less consistent faces across generations with the same prompt. Only for model DEFAULT

createdFromPromptId
string

Responses

Request samples

Content type
application/json
{
  • "seed": "string",
  • "faceCreationModel": "DEFAULT",
  • "prompt": "string",
  • "extraRandomness": true,
  • "createdFromPromptId": "string"
}

Response samples

Content type
application/json
{
  • "promptId": "string",
  • "seed": "string",
  • "promptContainer": {
    }
}

Create Edit Breasts

Authorizations:
SecuritySchemeApiKeyScheme
query Parameters
serverId
string
Request Body schema: application/json
required
seed
string
mediaId
required
string
createdFromPromptId
string

Responses

Request samples

Content type
application/json
{
  • "seed": "string",
  • "mediaId": "string",
  • "createdFromPromptId": "string"
}

Response samples

Content type
application/json
{
  • "promptId": "string",
  • "seed": "string",
  • "promptContainer": {
    }
}

Edit Eyes

Authorizations:
SecuritySchemeApiKeyScheme
query Parameters
serverId
string
Request Body schema: application/json
required
seed
string
mediaId
required
string
createdFromPromptId
required
string
text
required
string non-empty

Responses

Request samples

Content type
application/json
{
  • "seed": "string",
  • "mediaId": "string",
  • "createdFromPromptId": "string",
  • "text": "string"
}

Response samples

Content type
application/json
{
  • "promptId": "string",
  • "seed": "string",
  • "promptContainer": {
    }
}

Edit Image

Edit an existing image with a text prompt. Can be used to edit an image or re-use a character from an image in a new scene, outfit or pose

Authorizations:
SecuritySchemeApiKeyScheme
query Parameters
serverId
string
header Parameters
x-aliveai-request-blocking
boolean

Returns a synchronous response with the generation result. Waits max 40 seconds for the generation to complete.

Request Body schema: application/json
required
editModel
required
string (EditModel)
Enum: "CREATIVE" "REALISM" "QWEN_PRO" "GROK" "SEEDDANCE"

Model used for image editing.

Value Name Description
REALISM Realism Photorealistic edits — best for natural-looking changes to faces, bodies and scenes.
QWEN_PRO Pro Edit Higher-quality model with strong prompt understanding for detailed, precise edits. Not supported on private servers.
CREATIVE Creative 2.0 Versatile creative model — flexible edits, stylization and broader scene changes.
GROK Grok Ultra Advanced model for realistic images with great prompt understanding. Does NOT support explicit content. Not supported on private servers.
SEEDDANCE SeedDance High-quality image editing with strong prompt understanding. Does NOT support explicit content. Not supported on private servers.
seed
string^\d{1,18}$

Optional seed for image generation. Must be a numeric string (max 18 digits).

mediaId
required
string

The media ID of the original image to be edited.

createdFromPromptId
required
string

The ID of the prompt used to create the original image.

ignoreFace
required
boolean

Ignore the face during editing. If true, the face and head will not be modified. Only applicable for editModel CREATIVE

restoreFace
required
boolean

Restores the face after editing in order to preserve the original face details. Only applicable for editModel CREATIVE and REALISM

prompt
string <= 800 characters
object (PoseRequest)
object (ClothesRequest)
Array of objects (QwenTemplateRequest) [ 1 .. 5 ] items

List of model templates to apply during editing. Each template includes an ID, strength (0-10), and an optional template prompt. Maximum of 5 templates can be applied. Only applicable for editModel CREATIVE and REALISM

maskMediaId
string

Responses

Request samples

Content type
application/json
{
  • "editModel": "CREATIVE",
  • "seed": "string",
  • "mediaId": "string",
  • "createdFromPromptId": "string",
  • "ignoreFace": true,
  • "restoreFace": true,
  • "prompt": "string",
  • "pose": {
    },
  • "clothesRequest": {
    },
  • "modelTemplates": [
    ],
  • "maskMediaId": "string"
}

Response samples

Content type
application/json
{
  • "promptId": "string",
  • "seed": "string",
  • "promptContainer": {
    }
}

Create Edit Improve Face

Authorizations:
SecuritySchemeApiKeyScheme
query Parameters
serverId
string
Request Body schema: application/json
required
seed
string
mediaId
required
string
faceDetails
string
createdFromPromptId
required
string

Responses

Request samples

Content type
application/json
{
  • "seed": "string",
  • "mediaId": "string",
  • "faceDetails": "string",
  • "createdFromPromptId": "string"
}

Response samples

Content type
application/json
{
  • "promptId": "string",
  • "seed": "string",
  • "promptContainer": {
    }
}

Upscale Image

Authorizations:
SecuritySchemeApiKeyScheme
query Parameters
serverId
string
Request Body schema: application/json
required
seed
string
mediaId
required
string
createdFromPromptId
required
string
restoreFace
required
boolean
prompt
string <= 2000 characters
strength
number <double>
upscaleModel
string (UpscaleModel)
Enum: "DEFAULT" "ALTERNATIVE" "SKIN_DETAIL" "SEEDVR"

Responses

Request samples

Content type
application/json
{
  • "seed": "string",
  • "mediaId": "string",
  • "createdFromPromptId": "string",
  • "restoreFace": true,
  • "prompt": "string",
  • "strength": 0.1,
  • "upscaleModel": "DEFAULT"
}

Response samples

Content type
application/json
{
  • "promptId": "string",
  • "seed": "string",
  • "promptContainer": {
    }
}

Edit Vagina

Authorizations:
SecuritySchemeApiKeyScheme
query Parameters
serverId
string
Request Body schema: application/json
required
seed
string
mediaId
required
string
createdFromPromptId
required
string
prompt
string <= 300 characters

Responses

Request samples

Content type
application/json
{
  • "seed": "string",
  • "mediaId": "string",
  • "createdFromPromptId": "string",
  • "prompt": "string"
}

Response samples

Content type
application/json
{
  • "promptId": "string",
  • "seed": "string",
  • "promptContainer": {
    }
}

Edit Video Extend

Authorizations:
SecuritySchemeApiKeyScheme
query Parameters
serverId
string
Request Body schema: application/json
required
seed
string^\d{1,18}$

Optional seed for image generation. Must be a numeric string (max 18 digits).

videoExtensionModel
string (VideoExtensionModel)
Enum: "DEFAULT" "VIDEO_WITH_AUDIO"

Model used for extending a video.

Value Name Description
DEFAULT Default No Audio. Input must not contain Audio
VIDEO_WITH_AUDIO Video with Audio With Audio. Input must contain Audio (Recommended)
mediaId
required
string
prompt
required
string [ 1 .. 500 ] characters
createdFromPromptId
string
Array of objects (TemplateRequest) [ 1 .. 5 ] items

Responses

Request samples

Content type
application/json
{
  • "seed": "string",
  • "videoExtensionModel": "DEFAULT",
  • "mediaId": "string",
  • "prompt": "string",
  • "createdFromPromptId": "string",
  • "videoTemplates": [
    ]
}

Response samples

Content type
application/json
{
  • "promptId": "string",
  • "seed": "string",
  • "promptContainer": {
    }
}

Edit Video Increase Fps

Authorizations:
SecuritySchemeApiKeyScheme
query Parameters
serverId
string
Request Body schema: application/json
required
seed
string
mediaId
required
string
createdFromPromptId
string

Responses

Request samples

Content type
application/json
{
  • "seed": "string",
  • "mediaId": "string",
  • "createdFromPromptId": "string"
}

Response samples

Content type
application/json
{
  • "promptId": "string",
  • "seed": "string",
  • "promptContainer": {
    }
}

Create Enhance Image

Authorizations:
SecuritySchemeApiKeyScheme
query Parameters
serverId
string
Request Body schema: application/json
required
seed
string
mediaId
required
string
createdFromPromptId
string
prompt
string <= 500 characters
Default: "convert to realistic photo, perfect skin, photorealistic, fix fingers, amateur photo, avoid plastic look, instagram look"

Responses

Request samples

Content type
application/json
{
  • "seed": "string",
  • "mediaId": "string",
  • "createdFromPromptId": "string",
  • "prompt": "convert to realistic photo, perfect skin, photorealistic, fix fingers, amateur photo, avoid plastic look, instagram look"
}

Response samples

Content type
application/json
{
  • "promptId": "string",
  • "seed": "string",
  • "promptContainer": {
    }
}

Create Face Improve Prompt

Improves the face of an existing image

Authorizations:
SecuritySchemeApiKeyScheme
query Parameters
serverId
string
Request Body schema: application/json
required
seed
string
mediaId
required
string
faceDetails
string
negativeFaceDetails
string
strength
required
integer <int32> [ 1 .. 100 ]
faceIndex
integer <int32>
createdFromPromptId
string
faceModel
string (FaceModel)
Enum: "REALISM" "CREATIVE"

Responses

Request samples

Content type
application/json
{
  • "seed": "string",
  • "mediaId": "string",
  • "faceDetails": "string",
  • "negativeFaceDetails": "string",
  • "strength": 1,
  • "faceIndex": 0,
  • "createdFromPromptId": "string",
  • "faceModel": "REALISM"
}

Response samples

Content type
application/json
{
  • "promptId": "string",
  • "seed": "string",
  • "promptContainer": {
    }
}

Create Image To Video

Create a new prompt for video generation

Authorizations:
SecuritySchemeApiKeyScheme
query Parameters
serverId
string
Request Body schema: application/json
required
seed
string^\d{1,18}$

Optional seed for image generation. Must be a numeric string (max 18 digits).

videoModel
required
string (VideoModel)
Enum: "DEFAULT" "AUDIO" "GROK" "SEEDANCE" "KLING"

Model used for image-to-video generation.

Value Name Description
DEFAULT Creative Standard image-to-video model — versatile, uncensored and works for most scenes. Use templates for more options.
AUDIO Video with Audio Generates video with audio including speech and background audio. Use the script option and templates for best results.
GROK Grok Video with Audio Grok-powered video model with audio and dialog. This model only supports safe (not explicit) content. Not supported on private servers.
SEEDANCE Video Pro Higher-quality, longer video generation with audio and better prompt understanding. Not supported on private servers.
KLING Kling Premium video model with advanced capabilities. This model only supports safe (not explicit) content. Not supported on private servers.
mediaId
required
string

ID of the media (image) to be used as the source for video generation

lastFrameMediaId
string

ID of the media (image) to be used as the last frame in the video

customImage
boolean

Indicates whether a custom image (external image upload) is used for video generation

text
required
string [ 1 .. 1500 ] characters

Text prompt describing the content of the video to be generated

scene
string [ 1 .. 600 ] characters

Scene description to provide additional context for video generation

template
string (ImageToVideoTemplate)
Deprecated
Enum: "TITTY_DROP" "SPIN_360" "MISSIONARY" "BOOB_BOUNCE" "BLOWJOB"
createdFromPromptId
string
Array of objects (TemplateRequest) [ 1 .. 5 ] items
videoLength
string (VideoLength)
Default: "SHORT"
Enum: "SHORT" "MEDIUM" "LONG"

Length of the generated video. SHORT = 5 seconds. MEDIUM = 10 seconds. SHORT is recommended

videoFrameRate
string (VideoFrameRate)
Enum: "LOW" "MEDIUM" "HIGH"
videoQuality
string (VideoQuality)
Enum: "V_480P" "V_720P"

Quality of the generated video. Only applicable to videoModel GROK

motionStrength
integer <int32> [ 0 .. 6 ]

Optional. Adds additional motion to the video. Use it to avoid slow motion look. Only applicable to videoModel DEFAULT.

previewOnly
boolean
Default: false

Optional. If enabled will create a quick low quality preview video which can be used to preview the result before generating the full video. Only applicable to videoModel AUDIO.

fromPreviewSeed
string^\d{1,18}$

Optional. Seed from an previous preview video. Will be used to generate the final video with the same motion and style as the preview video. Only applicable to videoModel AUDIO.

Responses

Request samples

Content type
application/json
{
  • "mediaId": "1234",
  • "text": "She is walking towards the camera and then turns around to show her back, revealing her full body in a sexy pose"
}

Response samples

Content type
application/json
{
  • "promptId": "string",
  • "seed": "string",
  • "promptContainer": {
    }
}

Inpaint

Authorizations:
SecuritySchemeApiKeyScheme
query Parameters
serverId
string
Request Body schema: application/json
required
seed
string
maskMediaId
required
string
originalMediaId
required
string
createdFromPromptId
required
string
strength
required
integer <int32> [ 1 .. 100 ]
prompt
required
string <= 200 characters
negativePrompt
string <= 200 characters

Responses

Request samples

Content type
application/json
{
  • "seed": "string",
  • "maskMediaId": "string",
  • "originalMediaId": "string",
  • "createdFromPromptId": "string",
  • "strength": 1,
  • "prompt": "string",
  • "negativePrompt": "string"
}

Response samples

Content type
application/json
{
  • "promptId": "string",
  • "seed": "string",
  • "promptContainer": {
    }
}

Inpaint Google

Inpaint an image using Google's inpainting model. This model has better capabilities for consistency but can not handle explicit scenes

Authorizations:
SecuritySchemeApiKeyScheme
query Parameters
serverId
string
Request Body schema: application/json
required
seed
string
mediaId
required
string
object (CropArea)
base64Png
string
createdFromPromptId
required
string
prompt
required
string <= 400 characters
googleModel
required
string (GoogleModel)
Enum: "GEMINI_2_5" "GEMINI_3_PRO"

Responses

Request samples

Content type
application/json
{
  • "seed": "string",
  • "mediaId": "string",
  • "cropArea": {
    },
  • "base64Png": "string",
  • "createdFromPromptId": "string",
  • "prompt": "string",
  • "googleModel": "GEMINI_2_5"
}

Response samples

Content type
application/json
{
  • "promptId": "string",
  • "seed": "string",
  • "promptContainer": {
    }
}

Get Pending

Get pending prompts in the user's queue

Authorizations:
SecuritySchemeApiKeyScheme

Responses

Response samples

Content type
application/json
{
  • "queue": [
    ]
}

Delete From Queue

Delete a prompt from the user's queue

Authorizations:
SecuritySchemeApiKeyScheme
query Parameters
promptId
required
string

Responses

Upscale Video

Authorizations:
SecuritySchemeApiKeyScheme
query Parameters
serverId
string
Request Body schema: application/json
required
seed
string
videoUpscaleModel
required
string (VideoUpscaleModel)
Enum: "DEFAULT" "HIGH_DETAIL"
mediaId
required
string
createdFromPromptId
string

Responses

Request samples

Content type
application/json
{
  • "seed": "string",
  • "videoUpscaleModel": "DEFAULT",
  • "mediaId": "string",
  • "createdFromPromptId": "string"
}

Response samples

Content type
application/json
{
  • "promptId": "string",
  • "seed": "string",
  • "promptContainer": {
    }
}

Create Character Expression Video

Authorizations:
SecuritySchemeApiKeyScheme
query Parameters
serverId
string
Request Body schema: application/json
required
seed
string
mediaId
required
string
videoExpression
required
string (VideoExpression)
Enum: "SMILE_BIG" "SMILE_SMALL" "MOAN_EYES_OPEN" "MOAN_EYES_CLOSED" "KISS" "SHOCKED"
createdFromPromptId
string

Responses

Request samples

Content type
application/json
{
  • "seed": "string",
  • "mediaId": "string",
  • "videoExpression": "SMILE_BIG",
  • "createdFromPromptId": "string"
}

Response samples

Content type
application/json
{
  • "promptId": "string",
  • "seed": "string",
  • "promptContainer": {
    }
}

Websocket Prompt Event Example

Unused endpoint to show the Websocket payload for a prompt event. Connect to wss://api.aliveai.app/ws/prompts/{promptId} to receive real-time updates for the prompt.

Authorizations:
ApiKeyScheme

Responses

Response samples

Content type
application/json
{
  • "promptId": "string",
  • "progress": 0,
  • "isComplete": true,
  • "promptContainer": {
    },
  • "isError": true,
  • "isSystem": true,
  • "message": "string",
  • "errorType": "UNKNOWN",
  • "queuePosition": 0,
  • "created": "2022-03-10T16:15:50Z"
}

Websocket User Event Example

Unused endpoint to show the Websocket payload for a user event. Connect to wss://api.aliveai.app/ws/users/r9orK?token={bearerToken} to receive real-time updates for the user queue.

Authorizations:
ApiKeyScheme

Responses

Response samples

Content type
application/json
{
  • "eventType": "QUEUE_CHANGE",
  • "queue": [
    ],
  • "promptId": "string"
}

Upload Resource

Upload File

Upload a file to the server. Returns a mediaId which can be used to reference the file later.

Authorizations:
SecuritySchemeApiKeyScheme
Request Body schema: multipart/form-data
required
name
string
image
string <binary>

Responses

Response samples

Content type
application/json
{
  • "mediaId": "string",
  • "mediaType": "IMAGE"
}

Chat Quick Message Resource

Create Quick Message

Creates a new message suggestion for a existing conversation

Authorizations:
SecuritySchemeApiKeyScheme
Request Body schema: application/json
required
userMessage
required
string

Last user message

assistantMessage
required
string

Last assistant message

Responses

Request samples

Content type
application/json
{
  • "userMessage": "string",
  • "assistantMessage": "string"
}

Response samples

Content type
application/json
{
  • "quickMessages": [
    ]
}

Clothes Resource

Get Public Clothes

Get all public clothes

Authorizations:
SecuritySchemeApiKeyScheme

Responses

Response samples

Content type
application/json
[
  • {
    }
]

Get Custom Clothes

Get custom clothes

Authorizations:
SecuritySchemeApiKeyScheme

Responses

Response samples

Content type
application/json
[
  • {
    }
]

Get Custom Clothes

Get custom clothes by ID

Authorizations:
SecuritySchemeApiKeyScheme
path Parameters
clothesId
required
string

Responses

Response samples

Content type
application/json
{
  • "clothesId": "string",
  • "clothesPrompt": "string",
  • "clothesImageUrl": "string"
}

Delete Custom Clothes

Delete custom clothes

Authorizations:
SecuritySchemeApiKeyScheme
path Parameters
clothesId
required
string

Responses

Llm Resource

Generate Character Builder Prompt

Creates an extended text prompt for the character builder

Authorizations:
SecuritySchemeApiKeyScheme
Request Body schema: application/json
required
model
required
string (LlmModel)
Enum: "QWEN3_235B" "QWEN3_8B" "GROK" "MISTRAL" "RAW"
object

A map of attributes to be included in the prompt (hairColor, bodyShape, etc.). Each key is the attribute name and the value is the attribute value. The keys must be between 2 and 250 characters long.

Responses

Request samples

Content type
application/json
{
  • "model": "QWEN3_235B",
  • "attributes": {
    }
}

Response samples

Content type
application/json
{
  • "promptText": "string"
}

Generate Character Prompt

Creates an extended text prompt for a character (for a trainer or imported profile)

Authorizations:
SecuritySchemeApiKeyScheme
Request Body schema: application/json
required
profileId
required
string
theme
required
string
outfit
required
string
additionalDetails
string

Responses

Request samples

Content type
application/json
{
  • "profileId": "string",
  • "theme": "string",
  • "outfit": "string",
  • "additionalDetails": "string"
}

Response samples

Content type
application/json
{
  • "promptText": "string"
}

Get Clothes Description

Creates an extended text prompt describing clothes based on the provided clothes ID

Authorizations:
SecuritySchemeApiKeyScheme
path Parameters
clothesId
required
string

Responses

Response samples

Content type
application/json
{
  • "promptText": "string"
}

Generate Prompt

Creates an extended text prompt based on the provided input

Authorizations:
SecuritySchemeApiKeyScheme
Request Body schema: application/json
required
model
required
string (Model)
Enum: "DEFAULT" "REALISM" "ANIME" "TEMPORARY" "CHARACTER_CREATOR" "ANIMA" "GROK" "SEEDDANCE" "ZIMAGE" "KREA"

Image Generation model to use.

Value Name Description
DEFAULT Creative v2 Versatile model with strong prompt understanding for realistic or creative characters and scenes.
REALISM Realism (Beta) Advanced model that produces highly photorealistic images with detailed skin and body rendering.
TEMPORARY Limited: Dreamy Realism V2 Limited-time experimental model — try it out and explore the latest AI styles.
CHARACTER_CREATOR Character Creator Build characters step by step by mixing attributes, outfits, scenes and styles.
ANIMA Anima 1.0 Versatile artistic model focused on anime and manga with strong creative capabilities.
GROK Grok Ultra Advanced model for realistic images with great prompt understanding. Does NOT support explicit content. Not available on private servers
ANIME Anime & Cartoon Stylized model for anime, hentai, manga and cartoon-inspired characters and scenes.
SEEDDANCE SeedDance High-quality image generation with strong prompt understanding. Not available on private servers.
ZIMAGE Social Media High-quality realistic images in authentic influencer style, like real Instagram photos.
Krea Krea Uncensored Creative Model with strong prompt understanding
inputPrompt
required
string [ 5 .. 1000 ] characters \S

Responses

Request samples

Content type
application/json
{
  • "model": "DEFAULT",
  • "inputPrompt": "string"
}

Response samples

Content type
application/json
{
  • "promptText": "string"
}

Generate Update Prompt

Creates an extended text prompt based on the provided input

Authorizations:
SecuritySchemeApiKeyScheme
Request Body schema: application/json
required
model
required
string (Model)
Enum: "DEFAULT" "REALISM" "ANIME" "TEMPORARY" "CHARACTER_CREATOR" "ANIMA" "GROK" "SEEDDANCE" "ZIMAGE" "KREA"

Image Generation model to use.

Value Name Description
DEFAULT Creative v2 Versatile model with strong prompt understanding for realistic or creative characters and scenes.
REALISM Realism (Beta) Advanced model that produces highly photorealistic images with detailed skin and body rendering.
TEMPORARY Limited: Dreamy Realism V2 Limited-time experimental model — try it out and explore the latest AI styles.
CHARACTER_CREATOR Character Creator Build characters step by step by mixing attributes, outfits, scenes and styles.
ANIMA Anima 1.0 Versatile artistic model focused on anime and manga with strong creative capabilities.
GROK Grok Ultra Advanced model for realistic images with great prompt understanding. Does NOT support explicit content. Not available on private servers
ANIME Anime & Cartoon Stylized model for anime, hentai, manga and cartoon-inspired characters and scenes.
SEEDDANCE SeedDance High-quality image generation with strong prompt understanding. Not available on private servers.
ZIMAGE Social Media High-quality realistic images in authentic influencer style, like real Instagram photos.
Krea Krea Uncensored Creative Model with strong prompt understanding
inputPrompt
required
string [ 5 .. 1500 ] characters \S
updateInstructions
required
string [ 5 .. 300 ] characters \S

Responses

Request samples

Content type
application/json
{
  • "model": "DEFAULT",
  • "inputPrompt": "string",
  • "updateInstructions": "string"
}

Response samples

Content type
application/json
{
  • "promptText": "string"
}

Generate Update Prompt

Updates an existing prompt from the character builder with new information

Authorizations:
SecuritySchemeApiKeyScheme
Request Body schema: application/json
required
model
required
string (LlmModel)
Enum: "QWEN3_235B" "QWEN3_8B" "GROK" "MISTRAL" "RAW"
oldRequest
required
string
required
object (LlmBuilderPromptRequest)

Responses

Request samples

Content type
application/json
{
  • "model": "QWEN3_235B",
  • "oldRequest": "string",
  • "newRequest": {
    }
}

Response samples

Content type
application/json
{
  • "promptText": "string"
}

Generate Video Prompt

Creates an extended text prompt to be used as a video script

Authorizations:
SecuritySchemeApiKeyScheme
Request Body schema: application/json
required
model
required
string (VideoModel)
Enum: "DEFAULT" "AUDIO" "GROK" "SEEDANCE" "KLING"

Model used for image-to-video generation.

Value Name Description
DEFAULT Creative Standard image-to-video model — versatile, uncensored and works for most scenes. Use templates for more options.
AUDIO Video with Audio Generates video with audio including speech and background audio. Use the script option and templates for best results.
GROK Grok Video with Audio Grok-powered video model with audio and dialog. This model only supports safe (not explicit) content. Not supported on private servers.
SEEDANCE Video Pro Higher-quality, longer video generation with audio and better prompt understanding. Not supported on private servers.
KLING Kling Premium video model with advanced capabilities. This model only supports safe (not explicit) content. Not supported on private servers.
userInput
required
string [ 5 .. 500 ] characters
mediaId
required
string
frameCount
integer <int32>

Responses

Request samples

Content type
application/json
{
  • "model": "DEFAULT",
  • "userInput": "string",
  • "mediaId": "string",
  • "frameCount": 0
}

Response samples

Content type
application/json
{
  • "promptText": "string",
  • "negPrompt": "string"
}

Generate Vision Prompt

Creates an extended text prompt describing an existing image

Authorizations:
SecuritySchemeApiKeyScheme
Request Body schema: application/json
required
mediaId
required
string

Responses

Request samples

Content type
application/json
{
  • "mediaId": "string"
}

Response samples

Content type
application/json
{
  • "promptText": "string"
}

Lora Resource

List By Type

Get all templates (LoRAs) of a specific type

Authorizations:
SecuritySchemeApiKeyScheme
path Parameters
templateType
required
string (TemplateType)
Enum: "IMAGE" "IMAGE_EDIT_CREATIVE" "IMAGE_EDIT_REALISM" "VIDEO" "VIDEO_AUDIO" "ANIMA" "ZIMAGE" "KREA"

Responses

Response samples

Content type
application/json
[
  • {
    }
]

Get By Id

Get a template by its public ID

Authorizations:
SecuritySchemeApiKeyScheme
path Parameters
templateId
required
string

Responses

Response samples

Content type
application/json
{
  • "id": "string",
  • "name": "string",
  • "description": "string",
  • "prompts": [
    ],
  • "templateType": "IMAGE",
  • "isPublic": true,
  • "strength": 10,
  • "supportedModels": [
    ],
  • "medias": [
    ],
  • "public": true
}

Member Resource

Login

Login with email and password

Authorizations:
ApiKeyScheme
Request Body schema: application/json
required
email
required
string\S
password
required
string\S

Responses

Request samples

Content type
application/json
{
  • "email": "string",
  • "password": "string"
}

Response samples

Content type
application/json
{
  • "accessToken": "string"
}

Me

Get current user information

Authorizations:
SecuritySchemeApiKeyScheme

Responses

Response samples

Content type
application/json
{
  • "id": "string",
  • "credits": 0,
  • "email": "string",
  • "apiKey": "string",
  • "emailConfirmed": true,
  • "hasPurchase": true,
  • "approved": true,
  • "premiumExpiration": "2022-03-10T12:15:50-04:00",
  • "created": "2022-03-10T12:15:50-04:00"
}

Poses Resource

Get Poses

Authorizations:
SecuritySchemeApiKeyScheme

Responses

Response samples

Content type
application/json
{
  • "posesStanding": {
    },
  • "posesLying": {
    },
  • "posesAllFours": {
    },
  • "posesKneeling": {
    },
  • "posesSitting": {
    },
  • "posesSquatting": {
    },
  • "posesSuspended": {
    },
  • "posesPorn": {
    }
}

Get Custom Poses

Authorizations:
SecuritySchemeApiKeyScheme

Responses

Response samples

Content type
application/json
[
  • {
    }
]

Get Custom Pose

Authorizations:
SecuritySchemeApiKeyScheme
path Parameters
poseId
required
string

Responses

Response samples

Content type
application/json
{
  • "id": "string",
  • "image": "string",
  • "additionalPrompt": "string"
}

Delete Custom Pose

Authorizations:
SecuritySchemeApiKeyScheme
path Parameters
poseId
required
string

Responses

Profile Resource

Get Profiles For User

Get Profiles

Authorizations:
SecuritySchemeApiKeyScheme
query Parameters
page
required
integer <int32> >= 0
public
boolean

true view all profiles, false view only your profiles

sort
string (ProfileSortType)
Enum: "NEW" "TOP"

Responses

Response samples

Content type
application/json
{
  • "profiles": [
    ],
  • "hasNextPage": true
}